ROBOTIC AUGMENTATION OF CREATIVE TASKS

• US 20180173192A1
• Filed: 12/19/2016
• Published: 06/21/2018
• Est. Priority Date: 12/19/2016
• Status: Active Grant

• Current Assignee: Autodesk, Inc.
• Original Assignee: Autodesk, Inc.
• Inventors: Atherton, Evan Patrick, Thomasson, David, Conti, Maurice Ugo, Kerrick, Heather
• Granted Patent: US 10,642,244 B2
• Time in Patent Office: Days
• CPC Class Codes: G05B 19/188 characterised by special applications and not provided for in the relevant subclasses, (e.g. making dies, filament winding)
• CPC Class Codes: G05B 19/402 characterised by control arrangements for positioning, e.g. centring a tool relative to a hole in the workpiece, additional detection means to correct position G05B19/19 takes precedence
• CPC Class Codes: G05B 2219/37582 Position, angle of workpiece surface
• CPC Class Codes: G05B 2219/39004 Assisted by automatic control system for certain functions

Abstract

A robot is configured to assist an end-user with creative tasks. While the end-user modifies the work piece, the robot observes the modifications made by the end-user and determines one or more objectives that the end-user may endeavor to accomplish. The robot then determines a set of actions to perform that assist the end-user with accomplishing the objectives.

Claims

1. A computer-implemented method for controlling a robot, the method comprising:

determining, based on sensor data, a first modification that has been applied to a work piece by an end-user;

determining, based on the first modification, a second modification to apply to the work piece, wherein the second modification corresponds to the first modification; and

causing a robot to apply the second modification to the work piece to assist the end-user in modifying the work piece.

2. The computer-implemented method of claim 1, wherein determining the first modification comprises determining a first set of actions executed by the end-user relative to the work piece, and determining the second modification comprises determining a second set of actions that are derived from the first set of actions.

3. The computer implemented method of claim 2, wherein the first set of actions comprises a sequence of repeated operations applied to a first region of the work piece, and the second set of actions comprises the sequence of repeated actions applied to a second region of the work piece.

4. The computer-implemented method of claim 1, wherein the first modification is associated with a first class of operations related to a first theme and the second modification is also associated with the first class of operations.

5. The computer-implemented method of claim 4, further comprising determining the second modification by:

determining the first class of operations via a categorization procedure;

comparing the work piece to one or more other work pieces;

identifying a subset of the one or more other work pieces that is associated with the first theme based on associating the first class of operations with the subset; and

extracting the second modification from the subset of the one or more other work pieces.

6. The computer-implemented method of claim 1, wherein the first modification is associated with a first class of operations related to a first theme, and the second modification is associated with a second class of operations related to a second theme.

7. The computer-implemented method of claim 6, further comprising determining the second modification by:

determining the first class of operations via a categorization procedure;

comparing the work piece to one or more other work pieces;

identifying a subset of the one or more other work pieces that is associated with the second class of operations and includes at least one feature common to the work piece; and

extracting the second modification from the subset of the one or more other work pieces.

8. The computer-implemented method of claim 1, further comprising processing additional information received from the end-user to determine a third modification to the work piece.

9. The computer-implemented method of claim 8, wherein the third modification comprises a first number of actions, and the second modification comprises a second number of actions, and the first number of actions is greater than the second number of actions, and further comprising strengthening at least one weight included in a neural network associated with the robot based on the additional information received from the end-user.

10. The computer-implemented method of claim 8, wherein the third modification comprises a first number of actions, and the second modification comprises a second number of actions, and the first number of actions is less than the second number of actions, and further comprising weakening at least one weight included in a neural network associated with the robot based on the additional information received from the end-user.

11. A non-transitory computer-readable medium that, when executed by a processor, causes the processor to control a robot by performing the steps of:

determining, based on sensor data, a first modification that has been applied to a work piece by an end-user;

determining, based on the first modification, a second modification to apply to the work piece, wherein the second modification corresponds to the first modification; and

causing a robot to apply the second modification to the work piece to assist the end-user in modifying the work piece.

12. The non-transitory computer-readable medium of claim 11, wherein determining the first modification comprises determining a first set of actions executed by the end-user relative to the work piece, and determining the second modification comprises determining a second set of actions that are derived from the first set of actions.

13. The non-transitory computer-readable medium of claim 12, wherein the first set of actions comprises a sequence of repeated operations applied to a first region of the work piece, and the second set of actions comprises the sequence of repeated actions applied to a second region of the work piece.

14. The non-transitory computer-readable medium of claim 11, wherein the first modification is associated with a first class of operations related to a first theme and the second modification is also associated with the first class of operations.

15. The non-transitory computer-readable medium of claim 14, further comprising determining the second modification by:

determining the first class of operations via a categorization procedure;

comparing the work piece to one or more other work pieces;

identifying a subset of the one or more other work pieces that is associated with the first theme based on associating the first class of operations with the subset; and

extracting the second modification from the subset of the one or more other work pieces.

16. The non-transitory computer-readable medium of claim 11, wherein the first modification is associated with a first class of operations related to a first theme, and the second modification is associated with a second class of operations related to a second theme.

17. The non-transitory computer-readable medium of claim 16, further comprising determining the second modification by:

determining the first class of operations via a categorization procedure;

comparing the work piece to one or more other work pieces;

identifying a subset of the one or more other work pieces that is associated with the second class of operations and includes at least one feature common to the work piece; and

extracting the second modification from the subset of the one or more other work pieces.

18. The non-transitory computer-readable medium of claim 11, further comprising receiving feedback from the end-user indicating a correction to be made to the second modification.

19. The non-transitory computer-readable medium of claim 18, further comprising adjusting a neural network associated with the robot to incorporate the correction.

20. A system for controlling a robot, comprising:

a memory storing an application; and

a processor configured to execute the application to;

determine, based on sensor data, a first modification that has been applied to a work piece by an end-user,

determine, based on the first modification, a second modification to apply to the work piece, wherein the second modification corresponds to the first modification, and

cause a robot to apply the second modification to the work piece to assist the end-user in modifying the work piece.