Vision-guided robots and methods of training them

• US 9,434,072 B2
• Filed: 09/17/2012
• Issued: 09/06/2016
• Est. Priority Date: 06/21/2012
• Status: Active Grant

• Current Assignee: Rethink Robotics
• Original Assignee: Rethink Robotics
• Inventors: Buehler, Christopher J., Siracusa, Michael
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Seck, Ababacar
• Application Number:
  US13/621,687
• Publication Number:
  US 20130346348A1
• Time in Patent Office: 1,450 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: B25J 11/0005 Manipulators having means for high-level communication with users, e.g. speech generator, face recognition means
• CPC Class Codes: B25J 13/084 Tactile sensors in general G01L5/16, G01L5/22
• CPC Class Codes: B25J 9/0087 Dual arms double SCARA arms B25J9/043
• CPC Class Codes: B25J 9/163 learning, adaptive, model based, rule based expert control
• CPC Class Codes: B25J 9/1671 characterised by simulation, either to verify existing program or to create and verify new program, CAD/CAM oriented, graphic oriented programming systems
• CPC Class Codes: B25J 9/1676 Avoiding collision or forbidden zones
• CPC Class Codes: B25J 9/1682 Dual arm manipulator; Coordination of several manipulators
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: G05B 19/42 Recording and playback systems, i.e. in which the programme is recorded from a cycle of operations, e.g. the cycle of operations being manually controlled, after which this record is played back on the same machine
• CPC Class Codes: G05B 19/423 Teaching successive positions by walk-through, i.e. the tool head or end effector being grasped and guided directly, with or without servo-assistance, to follow a path
• CPC Class Codes: G05B 2219/39451 Augmented reality for robot programming
• CPC Class Codes: G05B 2219/39466 Hand, gripper, end effector of manipulator
• CPC Class Codes: G05B 2219/40116 Learn by operator observation, symbiosis, show, watch
• CPC Class Codes: G06F 17/00 Digital computing or data processing equipment or methods, specially adapted for specific functions information retrieval, database structures or file system structures therefor G06F16/00
• CPC Class Codes: G06F 18/28 Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06V 10/235 based on user input or interaction
• CPC Class Codes: G06V 30/1914 Determining representative reference patterns, e.g. averaging or distorting patterns; Generating dictionaries, e.g. user dictionaries
• CPC Class Codes: G06V 30/194 : References adjustable by an adaptive method, e.g. learning
• CPC Class Codes: Y02P 90/80 : Management or planning
• CPC Class Codes: Y10S 901/01 : Mobile robot
• CPC Class Codes: Y10S 901/03 : Teaching system
• CPC Class Codes: Y10S 901/09 : Closed loop, sensor feedback controls arm movement
• CPC Class Codes: Y10S 901/31 : Gripping jaw
• CPC Class Codes: Y10S 901/46 : Sensing device
• CPC Class Codes: Y10S 901/47 : Optical

Abstract

Via intuitive interactions with a user, robots may be trained to perform tasks such as visually detecting and identifying physical objects and/or manipulating objects. In some embodiments, training is facilitated by the robot'"'"'s simulation of task-execution using augmented-reality techniques.

Claims

1. A method of training a robot to complete a specified task comprising performing an action on an object, the robot having at least one appendage for manipulating the object and a machine-vision system for capturing images within a camera field of view, the method comprising:

(a) selecting, by the robot, an object in the field of view and displaying the selection on a robot-controlled visual display, the displayed selection including a camera view of the selected object;

(b) overlaying, by the robot, a representation of an end-effector onto the camera view and displaying, on the display, performance of an action on the object by the end-effector;

(c) based on the displayed performance, providing feedback to the robot indicating whether the action is performed correctly, the robot modifying the performance of the action in response to the feedback; and

(d) repeating steps (b) through (c) until the action is performed correctly on the display.

2. The method of claim 1, wherein the robot selects the action from a plurality of stored action templates.

3. The method of claim 1, wherein the end-effector is a gripper and the action comprises gripping the object, the feedback indicating whether the displayed grippers have gripped a proper part of the displayed object.

4. The method of claim 1, wherein the feedback comprises movement of the at least one appendage by the user.

5. A vision-guided robot trainable, via interactions with a human trainer, to complete a specified task comprising performing an action on an object, the robot comprising:

at least one movable appendage comprising an end-effector for performing the action on the object;

a machine-vision system comprising at least one camera for capturing images within a camera field of view and an image-processing module for identifying objects within the captured images;

a user interface comprising (i) a robot-controlled visual display for visually displaying performance of the action on the object in a camera view thereof using a robot-generated graphic representation of the end-effector, and (ii) at least one input device for receiving feedback from the trainer indicating whether the action is performed correctly on the display; and

a control system for modifying performance of the action on the display in response to the feedback until the action is performed correctly on the display.

6. The robot of claim 5, wherein the end-effector is a gripper.

7. The robot of claim 5, wherein the control system comprises a data storage medium for storing a plurality of action templates.

8. The robot of claim 5, wherein the at least one input device comprises the at least one appendage.

9. A robot-implemented method of manipulating objects based on visual recognition thereof, the method comprising causing a robot to execute steps comprising:

(a) selecting an object in a camera field of view;

(b) computationally selecting a visual model from among a plurality of computer-implemented visual models, each of the visual models including an associated algorithm, the associated algorithm for each visual model being distinct from the other algorithms;

(c) using the selected visual model to computationally identify the object based on a stored representation thereof associated with the model;

(d) determining whether an object-specific manipulation routine is stored in association with the stored representation; and

(e) if so, executing the object-specific manipulation routine, and if not, executing a generic manipulation routine.

10. A vision-guided robot for manipulating objects based on visual recognition thereof, the robot comprising:

at least one movable appendage for manipulating objects;

a camera for capturing an image within a camera field of view; and

a control system for (i) computationally selecting a visual model from among a plurality of computer-implemented visual models, each of the visual models including an associated algorithm, the associated algorithm for each visual model being distinct from the other algorithms, (ii) computationally identifying an object in the image based on a representation thereof stored in association with the selected visual model, (iii) determining whether an object-specific manipulation routine is stored in association with the stored representation, and (iv) if so, causing the at least one movably appendage to execute the object-specific manipulation routine, and if not, causing the at least one movable appendage to execute a generic manipulation routine.

11. The robot of claim 10, wherein the control system comprises a data storage medium storing a plurality of visual models and object representations associated therewith.