TRAINING AND OPERATING INDUSTRIAL ROBOTS

• US 20130345875A1
• Filed: 09/17/2012
• Published: 12/26/2013
• Est. Priority Date: 06/21/2012
• Status: Active Grant

• Current Assignee: Rethink Robotics
• Original Assignee: Rethink Robotics
• Inventors: Brooks, Rodney, Buehler, Christopher J., DiCicco, Matthew, Ens, Gerry, Siracusa, Michael, Williamson, Matthew M., Huang, Albert
• Granted Patent: US 8,965,580 B2
• Time in Patent Office: Days
• US Class Current: 700/259
• 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

Robots may manipulate objects based on sensor input about the objects and/or the environment in conjunction with data structures representing primitive tasks and, in some embodiments, objects and/or locations associated therewith. The data structures may be created by instantiating respective prototypes during training by a human trainer.

Claims

1. A robot for manipulating objects within an environment based on physical perception thereof, the robot comprising:

at least one appendage for manipulating an object;

a controller for operating the at least one appendage;

a perception system for receiving physical information about the object and the environment from at least one sensor;

an instance database comprising a plurality of instances at least some of which specify tasks to be performed by the appendage on the object, each task specifying an object and an action to be performed thereon and being defined in generic, spatially unspecified terms; and

a task-execution module, responsive to the perception system, for causing the robot to execute the tasks via commands to the controller.

2. The robot of claim 1, wherein the task-execution module generates, on the fly based on the physical information, a trajectory corresponding to the task in a coordinate system associated with the robot.

3. The robot of claim 1, wherein the task-execution module continuously monitors the object and, based thereon, causes the robot appendage to move toward the object without computing trajectory coordinates.

4. The robot of claim 3, wherein the task-execution module causes movement of the robot appendage toward the object to continue as long as a pre-condition associated with the movement is satisfied, as determined by the task execution module based on the monitored object.

5. The robot of claim 4, wherein the pre-condition comprises absence of physical contact between the appendage and the object.

6. The robot of claim 1, wherein the perception system includes at least one camera for acquiring images of the object.

7. The robot of claim 6, wherein the perception system further includes a computer vision system.

8. The robot of claim 1, wherein the perception system includes at least one touch-sensitive detector.

9. A robot-implemented method for manipulating objects within an environment thereof, comprising:

receiving sensor input about at least one of the object or the environment; and

based on (i) the sensor input and (ii) an instance database comprising a plurality of instances specifying tasks to be performed by the robot on the object in generic, spatially unspecified terms, executing at least one of the task instances so as to cause a robot appendage to manipulate the object in accordance therewith.

10. The method of claim 9, wherein executing the task instance comprises generating, on the fly based on the sensor input, a trajectory corresponding thereto in a coordinate system associated with the robot.

11. The method of claim 9, wherein executing the task instance comprises continuously monitoring the object and, based thereon, causing the robot appendage to move toward the object without computing trajectory coordinates.

12. The method of claim 11, wherein executing the task instance comprises determining whether a pre-condition associated therewith is satisfied and, if so, continuing movement toward the object.

13. The method of claim 12, wherein the pre-condition comprises absence of physical contact between the appendage and the object.

14. The method of claim 9, wherein receiving sensor input comprises acquiring images of the object.

15. The method of claim 9, wherein executing the at least one instance comprises instantiating a behavior associated with the instance.

16. The method of claim 15, wherein the behavior comprises a plurality of processor-executable threads having sets of conditions associated therewith, executing the at least one selected instance comprising monitoring the threads for satisfaction of the conditions.

17. The method of claim 16, wherein satisfaction of the conditions triggers transitions between threads.

18. The method of claim 9, further comprising executing at least one behavior preventing collisions of the robot with itself or an object in the environment.