Robotic systems and methods for task scoring and selection

• US 9,969,082 B1
• Filed: 01/05/2016
• Issued: 05/15/2018
• Est. Priority Date: 01/05/2016
• Status: Active Grant

• Current Assignee: Boston Dynamics, Inc. (SoftBank Group Corp.)
• Original Assignee: Boston Dynamics, Inc. (SoftBank Group Corp.)
• Inventors: Berard, Stephen, Swilling, Benjamin, Malchano, Matthew
• Primary Examiner(s): Bendidi, Rachid
• Application Number:
  US14/988,390
• Time in Patent Office: 861 Days
• CPC Class Codes: B25J 9/1661 characterised by task planning, object-oriented languages
• CPC Class Codes: B62D 57/032 with alternately or sequentially lifted supporting base and legs; with alternately or sequentially lifted feet or skid B62D57/024 takes precedence
• CPC Class Codes: Y10S 901/01 Mobile robot
• CPC Class Codes: Y10S 901/02 Arm motion controller
• CPC Class Codes: Y10S 901/27 Arm part
• CPC Class Codes: Y10S 901/30 End effector

Abstract

The present disclosure relates to methods and systems for improving robotic task selection and execution. An example method includes determining an external environment state based on receiving information indicative of at least one aspect of an environment proximate to a robotic system having at least one actuator. The method also includes optionally determining a goal to be accomplished by a robotic system and determining a plurality of possible tasks each including at least one task involving the at least one actuator that may be carried out by the robotic system in pursuance of the goal. For each possible task group, the method includes determining a respective task group score based on an expected performance capability. The expected performance capability is based, at least in part, on the external environment state. The method includes selecting a task group based on the respective task group scores.

Claims

1. A robotic system comprising:

at least one actuator;

a memory configured to contain instructions; and

a processor configured to execute the instructions to perform operations, the operations comprising;

determining an external environment state from information indicative of at least one aspect of an environment proximate to the robotic system;

determining a plurality of possible task groups to be carried out by the robotic system in pursuance of a task-oriented goal, wherein each possible task group comprises at least one task involving actuation of the at least one actuator;

determining, for each possible task group, a respective task group score based on;

an expected performance capability when carrying out the at least one task involving the at least one actuator, wherein the expected performance capability is based on the external environment state and an attribute of the at least one actuator, the attribute of the at least one actuator comprising at least one of a strength of the at least one actuator, a range of motion of the at least one actuator, or an accuracy of the at least one actuator;

a speed factor comprising an execution duration of the possible task group; and

a cost factor comprising at least one of an energy cost associated with the robotic system carrying out the possible task group;

selecting a task group from the plurality of possible task groups based on the plurality of task group scores; and

causing the robotic system to carry out the selected task group.

2. The robotic system of claim 1, wherein the at least one aspect of the environment proximate to the robotic system comprises at least one of:

an obstacle, an object, a living person, or an operating constraint.

3. The robotic system of claim 1, wherein the operations further comprise determining a robot state based on receiving information indicative of at least one aspect of the robotic system, wherein the expected performance capability is further based on the robot state.

4. The robotic system of claim 1 further comprising a robotic appendage having at least one actuator, wherein the at least one actuator comprises a linear actuator or a rotational actuator, and wherein the robotic appendage comprises a robotic arm or a robotic leg.

5. The robotic system of claim 4 further comprising a first robotic appendage having a first actuator and a second robotic appendage having a second actuator, wherein determining the plurality of possible task groups comprises determining at least a first possible task group and a second possible task group, wherein the first possible task group comprises at least one task involving the first actuator, wherein the second possible task group comprises at least one task involving the second actuator, and wherein selecting the task group comprises selecting between at least a first task group score assigned to the first possible task group and a second task group score assigned to the second possible task group.

6. The robotic system of claim 1, wherein determining a plurality of possible task groups comprises determining at least a first possible task group and a second possible task group, wherein the first possible task group comprises at least one task involving a portion of the robotic system moving along a first plane of motion, wherein the second possible task group comprises at least one task involving the portion of the robotic system moving along a second plane of motion, and wherein selecting the task group comprises selecting between at least a first task group score assigned to the first possible task group and a second task group score assigned to the second possible task group.

7. The robotic system of claim 1, wherein determining the respective task group score comprises assigning a numerical value to respective possible task group based on the respective expected performance capability according to a sum of squares algorithm.

8. The robotic system of claim 1, wherein the speed factor comprises a route of the robotic system while carrying out the possible task group.

9. The robotic system of claim 1, wherein determining the respective task group score is further based on a safety factor, wherein the safety factor comprises at least one of:

a safety margin, a proximity to at least one bystander, or a stability of the robotic system while carrying out the possible task group.

10. The robotic system of claim 1, wherein the cost factor comprises a monetary cost associated with the robotic system carrying out the possible task group.

11. The robotic system of claim 1, further comprising four legs, wherein the robotic system is arranged as a quadruped robot.

12. The robotic system of claim 1, further comprising two legs, wherein the robotic system is arranged as a biped robot.

13. A method comprising:

determining, by a processor of a robotic system, an external environment state from information indicative of at least one aspect of an environment proximate to the robotic system, wherein the robotic system comprises at least one actuator;

determining a plurality of possible task groups to be carried out by the robotic system in pursuance of a task-oriented goal, wherein each possible task group comprises at least one task involving actuation of the at least one actuator;

determining, for each possible task group, a respective task group score based on;

an expected performance capability when carrying out the at least one task involving the at least one actuator, wherein the expected performance capability is based on the external environment state and an attribute of the at least one actuator, the attribute of the at least one actuator comprising at least one of a strength of the at least one actuator, a range of motion of the at least one actuator, or an accuracy of the at least one actuator;

a speed factor comprising an execution duration of the possible task group; and

a cost factor comprising at least one of an energy cost associated with the robotic system carrying out the possible task group;

selecting a task group from the plurality of possible task groups based on the plurality of task group scores; and

causing the robotic system to carry out the selected task group.

14. The method of claim 13, wherein the at least one aspect of the environment proximate to the robotic system comprises at least one of:

an obstacle, an object, a living person, or an operating constraint.

15. The method of claim 13, further comprising determining a robot state based on receiving information indicative of at least one aspect of the robotic system, wherein the expected performance capability is further based on the robot state.

16. The method of claim 13, wherein determining the respective task group score comprises assigning a numerical value to the respective possible task group based on the respective expected performance capability according to a sum of squares algorithm.

17. The method of claim 13, wherein the speed factor comprises a route of the robotic system while carrying out the possible task group.

18. The method of claim 13, wherein determining the respective task group score is further based on a safety factor, wherein the safety factor comprises at least one of:

a safety margin, a proximity to at least one bystander, or a stability of the robotic system while carrying out the possible task group.

19. The method of claim 13, wherein the cost factor comprises a monetary cost associated with the robotic system carrying out the possible task group.

20. The method of claim 13, further comprising carrying out the method at a periodic interval of time.

21. The method of claim 13, wherein determining at least one respective task group score is further based on at least one of:

a machine learning process or an empirical scoring process.

22. The method of claim 13, wherein the robotic system further comprises a first robotic appendage having a first actuator and a second robotic appendage having a second actuator, wherein determining the plurality of possible task groups comprises determining at least a first possible task group and a second possible task group, wherein the first possible task group comprises at least one task involving the first actuator, wherein the second possible task group comprises at least one task involving the second actuator, and wherein selecting the task group comprises selecting between at least a first task group score assigned to the first possible task group and a second task group score assigned to the second possible task group.

23. The method of claim 13, wherein determining the plurality of possible task groups comprises determining at least a first possible task group and a second possible task group, wherein the first possible task group comprises at least one task involving a portion of the robotic system moving along a first plane of motion, wherein the second possible task group comprises at least one task involving the portion of the robotic system moving along a second plane of motion, and wherein selecting the task group comprises selecting between at least a first task group score assigned to the first possible task group and a second task group score assigned to the second possible task group.