WO2009018538A2 - System and method of three-dimensional pose estimation - Google Patents
System and method of three-dimensional pose estimation Download PDFInfo
- Publication number
- WO2009018538A2 WO2009018538A2 PCT/US2008/071983 US2008071983W WO2009018538A2 WO 2009018538 A2 WO2009018538 A2 WO 2009018538A2 US 2008071983 W US2008071983 W US 2008071983W WO 2009018538 A2 WO2009018538 A2 WO 2009018538A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- dimensional
- image
- runtime
- dimensional models
- object region
- Prior art date
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/35—Nc in input of data, input till input file format
- G05B2219/35315—Projection, two, three section views
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/40—Robotics, robotics mapping to robotics vision
- G05B2219/40543—Identification and location, position of components, objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Definitions
- three-dimensional pose i.e., three- dimensional position and orientation
- three-dimensional pose estimation may be useful in various robotic systems that employ machine-vision.
- the more simplified hybrid approaches introduce a second key problem for visual servoing, which is the need to keep features within the image plane as the robotic system moves.
- Conventional bin picking systems are relatively deficient in at least one of the following: robustness, accuracy, and speed. Robustness is required since there may be no cost savings to the manufacturer if the error rate of correctly picking an object from a bin is not close to zero (as the picking station will still need to be manned). Location accuracy is necessary so that the grasping operation will not fail. And finally, solutions which take too long between picks would slow down entire production lines, and would not be cost effective.
- the machine-vision based system 100 may include a sensor system 102, a robotic system 104, a control system 106 and a network 108 communicatively coupling the sensor system 102, robotic system 104 and control system 106.
- the machine-vision based system 100 may be employed to recognize a pose of and manipulate one or more work pieces, for example one or more objects such as parts 110.
- the parts 110 may be collocated, for example in a container such as a bin 112.
- the image capture device 114 may be mounted for movement relative to the parts 110.
- the image capture device 114 may be mounted to a sensor robotic system 116, which may include a base 116a, one or more arms 116b-116e, and one or more servomotors and other suitable actuators (not shown) which are operable to move the various arms 116b-116e and/or base 116a.
- the sensor robotic system 116 may be include a greater or less number of arms and/or different types of members such that any desirable range of rotational and/or translational movement of the image capture device 114 may be provided.
- the image capture device 114 may be positioned and/or oriented in any desirable pose to capture images of the pile of objects 112. Such permits the capture of images of two or more views of a given part 110, allowing the generation or derivation of three-dimensional data or information regarding the part 110.
- the position and/or orientation or pose of the various components of the sensor robotic system 116 may be known or ascertainable to the control system 106.
- the sensor robotic system 116 may include one or more sensors (e.g., encoders, Reed switches, position sensors, contact switches, accelerometers, etc.) or other devices positioned and configured to sense, measure or otherwise determine information indicative of a current position, speed, acceleration, and/or orientation or pose of the image capture device 114 in a defined coordinate frame (e.g., sensor robotic system coordinate frame, real world coordinate frame, etc.).
- the control system 106 may receive information from the various sensors or devices, and/or from actuators indicating position and/or orientation of the arms 116b-116e.
- control system 106 may maintain the position and/or orientation or pose information based on movements of the arms 116b-116e made from an initial position and/or orientation or pose of the sensor robotic system 116.
- the control system 106 may computationally determine a position and/or orientation or pose of the image capture device 114 with respect to a reference coordinate system 122. Any suitable position and/or orientation or pose determination methods, systems or devices may be used by the various embodiments.
- the reference coordinate system 122 is illustrated for convenience as a Cartesian coordinate system using an x-axis, a y-axis, and a z-axis. Alternative embodiments may employ other reference systems, for example a polar coordinate system.
- the position and/or orientation or pose of the various components of the robotic system 104 may be known or ascertainable to the control system 106.
- the robotic system 104 may include one or more sensors (e.g., encoders, Reed switches, position sensors, contact switches, accelerometers, etc.) or other devices positioned and configured to sense, measure or otherwise determine information indicative of a current position and/or orientation or pose of the end effector 104b in a defined coordinate frame (e.g., robotic system coordinate frame, real world coordinate frame, etc.).
- the control system 106 may receive information from the various sensors or devices, and/or from actuators indicating position and/or orientation of the arms 104c-104e.
- Figure 2 shows a sensor system 202 positioned to capture images of parts 210 which may, for example, be collocated in a bin 212, according to another embodiment.
- the sensor system 202 includes a pair of cameras
- the pair of cameras 214 may be packaged as a stereo sensor (commercially available) or may be separate cameras positioned to provide stereo images. Such permits the capture of stereo images of a given part 210 from two different views, allowing the generation or derivation of three- dimensional data or information regarding the part 210.
- Figure 3 shows a sensor system 302 positioned to capture three- dimensional information or data regarding parts 310 which may, for example, be collocated in a bin 312, according to another embodiment.
- control system 106 may take a variety of forms including one or more controllers, processors, microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) and associated devices and buses.
- DSPs digital signal processors
- ASICs application specific integrated circuits
- FPGAs field programmable gate arrays
- BIOS basic input/output system
- ROM 512 contains basic routines that help transfer information between elements within the user system 104a, such as during start-up. Some embodiments may employ separate buses for data, instructions and power.
- the sensor device logic 532b may include image processing or machine-vision logic to extract features from image data captured by one or more image capture devices 114, 214, 314a, 314b, 414 into two or three-dimensional information, data or models.
- the sensor device logic 532b may also include logic to convert range information captured by the range finding device 316 into three-dimensional information or models of objects.
- the robotic system logic may include logic to convert three- dimensional pose estimations into drive signals to control the robotic system 104 or to provide appropriate information (e.g., transformations) to suitable drivers of the robotic system 104.
- one of the image capture devices 114 may be calibrated relative to a robotic coordinate system, while the other image capture devices 114 are not calibrated.
- extrinsic calibration the relationship (i.e., three-dimensional transformation) between an image sensor coordinate reference frame and an external coordinate system (e.g., robotic system coordinate reference system) is determined, for example by computation.
- extrinsic calibration is performed for at least one image capture devices 114 to a preferred reference coordinate frame, typically that of the robotic system 104.
- An explanation of the preferred extrinsic calibration algorithms and descriptions of the variables to be calculated can be found in commonly assigned U.S. Patent 6,816,755 issued on November 9, 2004 and pending applications Serial No. 10/634,874 and 11/183,228.
- the method may employ any of the many other known techniques for performing the extrinsic calibration.
- Some embodiments may omit extrinsic calibration of the image capture devices 114, for example where the method 600 is employed only to create a comprehensive object model without driving the robotic system 104.
- the machine-vision based system is trained in a training mode or time. In particular, the machine-vision based system 100 is trained to recognize work pieces or objects, for example parts 110. Training is discussed in more detail below with reference to Figures 7-9.
- the machine-vision based system 100 performs three- dimensional pose estimation in at runtime or in a runtime mode. In particular, the machine-vision based system 100 employs reference two-dimensional information or models to identify object regions in an image, and employs reference three-dimensional information or models to determine a three- dimensional pose of an object represented in the object region.
- the three- dimensional pose of the object may be determined based on at least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known.
- Three-dimensional pose estimation is discussed in more detail below with reference to Figures 10-15.
- the machine-vision based system 100 determines a three-dimensional pose of the object ⁇ e.g., part 110) based on the reference three-dimensional information or data, for example the reference three- dimensional model identified at 1008.
- the machine-vision based system 100 determines if additional images or portions thereof will be processed. Control returns to 1004 if additional images or portions thereof will be processed. Otherwise control passes to 1014, where the method 1000 terminates.
- the method 1400 may be suitable for performing the act 1010 of method 1000 ( Figure 10).
- the machine-vision based system 100 determines whether the registration is successful. If the registration is successful, the three-dimensional pose estimation has been found and control passes to 1418 where the method 1400 terminates. In some embodiments, the machine-vision based system 100 may provide a suitable indication regarding the found three- dimensional pose estimation before terminating at 1418. If the registration is unsuccessful, control passes to 1412.
- a plurality of images are successively captured as the image capture device 114 is moved until the pose of an object is determined.
- the process may end upon the robotic system 104 successfully manipulating one or more parts 110.
- the process of successively capturing a plurality of images, and the associated analysis of the image data, determination of three- dimensional pose estimates, and driving of the robotic system 104 continues until a time period expires, referred to as a cycle time or the like.
- the cycle time limits the amount of time that an embodiment may search for an object region of interest. In such situations, it is desirable to end the process, move the image capture device to the start position (or a different start position), and begin the process anew. That is, upon expiration of the cycle time, the process starts over or otherwise resets.
Abstract
A system and method for identifying objects using a machine-vision based system are disclosed. Briefly described, one embodiment is a method that captures a first image of at least one object with an image capture device, processes the first captured image to find an object region based on a reference two-dimensional model and determines a three-dimensional pose estimation based on a reference three-dimensional model that corresponds to the reference two-dimensional model and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known. Thus, two-dimensional information or data is used to segment an image and three-dimensional information or data used to perform three-dimensional pose estimation on a segment of the image.
Description
SYSTEM AND METHOD OF THREE-DIMENSIONAL POSE ESTIMATION
BACKGROUND OF THE INVENTION
Field of the Invention
This disclosure generally relates to systems and methods of three-dimensional pose estimation employing machine vision, for example useful in robotic systems.
Description of the Related Art
The ability to determine a three-dimensional pose (i.e., three- dimensional position and orientation) of an object can be useful in a number of settings. For example, three-dimensional pose estimation may be useful in various robotic systems that employ machine-vision.
One type of machine-vision problem is known as bin picking. Bin picking typically takes the form of identifying an object collocated in a group of identical or similar objects, for example objects such as parts collocated in a bin or other container. Identification may include three-dimensional pose estimation of the object to allow engagement of the object by a robot member and removal of the object from the group of objects.
There are many object recognition methods available for locating complex industrial parts having a large number of machine-vision detectable features. A complex part with a large number of features provides redundancy, and typically can be reliably recognized even when some fraction of the features are not properly detected. However, many parts are simple parts and do not have a sufficient level of redundancy in machine-vision detectable features and/or which have rough edges or other geometric features which are not clear. In addition, the features typically used for recognition, such as edges detected in captured images, are notoriously difficult to extract consistently from image to image when a large number of parts are jumbled together in a bin. The parts therefore cannot be readily located, especially given the potentially
harsh nature of the environment, e.g., uncertain lighting conditions, varying amounts of occlusions, etc.
The problem of recognizing a simple part among many parts lying jumbled in a bin, such that a robotic system is able to grasp and manipulate the part in an industrial or other process, is quite different from the problem of recognizing a complex part having many detectable features. Machine-vision based systems recognizing and locating three-dimensional objects, using either (a) two-dimensional data from a single image or (b) three-dimensional data from stereo images or range scanners, are known. Single image methods can be subdivided into model-based and appearance-based approaches.
The model-based approaches suffer from difficulties in feature extraction under harsh lighting conditions, including significant shadowing and specularities. Furthermore, simple parts do not contain a large number of machine-vision detectable features, which degrades the accuracy of a model- based fit to noisy image data.
The appearance-based approaches have no knowledge of the underlying three-dimensional structure of the object, merely knowledge of two- dimensional images of the object. These approaches have problems in segmenting out the object for recognition, have trouble with occlusions, and may not provide a three-dimensional pose estimation that is accurate enough for grasping purposes.
Approaches that use three-dimensional data for recognition have somewhat different issues. Lighting effects cause problems for stereo reconstruction, and specularities can create spurious data both for stereo and laser range finders. Once the three-dimensional data is generated, there are the issues of segmentation and representation. On the representation side, more complex models are often used than in the two-dimensional case (e.g., superquadrics). These models contain a larger number of free parameters, which can be difficult to fit to noisy data. Assuming that a part can be located, it must be picked up by the robotic system. The current standard for motion trajectories leading up to the grasping of an identified part is known as image based visual servoing (IBVS).
A key problem for IBVS is that image based servo systems control image error, but do not explicitly consider the physical camera trajectory. Image error results when image trajectories cross near the center of the visual field (i.e., requiring a large scale rotation of the camera). The conditioning of the image Jacobian results in a phenomenon known as camera retreat. Namely, the robotic system is also required to move the camera back and forth along the optical axis direction over a large distance, possibly exceeding the robotic system range of motion. Hybrid approaches decompose the robotic system motion into translational and rotational components either through identifying homeographic relationships between sets of images, which is computationally expensive, or through a simplified approach which separates out the optical axis motion. The more simplified hybrid approaches introduce a second key problem for visual servoing, which is the need to keep features within the image plane as the robotic system moves. Conventional bin picking systems are relatively deficient in at least one of the following: robustness, accuracy, and speed. Robustness is required since there may be no cost savings to the manufacturer if the error rate of correctly picking an object from a bin is not close to zero (as the picking station will still need to be manned). Location accuracy is necessary so that the grasping operation will not fail. And finally, solutions which take too long between picks would slow down entire production lines, and would not be cost effective.
BRIEF SUMMARY OF THE INVENTION
In one aspect, an embodiment of a method of object pose estimation using machine-vision may be summarized as including identifying an object region of an image on which pose estimation is being performed based on a correspondence between at least a portion of a representation of an object in the object region of the image and at least a corresponding one of a plurality of reference two-dimensional models of the object, the object region being a portion of the image that contains the representation of at least a portion of the object; and determining a three-dimensional pose of the object based on at
least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point- to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known.
In another aspect, an embodiment of a computer-readable medium that stores instructions for causing a computer to perform object pose estimation using machine-vision may be summarized as including identifying an object region of an image based on a correspondence between at least a portion of a representation of an object in the object region of the image and at least a corresponding one of a plurality of reference two-dimensional models of the object, the object region being a portion of the image that contains the representation of at least a portion of the object; and determining a three- dimensional pose of the object based on at least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three- dimensional representation of the object region is not necessarily previously known. In further aspect, an embodiment of a system to perform three- dimensional pose estimation may be summarized as including at least one sensor; at least one processor; and at least one memory storing processor executable instructions that cause the at least one processor to segment an image captured by the at least one sensor into a number of object regions based at least in part on a correspondence between at least a portion of a representation of an object in the object region of the image and at least a corresponding one of a plurality of reference two-dimensional models of the object and to cause the at least one processor to determine a three- dimensional pose of the object based on at least one of a plurality of reference three-dimensional models of the object that is related to the corresponding one of the plurality of reference two-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point
relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known.
BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWING(S) In the drawings, identical reference numbers identify similar elements or acts. The sizes and relative positions of elements in the drawings are not necessarily drawn to scale. For example, the shapes of various elements and angles are not drawn to scale, and some of these elements are arbitrarily enlarged and positioned to improve drawing legibility. Further, the particular shapes of the elements as drawn, are not intended to convey any information regarding the actual shape of the particular elements, and have been solely selected for ease of recognition in the drawings.
Figure 1 is an isometric view of a machine-vision based system including a control system, a sensor system and robotic system operating on a bin containing parts, according to one illustrated embodiment, the sensor system including a camera mounted for movement with respect the parts.
Figure 2 is an isometric view of a sensor system according to another illustrated embodiment, the sensor system including a pair of cameras in a stereo configuration positioned to capture stereo images of the parts in the bin.
Figure 3 is an isometric view of a sensor system according to still another illustrated embodiment, the sensor system including at least one camera positioned to capture images of the parts in the bin and a range finding system positioned to determine range information indicative of a distance to parts in the bin.
Figure 4 is an isometric view of a sensor system according to yet another illustrated embodiment, the sensor system including a camera and a structure light system positioned to capture images of the parts in the bin.
Figure 5 is a block diagram illustrating a control system, according to one illustrated embodiment.
Figure 6 is a flow diagram of a method of operating a machine- vision system to perform three-dimensional pose estimation according to one illustrated embodiment, the method including calibrating, training in a training mode or time before a runtime or runtime mode, and three-dimensional pose estimating during the runtime or runtime mode.
Figure 7 is a flow diagram of a method of training a machine- vision system according to one illustrated embodiment, the method including extracting two-dimensional feature information, creating reference two- dimensional models, extracting three-dimensional information and creating reference three-dimensional model.
Figure 8 is a flow diagram of a method of extracting two- and three-dimensional information according to one illustrated embodiment in which the two- and three-dimensional feature information is extracted by accessing an existing computer or digital model of the object. Figure 9 is a flow diagram of a method of extracting two- and three-dimensional information according to another illustrated embodiment in which the two- and three-dimensional feature information is extracted from data sensed from a representative of training object.
Figure 10 is a flow diagram of a method of performing runtime three-dimensional pose estimation according to one illustrated embodiment which includes capturing an image, identifying a object region, identifying a reference three-dimensional model that corresponds to the identified object region, and determining a three-dimensional pose estimation for the object.
Figure 11 is a flow diagram of a method of identifying object regions in an image, according to one illustrated embodiment.
Figure 12 is a flow diagram of a method illustrating types of data on which may be used to identify the object region according to one illustrated embodiment.
Figure 13 is a flow diagram of a method illustrating a variety of approaches for identifying the object region according to one illustrated embodiment.
Figure 14 is a flow diagram of a method of determining a three- dimensional pose estimation for the object according to one illustrated embodiment which includes performing a registration.
Figure 15 is a flow diagram of illustrating a method of performing a registration according to one illustrated embodiment.
DETAILED DESCRIPTION OF THE INVENTION
In the following description, certain specific details are set forth in order to provide a thorough understanding of various embodiments. However, one skilled in the art will understand that the invention may be practiced without these details. In other instances, well-known structures associated with robotic systems, cameras and other image capture devices, range finders, lighting, as well as control systems including computers and networks, have not been shown or described in detail to avoid unnecessarily obscuring descriptions of the embodiments. Unless the context requires otherwise, throughout the specification and claims which follow, the word "comprise" and variations thereof, such as, "comprises" and "comprising" are to be construed in an open, inclusive sense, that is as "including, but not limited to."
Reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Further more, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
As used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the content clearly dictates otherwise. It should also be noted that the term "or" is generally employed in its sense including "and/or" unless the content clearly dictates otherwise.
The headings and Abstract of the Disclosure provided herein are for convenience only and do not interpret the scope or meaning of the embodiments.
Figure 1 shows a machine-vision based system 100, according to one illustrated embodiment.
The machine-vision based system 100 may include a sensor system 102, a robotic system 104, a control system 106 and a network 108 communicatively coupling the sensor system 102, robotic system 104 and control system 106. The machine-vision based system 100 may be employed to recognize a pose of and manipulate one or more work pieces, for example one or more objects such as parts 110. The parts 110 may be collocated, for example in a container such as a bin 112.
While illustrated as a machine-vision based system 100, aspects of the present disclosure may be employed in other systems, for example non- machine-vision based systems. Such non-machine-vision based systems may, for example, take the form of inspection systems. Also, while illustrated as operating in a bin picking environment, aspects of the present disclosure may be employed in other environments, for example non-bin picking environments in which the objects are not collocated or jumbled. As illustrated in Figure 1 , the sensor system 102 includes an image capture device 114. The image capture device 114 may take a variety of forms, for example an analog camera or digital camera. The image capture device 114 may, for example, take the form an array of charge coupled devices (CCDs) or complementary metal oxide semiconductor (CMOS) sensors, a Vidicon and other image capture devices.
In some embodiments, the image capture device 114 may be mounted for movement relative to the parts 110. For example, the image capture device 114 may be mounted to a sensor robotic system 116, which may include a base 116a, one or more arms 116b-116e, and one or more servomotors and other suitable actuators (not shown) which are operable to move the various arms 116b-116e and/or base 116a. It is noted that the sensor robotic system 116 may be include a greater or less number of arms and/or
different types of members such that any desirable range of rotational and/or translational movement of the image capture device 114 may be provided. Accordingly, the image capture device 114 may be positioned and/or oriented in any desirable pose to capture images of the pile of objects 112. Such permits the capture of images of two or more views of a given part 110, allowing the generation or derivation of three-dimensional data or information regarding the part 110.
In typical embodiments, the position and/or orientation or pose of the various components of the sensor robotic system 116 may be known or ascertainable to the control system 106. For example, the sensor robotic system 116 may include one or more sensors (e.g., encoders, Reed switches, position sensors, contact switches, accelerometers, etc.) or other devices positioned and configured to sense, measure or otherwise determine information indicative of a current position, speed, acceleration, and/or orientation or pose of the image capture device 114 in a defined coordinate frame (e.g., sensor robotic system coordinate frame, real world coordinate frame, etc.). The control system 106 may receive information from the various sensors or devices, and/or from actuators indicating position and/or orientation of the arms 116b-116e. Alternatively, or additionally, the control system 106 may maintain the position and/or orientation or pose information based on movements of the arms 116b-116e made from an initial position and/or orientation or pose of the sensor robotic system 116. The control system 106 may computationally determine a position and/or orientation or pose of the image capture device 114 with respect to a reference coordinate system 122. Any suitable position and/or orientation or pose determination methods, systems or devices may be used by the various embodiments. Further, the reference coordinate system 122 is illustrated for convenience as a Cartesian coordinate system using an x-axis, a y-axis, and a z-axis. Alternative embodiments may employ other reference systems, for example a polar coordinate system.
The robotic system 104 may include a base 104a, an end effector 104b, and a plurality of intermediate members 104c-104e. End effector 104b is
illustrated for convenience as a grasping device operable to grasp a selected one of the objects 110 from the pile of objects 110. Any device that can engage a part 110 may be suitable as an end effector device(s).
In typical embodiments, the position and/or orientation or pose of the various components of the robotic system 104 may be known or ascertainable to the control system 106. For example, the robotic system 104 may include one or more sensors (e.g., encoders, Reed switches, position sensors, contact switches, accelerometers, etc.) or other devices positioned and configured to sense, measure or otherwise determine information indicative of a current position and/or orientation or pose of the end effector 104b in a defined coordinate frame (e.g., robotic system coordinate frame, real world coordinate frame, etc.). The control system 106 may receive information from the various sensors or devices, and/or from actuators indicating position and/or orientation of the arms 104c-104e. Alternatively, or additionally, the control system 106 may maintain the position and/or orientation or pose information based on movements of the arms 104c-104e made from an initial position and/or orientation or pose of the robotic system 104. The control system 106 may computationally determine a position and/or orientation or pose of the end effector 104b with respect to a reference coordinate system 122. Any suitable position and/or orientation or pose determination methods, systems or devices may be used by the various embodiments.
Figure 2 shows a sensor system 202 positioned to capture images of parts 210 which may, for example, be collocated in a bin 212, according to another embodiment. In particular, the sensor system 202 includes a pair of cameras
214 to produce stereo images. The pair of cameras 214 may be packaged as a stereo sensor (commercially available) or may be separate cameras positioned to provide stereo images. Such permits the capture of stereo images of a given part 210 from two different views, allowing the generation or derivation of three- dimensional data or information regarding the part 210.
Figure 3 shows a sensor system 302 positioned to capture three- dimensional information or data regarding parts 310 which may, for example, be collocated in a bin 312, according to another embodiment.
In particular, the sensor system 302 includes at least one image capture device 314a, 314b and at least one range finding device 316, which may, for example, include a transmitter 316a and receiver 316b. The range finding device 316 may, for example, take the form of a laser range finding device, infrared range finding device or ultrasonic range finding device. Other range finding devices may be employed. Such permits the capture of images of a given part 310 along with distance data, allowing the generation or derivation of three-dimensional data or information regarding the part 310.
Figure 4 shows a sensor system 402 positioned to capture three- dimensional information or data regarding parts 410 which may, for example, be collocated in a bin 412, according to another embodiment. In particular, the sensor system 402 includes at least one image capture device 414 and structured lighting 418. The structure lighting 418 may, for example, include one or more light sources 418a, 418b. Such permits the capture of images of a given part 410 from two or more different lighting perspectives, allowing the generation or derivation of three-dimensional data or information regarding the part 410.
As will be described in more detail below with reference to Figure 5, the control system 106 may take a variety of forms including one or more controllers, processors, microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) and associated devices and buses.
Discussion of a Suitable Computing Environment
Figure 5 and the following discussion provide a brief, general description of a suitable control system 504 in which the various illustrated embodiments can be implemented. The control system 504 may, for example, implement the control system 106 (Figure 1 ). Although not required, some portion of the embodiments will be described in the general context of
computer-executable instructions or logic, such as program application modules, objects, or macros being executed by a computer. Those skilled in the relevant art will appreciate that the illustrated embodiments as well as other embodiments can be practiced with other computer system configurations, including handheld devices, multiprocessor systems, microprocessor-based or programmable consumer electronics, personal computers ("PCs"), network PCs, minicomputers, mainframe computers, and the like. The embodiments can be practiced in distributed computing environments where tasks or modules are performed by remote processing devices, which are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.
The control system 504 may take the form of a conventional PC, which includes a processing unit 506, a system memory 508 and a system bus 510 that couples various system components including the system memory 508 to the processing unit 506. The control system 504 will at times be referred to in the singular herein, but this is not intended to limit the embodiments to a single system, since in certain embodiments, there will be more than one system or other networked computing device involved. Non-limiting examples of commercially available systems include, but are not limited to, an 80x86 or Pentium series microprocessor from Intel Corporation, U.S.A., a PowerPC microprocessor from IBM, a Sparc microprocessor from Sun Microsystems, Inc., a PA-RISC series microprocessor from Hewlett-Packard Company, or a 68xxx series microprocessor from Motorola Corporation.
The processing unit 506 may be any logic processing unit, such as one or more central processing units (CPUs), microprocessors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), etc. Unless described otherwise, the construction and operation of the various blocks shown in Figure 5 are of conventional design. As a result, such blocks need not be described in further detail herein, as they will be understood by those skilled in the relevant art. The system bus 510 can employ any known bus structures or architectures, including a memory bus with memory controller, a peripheral bus,
and a local bus. The system memory 508 includes read-only memory ("ROM") 512 and random access memory ("RAM") 514. A basic input/output system ("BIOS") 516, which can form part of the ROM 512, contains basic routines that help transfer information between elements within the user system 104a, such as during start-up. Some embodiments may employ separate buses for data, instructions and power.
The control system 504 also includes a hard disk drive 518 for reading from and writing to a hard disk 520, and an optical disk drive 522 and a magnetic disk drive 524 for reading from and writing to removable optical disks 526 and magnetic disks 528, respectively. The optical disk 526 can be a CD or a DVD, while the magnetic disk 528 can be a magnetic floppy disk or diskette. The hard disk drive 518, optical disk drive 522 and magnetic disk drive 524 communicate with the processing unit 506 via the system bus 510. The hard disk drive 518, optical disk drive 522 and magnetic disk drive 524 may include interfaces or controllers (not shown) coupled between such drives and the system bus 510, as is known by those skilled in the relevant art. The drives 518, 522, 524, and their associated computer-readable media 520, 526, 528, provide nonvolatile storage of computer-readable instructions, data structures, program modules and other data for the user system 504. Although the depicted user system 504 employs hard disk 520, optical disk 526 and magnetic disk 528, those skilled in the relevant art will appreciate that other types of computer- readable media that can store data accessible by a computer may be employed, such as magnetic cassettes, flash memory cards, Bernoulli cartridges, RAMs, ROMs, smart cards, etc. Program modules can be stored in the system memory 508, such as an operating system 530, one or more application programs 532, other programs or modules 534, drivers 536 and program data 538.
The application programs 532 may, for example, include pose estimation logic 532a, sensor device logic 532b, and robotic system control logic 532c. The logic 532a-532c may, for example, be stored as one or more executable instructions. As discussed in more detail below, the pose estimation logic 532a may include logic or instructions to perform initialization, training and
runtime three-dimensional pose estimation, and may include matching or registration logic. The sensor device logic 532b may include logic to operate image capture devices, range finding devices, and light sources, such as structured light sources. As discussed in more detail below, the sensor device logic 532b may also include logic to convert information captured by the image capture devices and range finding devices into two-dimensional and/or three- dimensional information or data, for example two dimension and/or three- dimensional models of objects. In particular, the sensor device logic 532b may include image processing or machine-vision logic to extract features from image data captured by one or more image capture devices 114, 214, 314a, 314b, 414 into two or three-dimensional information, data or models. The sensor device logic 532b may also include logic to convert range information captured by the range finding device 316 into three-dimensional information or models of objects. The robotic system logic may include logic to convert three- dimensional pose estimations into drive signals to control the robotic system 104 or to provide appropriate information (e.g., transformations) to suitable drivers of the robotic system 104.
The system memory 508 may also include communications programs 540, for example a server and/or a Web client or browser for permitting the user system 504 to access and exchange data with sources such as Web sites on the Internet, corporate intranets, or other networks as described below. The communications programs 540 in the depicted embodiment is markup language based, such as Hypertext Markup Language (HTML), Extensible Markup Language (XML) or Wireless Markup Language (WML), and operates with markup languages that use syntactically delimited characters added to the data of a document to represent the structure of the document. A number of servers and/or Web clients or browsers are commercially available such as those from Mozilla Corporation of California and Microsoft of Washington. While shown in Figure 5 as being stored in the system memory
508, the operating system 530, application programs 532, other programs/modules 534, drivers 536, program data 538 and browser 540 can be
stored on the hard disk 520 of the hard disk drive 518, the optical disk 526 of the optical disk drive 522 and/or the magnetic disk 528 of the magnetic disk drive 524. A user can enter commands and information into the control system 504 through input devices such as a touch screen or keyboard 542 and/or a pointing device such as a mouse 544. Other input devices can include a microphone, joystick, game pad, tablet, scanner, biomethc scanning device, etc. These and other input devices are connected to the processing unit 506 through an interface 546 such as a universal serial bus ("USB") interface that couples to the system bus 510, although other interfaces such as a parallel port, a game port or a wireless interface or a serial port may be used. A monitor 548 or other display device is coupled to the system bus 510 via a video interface 550, such as a video adapter. Although not shown, the control system 504 can include other output devices, such as speakers, printers, etc.
The control system 504 operates in a networked environment using one or more of the logical connections 502a-502c to communicate with one or more remote computers, servers and/or devices via one or more communications channels, for example a network 514. These logical connections 502a-502c may facilitate any known method of permitting computers to communicate, such as through one or more LANs and/or WANs, such as the Internet. Such networking environments are well known in wired and wireless enterprise-wide computer networks, intranets, extranets, and the Internet. Other embodiments include other types of communication networks including telecommunications networks, cellular networks, paging networks, and other mobile networks. When used in a WAN networking environment, the control system
504 may include a modem 554 for establishing communications over the WAN 514. The modem 554 is shown in Figure 5 as communicatively linked between the interface 546 and the WAN 514. Additionally or alternatively, another device, such as a network interface 552a-552c, that is communicatively linked to the system bus 510, may be used for establishing communications over the WAN 514. In particular, a sensor interface 522a may provide communications with a sensor system {e.g., sensor system 102 of Figure 1 ; sensor system 202
of Figure 2, sensor system 302 of Figure 3; sensor system 402 of Figure 4). A robot interface 552b may provide communications with a robotic system (e.g., robotic system 104 of Figure 1 ). A lighting interface 552c may provide communications with specific lights or a lighting system {e.g., lighting system 418 of Figure 4).
In a networked environment, program modules, application programs, or data, or portions thereof, can be stored in a server computing system (not shown). Those skilled in the relevant art will recognize that the network connections shown in Figure 5 are only some examples of ways of establishing communications between computers, and other connections may be used, including wirelessly.
For convenience, the processing unit 506, system memory 508, and interfaces 546, 552a-552c8 are illustrated as communicatively coupled to each other via the system bus 510, thereby providing connectivity between the above-described components. In alternative embodiments of the control system 504, the above-described components may be communicatively coupled in a different manner than illustrated in Figure 5. For example, one or more of the above-described components may be directly coupled to other components, or may be coupled to each other, via intermediary components (not shown). In some embodiments, system bus 510 is omitted and the components are coupled directly to each other using suitable connections.
Discussion of Exemplary Operation
Operation of an exemplary embodiment of the machine-vision based system 100 will now be described in greater detail. While reference is made throughout the following discuss to the embodiment of Figure 1 , the method may be employed with the other described embodiments, as well as even other embodiments, with or without modification.
Figure 6 shows a method 600 of operating a machine-vision based system 100, according to one illustrated embodiment. The method 600 starts at 602. The method 600 may start, for example, when power is supplied to the machine-vision based system 100 or in
response to activation by a user or by an external system, for example the robotic system 104.
At 604, the machine-vision based system 100 and in particular the sensor system 102 are calibrated in a setup mode or time. The setup mode or time typically occurs before a training mode or time, and before a runtime or runtime mode. The calibration 604 may include intrinsic and/or extrinsic calibration of image capture devices 114 as well as calibration of range finding devices 316 and/or lighting 418. The calibration 604 may include any one or more of a variety of acts or operations. For example, intrinsic calibration may be performed for all the image capture devices 114, and may involve the determination of the internal parameters such as focal length, image sensor center and distortion factors. An explanation of the preferred calibration algorithms and descriptions of the variables to be calculated can be found in commonly assigned U.S. Patent 6,816,755 issued on November 9, 2004, and pending applications Serial No. 10/634,874 and 11 /183,228. The method 600 may employ any of the many other known techniques for performing the intrinsic calibration. In some embodiments, the intrinsic calibration of the image capture devices 114 may be performed before installation in the field. In such situations, the calibration data is stored and provided for each image capture devices 114. It is also possible to use typical internal parameters for a specific image sensor, for example parameters associate with particular camera model-lens combinations. Where a pair of cameras 314 are in a stereo configuration, camera-to-camera calibration may be performed. For example, extrinsic calibration may be preformed by determining the pose of one or more of the image capture devices 114. For example, one of the image capture devices 114 may be calibrated relative to a robotic coordinate system, while the other image capture devices 114 are not calibrated. Through extrinsic calibration the relationship (i.e., three-dimensional transformation) between an image sensor coordinate reference frame and an external coordinate system (e.g., robotic system coordinate reference system) is determined, for example by computation. In at least one embodiment,
extrinsic calibration is performed for at least one image capture devices 114 to a preferred reference coordinate frame, typically that of the robotic system 104. An explanation of the preferred extrinsic calibration algorithms and descriptions of the variables to be calculated can be found in commonly assigned U.S. Patent 6,816,755 issued on November 9, 2004 and pending applications Serial No. 10/634,874 and 11/183,228. The method may employ any of the many other known techniques for performing the extrinsic calibration.
Some embodiments may omit extrinsic calibration of the image capture devices 114, for example where the method 600 is employed only to create a comprehensive object model without driving the robotic system 104. At 606, the machine-vision based system is trained in a training mode or time. In particular, the machine-vision based system 100 is trained to recognize work pieces or objects, for example parts 110. Training is discussed in more detail below with reference to Figures 7-9. At 608, the machine-vision based system 100 performs three- dimensional pose estimation in at runtime or in a runtime mode. In particular, the machine-vision based system 100 employs reference two-dimensional information or models to identify object regions in an image, and employs reference three-dimensional information or models to determine a three- dimensional pose of an object represented in the object region. The three- dimensional pose of the object may be determined based on at least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known. Three-dimensional pose estimation is discussed in more detail below with reference to Figures 10-15.
Optionally, at 610 the machine-vision based system 100 drives the robotic system 102. For example, the machine-vision based system may provide control signals to the robotic system or to an intermediary robotic system controller to cause the robotic system to move from one pose to another pose. The signals may, for example, encode a transformation.
The method 600 terminates at 612. The method 600 may terminate, for example, in response to a disabling of the machine-vision based system 100 by a user, the interruption of power, or an absence of parts 110 in an image of the bin 112. Figure 7 shows a method of training 700 the machine-vision based system 100, according to one illustrated embodiment. Training refers to the process whereby a training, sample, or reference object (e.g., part 110) and its attributes are introduced to the machine-vision system 100. During the training process, various views of the training object are captured or acquired and various landmark features are selected whose geometrical properties are determined and stored. In some embodiments the views may be stored along with sparse model information, while in other embodiments feature information extracted from the views may be stored along with the sparse model information. The method 700 starts at 702, for example in response to an appropriate input by a user. The method 700 may be performed manually, automatically or a combination of manually and automatically.
Optionally at 704, the image sensor 114 captures an image of a first view of a work piece or training object such as a part 110. As explained below, some embodiments may employ existing information, for example existing digital models of the object or existing images of the object for training. At 706, an object region is identified, the object region including a representation of at least a portion of the training object. The object region may be identified manually or automatically or a combination of manually and automatically, for example by application of one or more rules to a computer or digital model of training the object.
At 708, the control system 504 extracts reference two-dimensional information or data, for example in the form of features. The reference two- dimensional information or data may be features that are discernable in the captured image, and which are good subjects for machine-vision algorithms. Alternatively, the reference two-dimensional information or data may be features that are discernable in a two-dimensional projection of a computer
model of the training object. The features may, for example, include points, lines, edges, contours, circles, corners, centers, radia, image patches, etc. In some embodiments, the feature on the object (e.g., part 110) is an artificial feature. The artificial feature may be painted on the object or may be a decal or the like affixed to the object.
The extraction 708 may include the manual identification of suitable features by a user and/or automatic identification of suitable features, for example defined features in a computer model, such as a digital model. As illustrated in Figure 8, extraction 708 of the features may include performing a method 800, which accesses an existing computer digital model {e.g., computer aided design or CAD model) of the part 110 at 802. As illustrated in Figure 9, extraction 708 of the features may include performing a method 800, which employs sensed data or information, for example at 902 accessing the image captured at 704 (Figure 7). At 710, the machine-vision based system 100 creates a reference two-dimensional model using the extracted reference two-dimensional information. The reference two-dimensional model may include information or data representative of some or all of the extracted features. For example, the reference two-dimensional model may include points defining a line, edge or contour, or a point defining a center of an opening and a radius defining a perimeter of the opening. Various approaches to defining and/or storing the reference two-dimensional information representing a feature may be employed.
At 712, the control system 106 extracts reference three- dimensional information or data. For example, the control system 106 may extract reference three-dimensional information or data in the form of a reference three-dimensional point cloud (also referred to as a dense point cloud or stereo dense point cloud) for all or some of the image points in the object region. The reference three-dimensional information may be extracted in a variety of ways, at least partially based on the particular components of the machine-vision based system 100. For example, the machine-vision based
system 100 may employ two or more images of slightly different views of an object such as a part 110. For instance, in the embodiment of Figure 1 , the machine-vision based system 100 may cause the image capture device 114 to capture an image at a first view, then cause the sensor robotic system 116 to move the image capture device 114 to capture an image of the part 110 at second view, to produce a stereo pair of images. The machine-vision based system 100 may perform stereo processing on the stereo pair of images to derive and/or extract the reference three-dimensional data or information. Also for example, in the embodiment of Figure 2, the machine-vision based system 100 may employ the pair of cameras 214 to produce the stereo pair of images, and process the same accordingly to produce a stereo dense point cloud. Suitable packaged stereo pairs of camera 214 with suitable processing software are commercially available from a variety of sources. As a further example, in the embodiment of Figure 3 the machine-vision based system 100 may employ an image captured by the image capture device 314a, 314b along with range finding data or information acquired by the range finding device 316 to derive or extract the reference three-dimensional information or data. Such range finding information or data may, for example, be determined using laser triangulation or laser time of flight techniques. Such range finding information or data may, for example, be determined using ultrasonic or infrared range finding techniques. As yet a further example, the machine-vision based system 100 embodiment of Figure 4 may employ two or more images captured with different lighting to derive or extract the reference three-dimensional information or data. As an even further example, the machine-vision based system 100 may employ a computer or digital model of the training object to extract the reference three-dimensional information or data.
At 714, the machine-vision based system 100 creates a reference three-dimensional model using the extracted reference three-dimensional information or data. The reference three-dimensional model may include three- dimensional information or data representative of some or all of the extracted reference information or data. For example, the reference three-dimensional model may include a point cloud, dense point cloud, or stereo dense point
cloud. Various approaches to defining and/or storing the reference three- dimensional information or data may be employed.
At 716, the machine-vision based system 100 may store relationships between the reference two- and three-dimensional models. Such may be an explicit act, or may be inherent in the way the reference two- and three-dimensional models are themselves stored. For example, the machine- vision based system 100 may store information that is indicative or reflects the relative pose between the image capture device and the object or part 110, and between the reference two- and three-dimensional models of the particular view.
At 718, the machine-vision based system 100 determines whether additional views of the training object (e.g., training part) are to be trained. Typically, several views of each stable pose of an object (e.g., part 110) are desired. If so, control passes to 720, if not control passes to 722. At 720, the machine-vision based system 100 changes the view of the training object, for example changing the pose of the image capture device 114 with respect to the training object (e.g., training part). The machine-vision based system 100 may change the pose using one or more of a variety of approaches. For example, in the machine-vision based system 100 of the embodiment of Figure 1 , the control system 106 may cause the sensor robot system 116 to move the image capture device 114 with respect to the training part 110. Also for example, in the machine-vision based system 100 of the embodiment of Figure 3, the machine-vision based system 100 may employ multiple image capture devices 314a, 314b which are positioned at various locations to provide different views of the training object (e.g., training part). Alternatively or additionally, the machine-vision based system 100 may cause the training part to be moved, for example where the training part is on a conveyor or table or is held by the end effector 104b of a robotic system 104. At 722, the method 700 terminates. An appropriate indication may be provided to a user, for example prompting the user to enter runtime or the runtime mode. Control may pass back to a calling routine or program, or may automatically or manually enter a runtime routine or program.
Figure 10 shows a method 1000 of performing three-dimensional pose estimation, according to one illustrated embodiment.
The method 1000 starts at 1002 during runtime or in the runtime mode. For example, the method 1000 may start in response to input from a user, the occurrence of the end of the method 700, or the appearance of parts 110.
At 1004, the machine-vision based system 100 captures an image of a location where one or more of the parts 110 may be present. For example, the control system 106 may cause one of the image capture devices 114, 214, 314a, 314b, 414 to capture an image of all or a portion of the parts 110.
At 1006, the machine-vision based system 100 identifies an object region of the captured image based on reference two-dimensional information or data, for example based on at least one of the reference two-dimensional models of the object created during the training mode or time. For example, the control system 106 may employ any one or more of various two-dimensional machine-vision techniques to recognize objects in the image based on the features stored as the reference two-dimensional information or data or reference two-dimensional models. Such techniques may include one or more of correlation based pattern matching, blob analysis, and/or geometric pattern matching, to name a few. Identification of an objection typically means that the object (e.g., part 110) in the object region has a similar pose relative to the sensor (e.g., image capture device 114) as the pose of the training object that produced the particular reference two-dimensional model.
At 1008, the machine-vision based system 100 identifies a corresponding one of the reference three-dimensional information or data, for example one of the reference three-dimensional models of the training object created during training. For example, the control system 106 may rely on the relationship stored 716 at of the method 700. Such may be stored as a relationship in a database, for example as a lookup table. Such may be stored as a logical connection between elements of a record or as a relationship between records of a data structure. Other approaches to storing and retrieving
or otherwise identifying the relationship will be apparent to those of skill in the computing arts.
At 1010, the machine-vision based system 100 determines a three-dimensional pose of the object {e.g., part 110) based on the reference three-dimensional information or data, for example the reference three- dimensional model identified at 1008.
Optionally, at 1012 the machine-vision based system 100 determines if additional images or portions thereof will be processed. Control returns to 1004 if additional images or portions thereof will be processed. Otherwise control passes to 1014, where the method 1000 terminates.
Alternatively, the method 1000 may pass control directly from determining the three-dimensional pose estimation at 1010 to terminating at 1014.
Figure 11 shows a method 1100 of identifying object regions in an image, according to one illustrated embodiment, where the identified object region is a region of the image that contains a representation of at least part of an object. The method 1100 may be suitable for performing the act 1006 of the method 1000 (Figure 10).
The method 1100 starts at 1102, for example called as part of executing act 1006 of the method 1000. At 1104, the machine-vision based system 100 extracts two- dimensional information from a first region of a captured image.
At 1106, the machine-vision based system 100 compares the two- dimensional information or data extracted from the first region of the image to reference two-dimensional information or data {e.g., representing features) such as reference two-dimensional models of the object. Figure 12 shows one method 1200 illustrating some of the types of elements that may be compared as part of the comparison 1106. In particular, the representations of edges, points, and/or image patches in a computer digital two-dimensional representation of the first region of the captured image may be compared with edges, points, and/or image patches in the reference two-dimensional model at 1202. Figure 13 shows one method 1300 of illustrating some of the particular types of comparisons that may be performed on various types of elements. In
particular, the machine-vision based system 100 may computationally perform correlation based pattern matching, blob analysis and/or geometric pattern matching at 1302.
At 1108, the machine-vision based system 100 determines based on the comparison whether the two-dimensional information, data or models of the first region of the captured image match the reference two-dimensional information, data or models within a defined tolerance. If so, an object region containing a representation of at least a portion of an object has been found, and control passes to 1116 where the method 1100 terminates. If not, an object region has not been found and control passes to 1110.
At 1110, the machine-vision based system 100 determines whether there are further portions of the captured image to be analyzed to find object regions. If there are not further portions of the captured image to be analyzed, then the machine-vision based system 100 has determined that the captured image does not include representations of the trained object. The machine-vision based system 100 provides a suitable indication of the lack of objects in the captured image at 1114 and terminates at 1116. If there are further portions of the captured image to be analyzed, control passes to 1112.
At 1112, the machine-vision based system 100 identifies a portion of the captured image that has not been previously analyzed, and returns control to 1104 to repeat the process. The various acts of the method 1100 may be repeated until an object region is located or until it is determined that the captured image does not contain a representation of the object or a time out condition occurs. Figure 14 shows a method 1400 of determining a three- dimensional pose estimation, according to one illustrated embodiment.
The method 1400 may be suitable for performing the act 1010 of method 1000 (Figure 10).
The method 1400 starts at 1402, for example called as part of executing act 1010 of the method 1000.
At 1404, the machine-vision based system 100 extracts three- dimensional information from an object region, for example an object region
identified at 1006 of the method 1000 (Figure 10). For example, the machine- vision system 100 may determine the three-dimensional coordinates for some or all of the points in the object region.
At 1406, the machine-vision based system 100 forms a runtime three-dimensional representation or model of the object region of the image. The runtime three-dimensional representation or model may, for example, take the form of a three-dimensional point cloud of the object region of the image for all or some of the points in the object region.
At 1408, the machine-vision based system 100 performs registration between the reference three-dimensional model of the object region and the runtime three-dimensional representation or model of the object region of the image. Figure 15 shows a method 1500 of performing registration according to one illustrated embodiment. The method 1500 may be suitable for performing the registration 1408 of method 1400 (Figure 14). In particular, at 1502, the machine-vision based system 100 executes an error minimization algorithm to minimize an error between a reference three-dimensional model identified at 1008 of method 1000 (Figure 10) and runtime three-dimensional model, for example by executing an iterative closest point algorithm.
In some embodiments, at least an approximate correspondence may be drawn between points in each of the reference three-dimensional models being compared. The correspondence may, for example, be based on a location where the runtime two-dimensional model is found and the stored relationship between the runtime two-dimensional model and the reference two- dimensional model. Additionally or alternatively, the approximate pose determined as a result of identifying an object region (e.g., 1006 of method 1000) may be used to initialize the comparison or registration process.
At 1410, the machine-vision based system 100 determines whether the registration is successful. If the registration is successful, the three-dimensional pose estimation has been found and control passes to 1418 where the method 1400 terminates. In some embodiments, the machine-vision based system 100 may provide a suitable indication regarding the found three-
dimensional pose estimation before terminating at 1418. If the registration is unsuccessful, control passes to 1412.
At 1412, the machine-vision based system 100 determines whether there are further objects regions to be analyzed and/or whether a number of iterations or amount of time is below a defined limit. If there are no further object regions to be analyzed and/or if the number of iterations or amount of time is not below a defined limit control passes to 1414. At 1414, the machine-vision based system 100 provides a suitable indication that a three- dimensional pose estimation was not found, and the method 1400 terminates at 1418.
If there are further object regions to be analyzed and/or if the number of iterations or amount of time is below a defined limit control passes to 1416. At 1416, the machine-vision based system 100 may return to find another object region of the image to analyze or process, for example returning to 1006 of method 1000 (Figure 10), the method 1400 terminating at 1418.
In the above-described various embodiments, the image capture device 114 was mounted on a member 116c of the sensor robotic system 116. In alternative embodiments, the image capture device 114 may be mounted on a portion of the robotic system 104 or mounted on a non-machine-vision based system, such as a track system, chain/pulley system or other suitable system. In other embodiments, a moveable mirror or the like may be adjustable to provide different views for a fixed image capture device 114.
In the above-described various embodiments, a plurality of images are successively captured as the image capture device 114 is moved until the pose of an object is determined. The process may end upon the robotic system 104 successfully manipulating one or more parts 110. In an alternative embodiment, the process of successively capturing a plurality of images, and the associated analysis of the image data, determination of three- dimensional pose estimates, and driving of the robotic system 104 continues until a time period expires, referred to as a cycle time or the like. The cycle time limits the amount of time that an embodiment may search for an object region of interest. In such situations, it is desirable to end the process, move
the image capture device to the start position (or a different start position), and begin the process anew. That is, upon expiration of the cycle time, the process starts over or otherwise resets.
In other embodiments, if the three-dimensional pose estimation for one or more objects of interest are determined before expiration of the cycle time, the process of capturing images and analyzing captured image information continues so that other objects of interest are identified and/or their respective three-dimensional pose estimates determined. Then, after the current object of interest is engaged, the next object of interest has already been identified and/or its respective three-dimensional pose estimate determined before the start of the next cycle time. Or, the identified next object of interest may be directly engaged without the start of a new cycle time.
In the above-described various embodiments, the control system 106 (Figure 1 ) may employ a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC) and/or a drive board or circuitry, along with any associated memory, such as random access memory (RAM), read only memory (ROM), electrically erasable read only memory (EEPROM), or other memory device storing instructions to control operation.
The above description of illustrated embodiments, including what is described in the Abstract, is not intended to be exhaustive or to limit the invention to the precise forms disclosed. Although specific embodiments of and examples are described herein for illustrative purposes, various equivalent modifications can be made without departing from the spirit and scope of the invention, as will be recognized by those skilled in the relevant art. The teachings provided herein of the invention can be applied to other object recognition systems, not necessarily the exemplary machine-vision based system embodiments generally described above.
The foregoing detailed description has set forth various embodiments of the devices and/or processes via the use of block diagrams, schematics, and examples. Insofar as such block diagrams, schematics, and examples contain one or more functions and/or operations, it will be understood by those skilled in the art that each function and/or operation within such block
diagrams, flowcharts, or examples can be implemented, individually and/or collectively, by a wide range of hardware, software, firmware, or virtually any combination thereof. In one embodiment, the present subject matter may be implemented via Application Specific Integrated Circuits (ASICs). However, those skilled in the art will recognize that the embodiments disclosed herein, in whole or in part, can be equivalently implemented in standard integrated circuits, as one or more computer programs running on one or more computers {e.g., as one or more programs running on one or more computer systems), as one or more programs running on one or more controllers {e.g., microcontrollers) as one or more programs running on one or more processors {e.g., microprocessors), as firmware, or as virtually any combination thereof, and that designing the circuitry and/or writing the code for the software and or firmware would be well within the skill of one of ordinary skill in the art in light of this disclosure. For convenience, the various communications paths are illustrated as hardwire connections. However, one or more of the various paths may employ other communication media, such as, but not limited to, radio frequency (RF) media, optical media, fiber optic media, or any other suitable communication media. In addition, those skilled in the art will appreciate that the control mechanisms taught herein are capable of being distributed as a program product in a variety of forms, and that an illustrative embodiment applies equally regardless of the particular type of signal bearing media used to actually carry out the distribution. Examples of signal bearing media include, but are not limited to, the following: recordable type media such as floppy disks, hard disk drives, CD ROMs, digital tape, and computer memory; and transmission type media such as digital and analog communication links using TDM or IP based communication links {e.g., packet links).
These and other changes can be made to the present systems and methods in light of the above-detailed description. In general, in the following claims, the terms used should not be construed to limit the invention to the specific embodiments disclosed in the specification and the claims, but should be
construed to include all power systems and methods that read in accordance with the claims. Accordingly, the invention is not limited by the disclosure, but instead its scope is to be determined entirely by the following claims.
Claims
1. A method of object pose estimation using machine-vision, comprising: identifying an object region of an image on which pose estimation is being performed based on a correspondence between at least a portion of a representation of an object in the image and at least a corresponding one of a plurality of reference two-dimensional models of the object, the object region being a portion of the image that contains the representation of at least a portion of the object; and determining a three-dimensional pose of the object based on at least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point- to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known.
2. The method of claim 1 wherein identifying an object region of an image includes comparing each of a number of features in a digital representation of the image with a number of features in the corresponding one of the reference two-dimensional models.
3. The method of claim 2 wherein identifying an object region of an image includes comparing each of the number of features in the digital representation of the image to a number of features in successive ones of the reference two-dimensional models until a match is found within a defined tolerance or no match is found among all of the reference two-dimensional models of a set of the reference two-dimensional models.
4. The method of claim 3 wherein comparing a number of features in digital representation of the image to a number of features in successive ones of the reference two-dimensional models includes comparing a representation of at least one of an edge, a point, or an image patch in the digital representation of the image to a representation at least one of an edge, a point, or an image patch in the reference two-dimensional model.
5. The method of claim 1 wherein identifying an object region of an image includes computationally performing at least one of correlation based pattern matching, blob analysis, or geometric pattern matching.
6. The method of claim 1 , further comprising: identifying the at least one of the plurality of reference three- dimensional models of the object based on the at least corresponding one of the reference two-dimensional models of the object.
7. The method of claim 6 wherein identifying at least one of the plurality of reference three-dimensional models of the object based on the at least corresponding one of the reference two-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known includes identifying at least one of the reference three-dimensional models based on a stored relationship between the corresponding one of the reference two-dimensional models and the at least one of the reference three-dimensional models.
8. The method of claim 7 wherein determining a three- dimensional pose of the object based on at least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three- dimensional representation of the object region is not necessarily previously known includes performing a registration between the at least one of the reference three-dimensional models and a digital runtime three-dimensional representation of the object region of the image.
9. The method of claim 8 wherein the digital runtime three- dimensional representation of the object region of the image is a runtime three- dimensional model of the object region of the image and wherein performing a registration between the at least one of the reference three-dimensional models and a digital runtime three-dimensional representation of the object region of the image includes executing an error minimization algorithm to minimize error between the at least one of the reference three-dimensional models and the runtime three-dimensional model of the object region of the image.
10. The method of claim 9 wherein executing an error minimization algorithm includes executing an iterative closest point algorithm.
11. The method of claim 8, further comprising: extracting three-dimensional information from the object region of the image.
12. The method of claim 11 , further comprising: forming the runtime three-dimensional model of the object region of the image from the runtime three-dimensional information extracted from the object region of the image.
13. The method of claim 8, further comprising: providing an indication that the three-dimensional pose of the object has not been found if an outcome of the registration is unsuccessful.
14. The method of claim 1 wherein determining a three- dimensional pose of the object based on at least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three- dimensional representation of the object region is not necessarily previously known includes performing a registration between a set of dense three- dimensional data stored as the at least one reference three-dimensional model and a set of dense three-dimensional data stored as the runtime three- dimensional representation of the object region of the image.
15. The method of claim 1 , further comprising: capturing the image.
16. The method of claim 15 wherein the capturing an image, the identifying an object region of the image and the determining a three- dimensional pose of the object all occur during a runtime mode that follows a training mode.
17. The method of claim 16, further comprising: acquiring the reference two-dimensional models during the training mode.
18. The method of claim 17 wherein acquiring the reference two-dimensional models during the training mode includes at least one of accessing an existing computer model of the object or sensing data from a representative object.
19. The method of claim 17, further comprising: acquiring the reference three-dimensional models during the training mode.
20. The method of claim 19 wherein acquiring the reference three-dimensional models during the training mode includes acquiring information using at least one of a dense stereo sensor system, a laser triangulation system, a laser time of fight system or an ultrasound transducer.
21. The method of claim 19 wherein acquiring the reference three-dimensional models during the training mode includes identifying a portion of the image that contains a digital representation of at least part of the object.
22. The method of claim 21 wherein identifying a portion of the image that contains a digital representation of at least part of the object is performed either manually or automatically.
23. A computer readable medium that stores instructions for causing a computer to perform object pose estimation using machine-vision, by: identifying an object region of an image based on a correspondence between at least a portion of a representation of an object in the object region of the image and at least a corresponding one of a plurality of reference two-dimensional models of the object, the object region being a portion of the image that contains the representation of at least a portion of the object; and determining a three-dimensional pose of the object based on at least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point- to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known.
24. The computer readable medium of claim 23 wherein the instructions cause the computer to perform object pose estimation using machine-vision, further by: extracting two-dimensional information from the object region of the image during a runtime to form a runtime two-dimensional digital model of the object region of the image.
25. The computer readable medium of claim 24 wherein identifying an object region of an image includes comparing each of the number of features in the runtime two-dimensional digital model of the object region of the image to a number of features in successive ones of the reference two- dimensional models until a match within a defined tolerance is found or no match is found among all of the reference two-dimensional models of a set of the reference two-dimensional models.
26. The computer readable medium of claim 24 wherein the instructions cause the computer to perform object pose estimation using machine-vision, further by: extracting three-dimensional information from the object region of the image during the runtime to form a runtime three-dimensional model of the object region of the image.
27. The computer readable medium of claim 26 wherein the instructions cause the computer to perform object pose estimation using machine-vision, further by: identifying the at least one of the plurality of reference three- dimensional models of the object based on a stored relationship between the corresponding one of the reference two-dimensional models and the at least one of the reference three-dimensional models.
28. The computer readable medium of claim 26 wherein determining a three-dimensional pose of the object based on at least one of a plurality of reference three-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three-dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known includes performing a registration between the at least one of the reference three-dimensional models and the runtime three- dimensional model of the object region of the image.
29. The computer readable medium of claim 23 wherein the identifying an object region of the image and the determining a three- dimensional pose of the object all occur during a runtime mode following a training mode.
30. The computer readable medium of claim 29 wherein the instructions cause the computer to perform object pose estimation using machine-vision, further by: acquiring the reference two-dimensional models during the training mode; and acquiring the reference three-dimensional models during the training mode.
31. A system to perform three-dimensional pose estimation, the system comprising: at least one sensor; at least one processor; and at least one memory storing processor executable instructions that cause the at least one processor to segment an image captured by the at least one sensor into a number of object regions based at least in part on a correspondence between at least a portion of a representation of an object in the object region of the image and at least a corresponding one of a plurality of reference two-dimensional models of the object and to cause the at least one processor to determine a three-dimensional pose of the object based on at least one of a plurality of reference three-dimensional models of the object that is related to the corresponding one of the plurality of reference two-dimensional models of the object and a runtime three-dimensional representation of the object region where a point-to-point relationship between the reference three- dimensional models of the object and the runtime three-dimensional representation of the object region is not necessarily previously known.
32. The system of claim 31 wherein the instructions further cause at least one processor to identify the at least one of the plurality of reference three-dimensional models of the object based on a set of stored relationships between a plurality of reference two-dimensional models and the plurality of reference three-dimensional models of the object.
33. The system of claim 31 wherein the at least one sensor includes at least one of an imager mounted for movement, a stereo pair of cameras, and a laser.
34. The system of claim 31 wherein the at least one sensor includes at least one imager mounted for movement with respect to the object.
35. The system of claim 31 wherein the at least one sensor includes at least one imager and at least one of a laser or a set of structured lighting.
36. The system of claim 31 wherein the at least one sensor includes at least one stereo pair of cameras.
37. The system of claim 31 wherein the instructions further cause the at least one processor to provide drive signals to drive a robotic member based on the determined three-dimensional pose estimation.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/833,187 | 2007-08-02 | ||
US11/833,187 US7957583B2 (en) | 2007-08-02 | 2007-08-02 | System and method of three-dimensional pose estimation |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2009018538A2 true WO2009018538A2 (en) | 2009-02-05 |
WO2009018538A3 WO2009018538A3 (en) | 2009-04-09 |
Family
ID=40305294
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2008/071983 WO2009018538A2 (en) | 2007-08-02 | 2008-08-01 | System and method of three-dimensional pose estimation |
Country Status (2)
Country | Link |
---|---|
US (1) | US7957583B2 (en) |
WO (1) | WO2009018538A2 (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012066769A1 (en) * | 2010-11-19 | 2012-05-24 | Canon Kabushiki Kaisha | Information processing apparatus and information processing method |
WO2013192492A1 (en) * | 2012-06-21 | 2013-12-27 | Rethink Robotics, Inc. | Vision-guided robots and methods of training them |
WO2013149916A3 (en) * | 2012-04-03 | 2014-04-10 | Gea Farm Technologies Gmbh | Method and device for optically determining a position and/or orientation of an object in space |
WO2016156667A1 (en) * | 2015-04-01 | 2016-10-06 | Konecranes Global Corporation | Method, load handling device, computer program and computer program product for positioning gripping means |
EP3333803A1 (en) * | 2016-12-12 | 2018-06-13 | HERE Global B.V. | Pose error estimation and localization using static features |
US11403764B2 (en) * | 2020-02-14 | 2022-08-02 | Mujin, Inc. | Method and computing system for processing candidate edges |
FR3135555A1 (en) * | 2022-05-03 | 2023-11-17 | Innodura Tb | Process for gripping objects arranged in bulk |
Families Citing this family (116)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008036354A1 (en) | 2006-09-19 | 2008-03-27 | Braintech Canada, Inc. | System and method of determining object pose |
WO2008076942A1 (en) * | 2006-12-15 | 2008-06-26 | Braintech Canada, Inc. | System and method of identifying objects |
US8368721B2 (en) * | 2007-10-06 | 2013-02-05 | Mccoy Anthony | Apparatus and method for on-field virtual reality simulation of US football and other sports |
EP2201495B1 (en) * | 2007-10-12 | 2013-03-27 | MVTec Software GmbH | Computer vision cad models |
US20090306825A1 (en) * | 2008-04-21 | 2009-12-10 | Ying Li | Manipulation system and method |
CA2666256C (en) * | 2008-05-23 | 2015-12-29 | National Research Council Of Canada | Deconvolution-based structured light system with geometrically plausible regularization |
US20100030365A1 (en) * | 2008-07-30 | 2010-02-04 | Pratt & Whitney | Combined matching and inspection process in machining of fan case rub strips |
US8559699B2 (en) * | 2008-10-10 | 2013-10-15 | Roboticvisiontech Llc | Methods and apparatus to facilitate operations in image based systems |
JP2010115723A (en) * | 2008-11-11 | 2010-05-27 | Seiko Epson Corp | Robot and robot system |
US8437537B2 (en) * | 2009-03-27 | 2013-05-07 | Mitsubishi Electric Research Laboratories, Inc. | Method and system for estimating 3D pose of specular objects |
US8503720B2 (en) | 2009-05-01 | 2013-08-06 | Microsoft Corporation | Human body pose estimation |
JP5333344B2 (en) * | 2009-06-19 | 2013-11-06 | 株式会社安川電機 | Shape detection apparatus and robot system |
JP5127787B2 (en) * | 2009-07-30 | 2013-01-23 | 富士フイルム株式会社 | Compound eye photographing apparatus and control method thereof |
JP5382436B2 (en) * | 2009-08-03 | 2014-01-08 | ソニー株式会社 | Data processing apparatus, data processing method, and program |
US9595108B2 (en) * | 2009-08-04 | 2017-03-14 | Eyecue Vision Technologies Ltd. | System and method for object extraction |
EP2462537A1 (en) | 2009-08-04 | 2012-06-13 | Eyecue Vision Technologies Ltd. | System and method for object extraction |
EP2339537B1 (en) * | 2009-12-23 | 2016-02-24 | Metaio GmbH | Method of determining reference features for use in an optical object initialization tracking process and object initialization tracking method |
JP2011175477A (en) * | 2010-02-24 | 2011-09-08 | Canon Inc | Three-dimensional measurement apparatus, processing method and program |
JP5525953B2 (en) * | 2010-07-29 | 2014-06-18 | 株式会社キーエンス | Dimension measuring apparatus, dimension measuring method and program for dimension measuring apparatus |
US9599461B2 (en) | 2010-11-16 | 2017-03-21 | Ectoscan Systems, Llc | Surface data acquisition, storage, and assessment system |
US11880178B1 (en) | 2010-11-16 | 2024-01-23 | Ectoscan Systems, Llc | Surface data, acquisition, storage, and assessment system |
JP5839971B2 (en) * | 2010-12-14 | 2016-01-06 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
JP5769411B2 (en) * | 2010-12-15 | 2015-08-26 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
US8942917B2 (en) | 2011-02-14 | 2015-01-27 | Microsoft Corporation | Change invariant scene recognition by an agent |
US9259289B2 (en) * | 2011-05-13 | 2016-02-16 | Intuitive Surgical Operations, Inc. | Estimation of a position and orientation of a frame used in controlling movement of a tool |
US20130041508A1 (en) * | 2011-08-12 | 2013-02-14 | Georgia Tech Research Corporation | Systems and methods for operating robots using visual servoing |
JP5852364B2 (en) * | 2011-08-26 | 2016-02-03 | キヤノン株式会社 | Information processing apparatus, information processing apparatus control method, and program |
US8467596B2 (en) * | 2011-08-30 | 2013-06-18 | Seiko Epson Corporation | Method and apparatus for object pose estimation |
US9978036B1 (en) | 2011-09-14 | 2018-05-22 | Express Scripts Strategic Development, Inc. | Methods and systems for unit of use product inventory |
US8958630B1 (en) * | 2011-10-24 | 2015-02-17 | Google Inc. | System and method for generating a classifier for semantically segmenting an image |
JP2013101045A (en) * | 2011-11-08 | 2013-05-23 | Fanuc Ltd | Recognition device and recognition method of three-dimensional position posture of article |
US8970693B1 (en) * | 2011-12-15 | 2015-03-03 | Rawles Llc | Surface modeling with structured light |
US8965104B1 (en) | 2012-02-10 | 2015-02-24 | Google Inc. | Machine vision calibration with cloud computing systems |
EP2817712B1 (en) * | 2012-02-21 | 2020-08-05 | Amazon Technologies, Inc. | System and method for automatic picking of products in a materials handling facility |
JP2013184257A (en) | 2012-03-08 | 2013-09-19 | Sony Corp | Robot apparatus, method for controlling robot apparatus, and computer program |
JP5977544B2 (en) | 2012-03-09 | 2016-08-24 | キヤノン株式会社 | Information processing apparatus and information processing method |
JP6000579B2 (en) * | 2012-03-09 | 2016-09-28 | キヤノン株式会社 | Information processing apparatus and information processing method |
JP5975685B2 (en) | 2012-03-09 | 2016-08-23 | キヤノン株式会社 | Information processing apparatus and information processing method |
JP5642738B2 (en) * | 2012-07-26 | 2014-12-17 | ファナック株式会社 | Apparatus and method for picking up loosely stacked articles by robot |
DE102012015056A1 (en) * | 2012-07-28 | 2014-02-13 | Bsautomatisierung Gmbh | Robot control device |
JP5469216B2 (en) * | 2012-07-31 | 2014-04-16 | ファナック株式会社 | A device for picking up bulk items by robot |
US10572774B2 (en) | 2012-12-06 | 2020-02-25 | Toyota Motor Engineering & Manufacturing North America. Inc. | Methods and robots for adjusting object detection parameters, object recognition parameters, or both object detection parameters and object recognition parameters |
CN103077372A (en) * | 2012-12-18 | 2013-05-01 | 上海电机学院 | Name card design method and identification system |
DE102012113009A1 (en) * | 2012-12-21 | 2014-06-26 | Jenoptik Robot Gmbh | Method for automatically classifying moving vehicles |
US9857470B2 (en) | 2012-12-28 | 2018-01-02 | Microsoft Technology Licensing, Llc | Using photometric stereo for 3D environment modeling |
US9083960B2 (en) * | 2013-01-30 | 2015-07-14 | Qualcomm Incorporated | Real-time 3D reconstruction with power efficient depth sensor usage |
US9940553B2 (en) * | 2013-02-22 | 2018-04-10 | Microsoft Technology Licensing, Llc | Camera/object pose from predicted coordinates |
US9227323B1 (en) | 2013-03-15 | 2016-01-05 | Google Inc. | Methods and systems for recognizing machine-readable information on three-dimensional objects |
JP2015024453A (en) * | 2013-07-25 | 2015-02-05 | トヨタ自動車株式会社 | Loading determination method, loading method, loading determination device and robot |
JP6245880B2 (en) * | 2013-07-31 | 2017-12-13 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
US9633433B1 (en) | 2013-08-08 | 2017-04-25 | Intellimed Systems, Llc | Scanning system and display for aligning 3D images with each other and/or for detecting and quantifying similarities or differences between scanned images |
CN105916636B (en) * | 2013-10-11 | 2019-08-06 | 睿信科机器人有限公司 | High-precision robot is placed and manipulation |
CN103593658A (en) * | 2013-11-22 | 2014-02-19 | 中国电子科技集团公司第三十八研究所 | Three-dimensional space positioning system based on infrared image recognition |
US9407809B2 (en) * | 2013-11-27 | 2016-08-02 | Qualcomm Incorporated | Strategies for triggering depth sensors and transmitting RGBD images in a cloud-based object recognition system |
JP2015147256A (en) * | 2014-02-04 | 2015-08-20 | セイコーエプソン株式会社 | Robot, robot system, control device, and control method |
KR102081139B1 (en) * | 2014-03-12 | 2020-02-25 | 한국전자통신연구원 | Object peaking system, object detecting device and method thereof |
KR101830249B1 (en) * | 2014-03-20 | 2018-03-29 | 한국전자통신연구원 | Position recognition apparatus and method of mobile object |
CN103927806B (en) * | 2014-04-28 | 2016-08-17 | 深圳市康凯斯信息技术有限公司 | Unlocking system and the method thereof of password authentification is performed based on wireless communication module pairing |
JP5778311B1 (en) * | 2014-05-08 | 2015-09-16 | 東芝機械株式会社 | Picking apparatus and picking method |
CN103985172A (en) * | 2014-05-14 | 2014-08-13 | 南京国安光电科技有限公司 | An access control system based on three-dimensional face identification |
JP6357949B2 (en) * | 2014-07-29 | 2018-07-18 | セイコーエプソン株式会社 | Control system, robot system, and control method |
US9327406B1 (en) | 2014-08-19 | 2016-05-03 | Google Inc. | Object segmentation based on detected object-specific visual cues |
CN107073346A (en) | 2014-09-10 | 2017-08-18 | 孩之宝公司 | Toy system with manually operated scanner |
TWI552597B (en) * | 2014-11-12 | 2016-10-01 | 觸動創意股份有限公司 | System for portable wireless object virtual reality photography and method thereof |
DE102014223167A1 (en) * | 2014-11-13 | 2016-05-19 | Kuka Roboter Gmbh | Determining object-related gripping spaces by means of a robot |
EP3250346B1 (en) * | 2015-01-29 | 2021-08-18 | ABB Schweiz AG | 3d segmentation for robotic applications |
JP6548422B2 (en) * | 2015-03-27 | 2019-07-24 | キヤノン株式会社 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND PROGRAM |
JP6522488B2 (en) * | 2015-07-31 | 2019-05-29 | ファナック株式会社 | Machine learning apparatus, robot system and machine learning method for learning work taking-out operation |
DE102016009030B4 (en) * | 2015-07-31 | 2019-05-09 | Fanuc Corporation | Machine learning device, robot system and machine learning system for learning a workpiece receiving operation |
JP6240689B2 (en) | 2015-07-31 | 2017-11-29 | ファナック株式会社 | Machine learning device, robot control device, robot system, and machine learning method for learning human behavior pattern |
US9830703B2 (en) * | 2015-08-12 | 2017-11-28 | Nvidia Corporation | Model-based three-dimensional head pose estimation |
US10404962B2 (en) * | 2015-09-24 | 2019-09-03 | Intel Corporation | Drift correction for camera tracking |
US10025886B1 (en) | 2015-09-30 | 2018-07-17 | X Development Llc | Methods and systems for using projected patterns to facilitate mapping of an environment |
US10046459B2 (en) * | 2015-11-16 | 2018-08-14 | Abb Schweiz Ag | Three-dimensional visual servoing for robot positioning |
JP6117901B1 (en) * | 2015-11-30 | 2017-04-19 | ファナック株式会社 | Position / orientation measuring apparatus for a plurality of articles and a robot system including the position / orientation measuring apparatus |
JP6582061B2 (en) * | 2016-01-06 | 2019-09-25 | 株式会社日立製作所 | Robot system and control method |
JP6333871B2 (en) * | 2016-02-25 | 2018-05-30 | ファナック株式会社 | Image processing apparatus for displaying an object detected from an input image |
US10452071B1 (en) * | 2016-02-29 | 2019-10-22 | AI Incorporated | Obstacle recognition method for autonomous robots |
US9990685B2 (en) | 2016-03-21 | 2018-06-05 | Recognition Robotics, Inc. | Automated guidance system and method for a coordinated movement machine |
WO2017199261A1 (en) | 2016-05-19 | 2017-11-23 | Deep Learning Robotics Ltd. | Robot assisted object learning vision system |
US10245724B2 (en) * | 2016-06-09 | 2019-04-02 | Shmuel Ur Innovation Ltd. | System, method and product for utilizing prediction models of an environment |
JP6514156B2 (en) * | 2016-08-17 | 2019-05-15 | ファナック株式会社 | Robot controller |
WO2018053430A1 (en) * | 2016-09-16 | 2018-03-22 | Carbon Robotics, Inc. | System and calibration, registration, and training methods |
US10331974B2 (en) * | 2016-11-08 | 2019-06-25 | Nec Corporation | Action recognition system with landmark localization on objects in images using convolutional neural networks |
JP6450788B2 (en) | 2017-02-21 | 2019-01-09 | ファナック株式会社 | Work removal system |
JP2018167334A (en) * | 2017-03-29 | 2018-11-01 | セイコーエプソン株式会社 | Teaching device and teaching method |
EP3605250A4 (en) * | 2017-03-31 | 2020-07-29 | Sony Corporation | Information processing device and information processing method, computer program, and program manufacturing method |
US10600203B2 (en) | 2017-06-06 | 2020-03-24 | CapSen Robotics, Inc. | Three-dimensional scanner with detector pose identification |
US11370111B2 (en) * | 2017-09-20 | 2022-06-28 | Magna International Inc. | System and method for adaptive bin picking for manufacturing |
JP2019058993A (en) * | 2017-09-27 | 2019-04-18 | セイコーエプソン株式会社 | Robot system |
US10436590B2 (en) * | 2017-11-10 | 2019-10-08 | Ankobot (Shanghai) Smart Technologies Co., Ltd. | Localization system and method, and robot using the same |
US11504853B2 (en) | 2017-11-16 | 2022-11-22 | General Electric Company | Robotic system architecture and control processes |
US10060857B1 (en) | 2017-11-16 | 2018-08-28 | General Electric Company | Robotic feature mapping and motion control |
CA3084951A1 (en) | 2017-12-06 | 2019-06-13 | Ectoscan Systems, Llc | Performance scanning system and method for improving athletic performance |
JP6911777B2 (en) * | 2018-01-23 | 2021-07-28 | トヨタ自動車株式会社 | Motion trajectory generator |
CN108416879A (en) * | 2018-03-19 | 2018-08-17 | 西安冠铭科技股份有限公司 | Access control system based on recognition of face and method |
JP6888580B2 (en) * | 2018-04-05 | 2021-06-16 | オムロン株式会社 | Information processing equipment, information processing methods, and programs |
US11287507B2 (en) | 2018-04-30 | 2022-03-29 | The Boeing Company | System and method for testing a structure using laser ultrasound |
US10967507B2 (en) * | 2018-05-02 | 2021-04-06 | X Development Llc | Positioning a robot sensor for object classification |
US11040452B2 (en) * | 2018-05-29 | 2021-06-22 | Abb Schweiz Ag | Depth sensing robotic hand-eye camera using structured light |
JP7182528B2 (en) * | 2018-09-12 | 2022-12-02 | コグネックス・コーポレイション | Method and apparatus for processing image data for machine vision |
US10878299B2 (en) | 2018-09-12 | 2020-12-29 | Cognex Corporation | Methods and apparatus for testing multiple fields for machine vision |
CN109448090B (en) * | 2018-11-01 | 2023-06-16 | 北京旷视科技有限公司 | Image processing method, device, electronic equipment and storage medium |
US10926416B2 (en) * | 2018-11-21 | 2021-02-23 | Ford Global Technologies, Llc | Robotic manipulation using an independently actuated vision system, an adversarial control scheme, and a multi-tasking deep learning architecture |
US11433545B2 (en) | 2019-02-17 | 2022-09-06 | Samsung Electronics Co., Ltd. | Robotic vision |
US11741566B2 (en) * | 2019-02-22 | 2023-08-29 | Dexterity, Inc. | Multicamera image processing |
US10549928B1 (en) | 2019-02-22 | 2020-02-04 | Dexterity, Inc. | Robotic multi-item type palletizing and depalletizing |
EP3946825A1 (en) * | 2019-03-25 | 2022-02-09 | ABB Schweiz AG | Method and control arrangement for determining a relation between a robot coordinate system and a movable apparatus coordinate system |
CN110119698B (en) * | 2019-04-29 | 2021-08-10 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for determining object state |
WO2020261881A1 (en) * | 2019-06-27 | 2020-12-30 | パナソニックIpマネジメント株式会社 | End effector control system and end effector control method |
CN110866977B (en) * | 2019-10-31 | 2023-06-16 | Oppo广东移动通信有限公司 | Augmented reality processing method, device, system, storage medium and electronic equipment |
JP7120512B2 (en) * | 2019-11-22 | 2022-08-17 | Smc株式会社 | Trajectory control device |
CN111031278B (en) * | 2019-11-25 | 2021-02-05 | 广州恒龙信息技术有限公司 | Monitoring method and system based on structured light and TOF |
CN110969660B (en) * | 2019-12-17 | 2023-09-22 | 浙江大学 | Robot feeding system based on three-dimensional vision and point cloud deep learning |
CN113029124B (en) * | 2021-03-03 | 2024-01-16 | 吉林大学 | Three-dimensional attitude position measurement device based on infrared visual guidance and laser ranging |
CN115446836B (en) * | 2022-09-17 | 2023-09-12 | 上海交通大学 | Visual servo method based on mixing of various image characteristic information |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4011437A (en) * | 1975-09-12 | 1977-03-08 | Cincinnati Milacron, Inc. | Method and apparatus for compensating for unprogrammed changes in relative position between a machine and workpiece |
US4187454A (en) * | 1977-04-30 | 1980-02-05 | Tokico Ltd. | Industrial robot |
Family Cites Families (104)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3986007A (en) * | 1975-08-20 | 1976-10-12 | The Bendix Corporation | Method and apparatus for calibrating mechanical-visual part manipulating system |
US4146924A (en) * | 1975-09-22 | 1979-03-27 | Board Of Regents For Education Of The State Of Rhode Island | System for visually determining position in space and/or orientation in space and apparatus employing same |
CA1103803A (en) * | 1978-03-01 | 1981-06-23 | National Research Council Of Canada | Method and apparatus of determining the center of area or centroid of a geometrical area of unspecified shape lying in a larger x-y scan field |
JPS5923467B2 (en) * | 1979-04-16 | 1984-06-02 | 株式会社日立製作所 | Position detection method |
US4373804A (en) * | 1979-04-30 | 1983-02-15 | Diffracto Ltd. | Method and apparatus for electro-optically determining the dimension, location and attitude of objects |
US4305130A (en) * | 1979-05-29 | 1981-12-08 | University Of Rhode Island | Apparatus and method to enable a robot with vision to acquire, orient and transport workpieces |
US4294544A (en) * | 1979-08-03 | 1981-10-13 | Altschuler Bruce R | Topographic comparator |
US4402053A (en) * | 1980-09-25 | 1983-08-30 | Board Of Regents For Education For The State Of Rhode Island | Estimating workpiece pose using the feature points method |
US6317953B1 (en) * | 1981-05-11 | 2001-11-20 | Lmi-Diffracto | Vision target based assembly |
US4654949A (en) * | 1982-02-16 | 1987-04-07 | Diffracto Ltd. | Method for automatically handling, assembling and working on objects |
US5506682A (en) * | 1982-02-16 | 1996-04-09 | Sensor Adaptive Machines Inc. | Robot vision using targets |
US4613942A (en) * | 1982-02-19 | 1986-09-23 | Chen Richard M | Orientation and control system for robots |
US4437114A (en) * | 1982-06-07 | 1984-03-13 | Farrand Optical Co., Inc. | Robotic vision system |
EP0114505B1 (en) | 1982-12-28 | 1987-05-13 | Diffracto Ltd. | Apparatus and method for robot calibration |
US4523809A (en) * | 1983-08-04 | 1985-06-18 | The United States Of America As Represented By The Secretary Of The Air Force | Method and apparatus for generating a structured light beam array |
EP0151417A1 (en) | 1984-01-19 | 1985-08-14 | Hitachi, Ltd. | Method for correcting systems of coordinates in a robot having visual sensor device and apparatus therefor |
US4578561A (en) * | 1984-08-16 | 1986-03-25 | General Electric Company | Method of enhancing weld pool boundary definition |
US5267143A (en) * | 1984-10-12 | 1993-11-30 | Sensor Adaptive Machines, Incorporated | Vision assisted fixture construction |
US4687325A (en) * | 1985-03-28 | 1987-08-18 | General Electric Company | Three-dimensional range camera |
US4879664A (en) * | 1985-05-23 | 1989-11-07 | Kabushiki Kaisha Toshiba | Three-dimensional position sensor and three-dimensional position setting system |
US4791482A (en) * | 1987-02-06 | 1988-12-13 | Westinghouse Electric Corp. | Object locating system |
JPS63288683A (en) * | 1987-05-21 | 1988-11-25 | 株式会社東芝 | Assembling robot |
US5579444A (en) * | 1987-08-28 | 1996-11-26 | Axiom Bildverarbeitungssysteme Gmbh | Adaptive vision-based controller |
JPH01124072A (en) | 1987-11-09 | 1989-05-16 | Seiko Instr & Electron Ltd | Pick and place |
US4942539A (en) * | 1988-12-21 | 1990-07-17 | Gmf Robotics Corporation | Method and system for automatically determining the position and orientation of an object in 3-D space |
JP2710850B2 (en) * | 1989-03-27 | 1998-02-10 | キヤノン株式会社 | Work holding device, work and its storage case |
US4985846A (en) * | 1989-05-11 | 1991-01-15 | Fallon Patrick J | Acoustical/optical bin picking system |
JP2509357B2 (en) * | 1990-01-19 | 1996-06-19 | トキコ株式会社 | Work position detector |
JP2686351B2 (en) | 1990-07-19 | 1997-12-08 | ファナック株式会社 | Vision sensor calibration method |
US5208763A (en) * | 1990-09-14 | 1993-05-04 | New York University | Method and apparatus for determining position and orientation of mechanical objects |
US5083073A (en) * | 1990-09-20 | 1992-01-21 | Mazada Motor Manufacturing U.S.A. Corp. | Method and apparatus for calibrating a vision guided robot |
US5325468A (en) * | 1990-10-31 | 1994-06-28 | Sanyo Electric Co., Ltd. | Operation planning system for robot |
US5212738A (en) * | 1991-04-12 | 1993-05-18 | Martin Marietta Magnesia Specialties Inc. | Scanning laser measurement system |
GB2261069B (en) * | 1991-10-30 | 1995-11-01 | Nippon Denso Co | High speed picking system for stacked parts |
JP2767340B2 (en) * | 1991-12-26 | 1998-06-18 | ファナック株式会社 | 3D position / posture measurement method for objects |
IT1258006B (en) * | 1992-01-13 | 1996-02-20 | Gd Spa | SYSTEM AND METHOD FOR THE AUTOMATIC COLLECTION OF OBJECTS |
US5715166A (en) * | 1992-03-02 | 1998-02-03 | General Motors Corporation | Apparatus for the registration of three-dimensional shapes |
JP2769947B2 (en) * | 1992-05-15 | 1998-06-25 | 株式会社椿本チエイン | Manipulator position / posture control method |
US5499306A (en) * | 1993-03-08 | 1996-03-12 | Nippondenso Co., Ltd. | Position-and-attitude recognition method and apparatus by use of image pickup means |
FR2706345B1 (en) * | 1993-06-11 | 1995-09-22 | Bertin & Cie | Method and device for locating in space a mobile object such as a sensor or a tool carried by a robot. |
US5568593A (en) * | 1994-01-13 | 1996-10-22 | Ethicon, Inc. | Robotic control system for a needle sorting and feeding apparatus |
JP3394322B2 (en) * | 1994-05-19 | 2003-04-07 | ファナック株式会社 | Coordinate system setting method using visual sensor |
US5454775A (en) * | 1994-09-13 | 1995-10-03 | Applied Robotics, Inc. | Automated exchangeable parts feeding system |
CA2172791C (en) * | 1995-03-31 | 2000-11-14 | Teruyoshi Washizawa | Method and apparatus for processing visual information |
ES2145194T3 (en) | 1995-09-15 | 2000-07-01 | Ersu Enis | PROCEDURE TO DETERMINE THE POSITION OF A BODY IN SPACE. |
JP3413694B2 (en) * | 1995-10-17 | 2003-06-03 | ソニー株式会社 | Robot control method and robot |
US5802201A (en) * | 1996-02-09 | 1998-09-01 | The Trustees Of Columbia University In The City Of New York | Robot system with vision apparatus and transparent grippers |
US5988862A (en) * | 1996-04-24 | 1999-11-23 | Cyra Technologies, Inc. | Integrated system for quickly and accurately imaging and modeling three dimensional objects |
US6004016A (en) * | 1996-08-06 | 1999-12-21 | Trw Inc. | Motion planning and control for systems with multiple mobile objects |
US6141863A (en) * | 1996-10-24 | 2000-11-07 | Fanuc Ltd. | Force-controlled robot system with visual sensor for performing fitting operation |
US6064759A (en) * | 1996-11-08 | 2000-05-16 | Buckley; B. Shawn | Computer aided inspection machine |
JP4091124B2 (en) * | 1996-11-26 | 2008-05-28 | ファナック株式会社 | Robot control device with motion path simulation function |
US5974169A (en) * | 1997-03-20 | 1999-10-26 | Cognex Corporation | Machine vision methods for determining characteristics of an object using boundary points and bounding regions |
US5978521A (en) * | 1997-09-25 | 1999-11-02 | Cognex Corporation | Machine vision methods using feedback to determine calibration locations of multiple cameras that image a common object |
DE59703917D1 (en) | 1997-10-22 | 2001-08-02 | Isra Vision Systems Ag | Method for the optical determination of the position of a spatial body |
FR2770317B1 (en) * | 1997-10-24 | 2000-12-08 | Commissariat Energie Atomique | METHOD FOR CALIBRATING THE ORIGINAL POSITION AND ORIENTATION OF ONE OR MORE MOBILE CAMERAS AND ITS APPLICATION TO MEASURING THE THREE-DIMENSIONAL POSITION OF FIXED OBJECTS |
JPH11300670A (en) | 1998-04-21 | 1999-11-02 | Fanuc Ltd | Article picking-up device |
US6549288B1 (en) * | 1998-05-14 | 2003-04-15 | Viewpoint Corp. | Structured-light, triangulation-based three-dimensional digitizer |
US6516092B1 (en) * | 1998-05-29 | 2003-02-04 | Cognex Corporation | Robust sub-model shape-finder |
JP4387476B2 (en) | 1998-07-13 | 2009-12-16 | 株式会社明電舎 | Bin picking position data calibration device |
US6628819B1 (en) * | 1998-10-09 | 2003-09-30 | Ricoh Company, Ltd. | Estimation of 3-dimensional shape from image sequence |
US5959425A (en) * | 1998-10-15 | 1999-09-28 | Fanuc Robotics North America, Inc. | Vision guided automatic robotic path teaching method |
US6459926B1 (en) * | 1998-11-20 | 2002-10-01 | Intuitive Surgical, Inc. | Repositioning and reorientation of master/slave relationship in minimally invasive telesurgery |
DE19855478B4 (en) * | 1998-12-01 | 2006-01-12 | Steinbichler Optotechnik Gmbh | Method and device for optical detection of a contrast line |
JP4794708B2 (en) * | 1999-02-04 | 2011-10-19 | オリンパス株式会社 | 3D position and orientation sensing device |
US6721444B1 (en) * | 1999-03-19 | 2004-04-13 | Matsushita Electric Works, Ltd. | 3-dimensional object recognition method and bin-picking system using the method |
US6341246B1 (en) * | 1999-03-26 | 2002-01-22 | Kuka Development Laboratories, Inc. | Object oriented motion system |
US6424885B1 (en) * | 1999-04-07 | 2002-07-23 | Intuitive Surgical, Inc. | Camera referenced control in a minimally invasive surgical apparatus |
JP3421608B2 (en) | 1999-04-08 | 2003-06-30 | ファナック株式会社 | Teaching model generator |
JP3300682B2 (en) | 1999-04-08 | 2002-07-08 | ファナック株式会社 | Robot device with image processing function |
JP3377465B2 (en) | 1999-04-08 | 2003-02-17 | ファナック株式会社 | Image processing device |
US6415051B1 (en) * | 1999-06-24 | 2002-07-02 | Geometrix, Inc. | Generating 3-D models using a manually operated structured light source |
US6490369B1 (en) * | 1999-07-06 | 2002-12-03 | Fanuc Robotics North America | Method of viewing and identifying a part for a robot manipulator |
US7006236B2 (en) * | 2002-05-22 | 2006-02-28 | Canesta, Inc. | Method and apparatus for approximating depth of an object's placement onto a monitored region with applications to virtual interface devices |
US6748104B1 (en) * | 2000-03-24 | 2004-06-08 | Cognex Corporation | Methods and apparatus for machine vision inspection using single and multiple templates or patterns |
KR20020008848A (en) * | 2000-03-31 | 2002-01-31 | 이데이 노부유끼 | Robot device, robot device action control method, external force detecting device and external force detecting method |
US6392744B1 (en) * | 2000-12-11 | 2002-05-21 | Analog Technologies, Corp. | Range measurement system |
US6841780B2 (en) * | 2001-01-19 | 2005-01-11 | Honeywell International Inc. | Method and apparatus for detecting objects |
US6804416B1 (en) * | 2001-03-16 | 2004-10-12 | Cognex Corporation | Method and system for aligning geometric object models with images |
US7362969B2 (en) * | 2001-05-29 | 2008-04-22 | Lucent Technologies Inc. | Camera model and calibration procedure for omnidirectional paraboloidal catadioptric cameras |
US7061628B2 (en) * | 2001-06-27 | 2006-06-13 | Southwest Research Institute | Non-contact apparatus and method for measuring surface profile |
US7181083B2 (en) * | 2003-06-09 | 2007-02-20 | Eaton Corporation | System and method for configuring an imaging tool |
US6466843B1 (en) * | 2001-10-16 | 2002-10-15 | General Electric Company | Method and apparatus for lifting objects |
US6580971B2 (en) * | 2001-11-13 | 2003-06-17 | Thierica, Inc. | Multipoint inspection system |
JP2005515910A (en) * | 2002-01-31 | 2005-06-02 | ブレインテック カナダ インコーポレイテッド | Method and apparatus for single camera 3D vision guide robotics |
CA2369845A1 (en) * | 2002-01-31 | 2003-07-31 | Braintech, Inc. | Method and apparatus for single camera 3d vision guided robotics |
US7233841B2 (en) * | 2002-04-19 | 2007-06-19 | Applied Materials, Inc. | Vision system |
US6898484B2 (en) * | 2002-05-01 | 2005-05-24 | Dorothy Lemelson | Robotic manufacturing and assembly with relative radio positioning using radio based location determination |
DE10236040A1 (en) | 2002-08-06 | 2004-02-19 | Manz Automation Ag | Gripper or handling device for picking up an object and moving it from one location to another comprises an array of cameras linked to an evaluation and control unit for determination of the object position relative to the gripper |
US7009717B2 (en) * | 2002-08-14 | 2006-03-07 | Metris N.V. | Optical probe for scanning the features of an object and methods therefor |
JP3702257B2 (en) * | 2002-08-23 | 2005-10-05 | ファナック株式会社 | Robot handling device |
JP4004899B2 (en) * | 2002-09-02 | 2007-11-07 | ファナック株式会社 | Article position / orientation detection apparatus and article removal apparatus |
US7277599B2 (en) * | 2002-09-23 | 2007-10-02 | Regents Of The University Of Minnesota | System and method for three-dimensional video imaging using a single camera |
JP3859571B2 (en) * | 2002-10-17 | 2006-12-20 | ファナック株式会社 | 3D visual sensor |
JP3711105B2 (en) * | 2002-12-20 | 2005-10-26 | ファナック株式会社 | 3D measuring device |
SE525108C2 (en) * | 2002-12-30 | 2004-11-30 | Abb Research Ltd | Method and system for programming an industrial robot, computer program product, computer-readable medium and use |
JP3834297B2 (en) * | 2003-05-12 | 2006-10-18 | ファナック株式会社 | Image processing device |
EP1484716A1 (en) | 2003-06-06 | 2004-12-08 | Sony France S.A. | An architecture for self-developing devices |
US6836702B1 (en) * | 2003-06-11 | 2004-12-28 | Abb Ab | Method for fine tuning of a robot program |
US8542219B2 (en) | 2004-01-30 | 2013-09-24 | Electronic Scripting Products, Inc. | Processing pose data derived from the pose of an elongate object |
JP4522140B2 (en) * | 2004-05-14 | 2010-08-11 | キヤノン株式会社 | Index placement information estimation method and information processing apparatus |
WO2006019970A2 (en) * | 2004-07-14 | 2006-02-23 | Braintech Canada, Inc. | Method and apparatus for machine-vision |
EP1938246A4 (en) * | 2005-09-22 | 2011-04-06 | 3M Innovative Properties Co | Artifact mitigation in three-dimensional imaging |
EP1927038A2 (en) * | 2005-09-23 | 2008-06-04 | Braintech Canada, Inc. | System and method of visual tracking |
-
2007
- 2007-08-02 US US11/833,187 patent/US7957583B2/en active Active - Reinstated
-
2008
- 2008-08-01 WO PCT/US2008/071983 patent/WO2009018538A2/en active Application Filing
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4011437A (en) * | 1975-09-12 | 1977-03-08 | Cincinnati Milacron, Inc. | Method and apparatus for compensating for unprogrammed changes in relative position between a machine and workpiece |
US4187454A (en) * | 1977-04-30 | 1980-02-05 | Tokico Ltd. | Industrial robot |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012066769A1 (en) * | 2010-11-19 | 2012-05-24 | Canon Kabushiki Kaisha | Information processing apparatus and information processing method |
EP2834789B1 (en) * | 2012-04-03 | 2020-03-18 | GEA Farm Technologies GmbH | Method and device for optically determining a position and/or orientation of an object in space |
US9576368B2 (en) | 2012-04-03 | 2017-02-21 | Gea Farm Technologies Gmbh | Method and device for optically determining a position and/or orientation of an object in space using a two dimensional image to generate three dimensional information |
WO2013149916A3 (en) * | 2012-04-03 | 2014-04-10 | Gea Farm Technologies Gmbh | Method and device for optically determining a position and/or orientation of an object in space |
US8996175B2 (en) | 2012-06-21 | 2015-03-31 | Rethink Robotics, Inc. | Training and operating industrial robots |
US8965580B2 (en) | 2012-06-21 | 2015-02-24 | Rethink Robotics, Inc. | Training and operating industrial robots |
US8965576B2 (en) | 2012-06-21 | 2015-02-24 | Rethink Robotics, Inc. | User interfaces for robot training |
US8996174B2 (en) | 2012-06-21 | 2015-03-31 | Rethink Robotics, Inc. | User interfaces for robot training |
US9092698B2 (en) | 2012-06-21 | 2015-07-28 | Rethink Robotics, Inc. | Vision-guided robots and methods of training them |
US9434072B2 (en) | 2012-06-21 | 2016-09-06 | Rethink Robotics, Inc. | Vision-guided robots and methods of training them |
US8958912B2 (en) | 2012-06-21 | 2015-02-17 | Rethink Robotics, Inc. | Training and operating industrial robots |
WO2013192492A1 (en) * | 2012-06-21 | 2013-12-27 | Rethink Robotics, Inc. | Vision-guided robots and methods of training them |
US9669544B2 (en) | 2012-06-21 | 2017-06-06 | Rethink Robotics, Inc. | Vision-guided robots and methods of training them |
US9701015B2 (en) | 2012-06-21 | 2017-07-11 | Rethink Robotics, Inc. | Vision-guided robots and methods of training them |
WO2016156667A1 (en) * | 2015-04-01 | 2016-10-06 | Konecranes Global Corporation | Method, load handling device, computer program and computer program product for positioning gripping means |
US10282861B2 (en) | 2016-12-12 | 2019-05-07 | Here Global B.V. | Pose error estimation and localization using static features |
EP3333803A1 (en) * | 2016-12-12 | 2018-06-13 | HERE Global B.V. | Pose error estimation and localization using static features |
US11403764B2 (en) * | 2020-02-14 | 2022-08-02 | Mujin, Inc. | Method and computing system for processing candidate edges |
US20220351389A1 (en) * | 2020-02-14 | 2022-11-03 | Mujin, Inc. | Method and computing system for processing candidate edges |
FR3135555A1 (en) * | 2022-05-03 | 2023-11-17 | Innodura Tb | Process for gripping objects arranged in bulk |
Also Published As
Publication number | Publication date |
---|---|
US20090033655A1 (en) | 2009-02-05 |
US7957583B2 (en) | 2011-06-07 |
WO2009018538A3 (en) | 2009-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US7957583B2 (en) | System and method of three-dimensional pose estimation | |
CN110555889B (en) | CALTag and point cloud information-based depth camera hand-eye calibration method | |
CN108932736B (en) | Two-dimensional laser radar point cloud data processing method and dynamic robot pose calibration method | |
CN111791239B (en) | Method for realizing accurate grabbing by combining three-dimensional visual recognition | |
CN108656107B (en) | Mechanical arm grabbing system and method based on image processing | |
US9616569B2 (en) | Method for calibrating an articulated end effector employing a remote digital camera | |
JP5726378B2 (en) | Method for estimating the pose of an object | |
Marton et al. | General 3D modelling of novel objects from a single view | |
CN110580725A (en) | Box sorting method and system based on RGB-D camera | |
CN112476434A (en) | Visual 3D pick-and-place method and system based on cooperative robot | |
Song et al. | CAD-based pose estimation design for random bin picking using a RGB-D camera | |
CN111693968B (en) | Systematic calibration method for external parameters of vehicle-mounted three-dimensional laser radar system | |
US20080181485A1 (en) | System and method of identifying objects | |
CA2135528A1 (en) | 3-d pose refinement | |
CN114952809A (en) | Workpiece identification and pose detection method and system and grabbing control method of mechanical arm | |
Lambrecht | Robust few-shot pose estimation of articulated robots using monocular cameras and deep-learning-based keypoint detection | |
JP2011044046A (en) | Object recognition device and object recognition method | |
JP2018169660A (en) | Object attitude detection apparatus, control apparatus, robot and robot system | |
Zhou et al. | Design and test of a sorting device based on machine vision | |
US20230173660A1 (en) | Robot teaching by demonstration with visual servoing | |
Haidacher et al. | Estimating finger contact location and object pose from contact measurements in 3d grasping | |
CN101098492A (en) | Method for determining drone target topological relation and camera calibration target capable of disposing arbitrarily | |
Boby | Hand-eye calibration using a single image and robotic picking up using images lacking in contrast | |
CN116309817A (en) | Tray detection and positioning method based on RGB-D camera | |
CN109211222B (en) | High-precision positioning system and method based on machine vision |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 08782597 Country of ref document: EP Kind code of ref document: A2 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 08782597 Country of ref document: EP Kind code of ref document: A2 |