Robotic intelligence kernel

• US 7,620,477 B2
• Filed: 07/05/2006
• Issued: 11/17/2009
• Est. Priority Date: 07/05/2006
• Status: Active Grant

• Current Assignee: Humatics Corporation
• Original Assignee: Battelle Energy Alliance LLC (Battelle Memorial Institute)
• Inventors: Bruemmer, David J.
• Primary Examiner(s): Tran; Khoi
• Assistant Examiner(s): Marc; McDieunel
• Application Number:
  US11/428,650
• Publication Number:
  US 20080009967A1
• Time in Patent Office: 1,231 Days
• Field of Search: 700/245, 700/248, 700/258, 700/259, 700/31, 318/568.1, 318/568.11, 318/568.12, 318/568.2, 318/569, 901/1, 901/15, 901/47, 704/207, 704/209, 704/270, 701/2, 701/23, 701/24, 701/206, 701/209, 701/211, 340/995.16, 342/357.09
• US Class Current: 700/245
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G06N 3/008 based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour

Abstract

A robot platform includes perceptors, locomotors, and a system controller. The system controller executes a robot intelligence kernel (RIK) that includes a multi-level architecture and a dynamic autonomy structure. The multi-level architecture includes a robot behavior level for defining robot behaviors, that incorporate robot attributes and a cognitive level for defining conduct modules that blend an adaptive interaction between predefined decision functions and the robot behaviors. The dynamic autonomy structure is configured for modifying a transaction capacity between an operator intervention and a robot initiative and may include multiple levels with at least a teleoperation mode configured to maximize the operator intervention and minimize the robot initiative and an autonomous mode configured to minimize the operator intervention and maximize the robot initiative. Within the RIK at least the cognitive level includes the dynamic autonomy structure.

Claims

1. A method for providing a robot intelligence kernel for robot control software, comprising:

providing a multi-level architecture, comprising;

a robot behavior level configured for defining a plurality of robot behaviors, each robot behavior configured for incorporating at least one robot attribute to cause the robot to perform an intended behavior; and

a cognitive level configured for defining a plurality of cognitive conduct modules, each cognitive conduct module configured for blending an adaptive interaction between at least one predefined decision function and at least one of the plurality of robot behaviors; and

providing a dynamic autonomy structure configured for modifying a transaction capacity between an operator intervention and a robot initiative, the dynamic autonomy structure comprising;

a teleoperation mode configured to maximize the operator intervention and minimize the robot initiative; and

an autonomous mode configured to minimize the operator intervention and maximize the robot initiative;

wherein the cognitive level includes the dynamic autonomy structure.

2. The method of claim 1, wherein the robot behavior level includes the dynamic autonomy structure.

3. The method of claim 1, wherein the plurality of robot behaviors includes reactive behaviors and deliberative behaviors.

4. The method of claim 1, wherein the plurality of robot behaviors are selected from the group consisting of obstacle avoidance, guarded motion, visual tracking, laser tracking, get-unstuck behavior, reactive path planning, waypoint navigation, global path planning, and occupancy change detection.

5. The method of claim 1, wherein the dynamic autonomy structure further comprises:

a safe mode configured to include less of the operator intervention and more of the robot initiative relative to the teleoperation mode;

a collaborative tasking mode configured to include more of the operator intervention and less of the robot initiative relative to the autonomous mode; and

a shared mode configured to include less of the operator intervention and more of the robot initiative relative to the safe mode and configured to include more of the operator intervention and less of the robot initiative relative to the collaborative tasking mode.

6. The method of claim 5, wherein the robot behavior level includes the dynamic autonomy structure.

7. The method of claim 1, wherein modifying the transaction capacity is configured to be performed by an operator selecting one of the available autonomy modes or by the operator adjusting the robot initiative, the operator intervention, or combinations thereof.

8. The method of claim 7, wherein change in a dynamic autonomy level is requested by a robot.

9. The method of claim 1, wherein the multi-level architecture further comprises:

a hardware abstraction level configured for developing a plurality of hardware abstractions for defining, monitoring, and controlling a plurality of hardware modules available on a robot platform; and

a robot abstraction level configured for defining a plurality of robot attributes comprising at least one of the plurality of hardware abstractions, each robot attribute configured for use by the plurality of robot behaviors, the plurality of cognitive conduct modules, and others of the plurality of robot attributes.

10. The method of claim 9, wherein the plurality of hardware abstractions is selected from the group consisting of manipulation abstractions of manipulation type devices, communication abstractions of communication media and communication protocols, locomotion abstractions of locomotion hardware, and perception abstractions of perception type devices.

11. The method of claim 9, wherein the plurality of robot attributes are selected from the group consisting of robot health, robot position, robot motion, robot bounding shape, environmental occupancy grid, and range.

12. The method of claim 9, wherein the dynamic autonomy structure further comprises:

a safe mode configured to include less of the operator intervention and more of the robot initiative relative to the teleoperation mode;

a collaborative tasking mode configured to include more of the operator intervention and less of the robot initiative relative to the autonomous mode; and

a shared mode configured to include less of the operator intervention and more of the robot initiative relative to the safe mode and configured to include more of the operator intervention and less of the robot initiative relative to the collaborative tasking mode.

13. The method of claim 12, wherein the robot abstraction level includes the dynamic autonomy structure.

14. The method of claim 12, wherein the hardware abstraction level includes the dynamic autonomy structure.

15. A computer readable medium having computer executable instructions thereon, which when executed on a processor provide a robot intelligence kernel, comprising:

a multi-level architecture, comprising;

a robot behavior level configured for defining a plurality of robot behaviors, each robot behavior configured for incorporating at least one robot attribute to cause the robot to perform an intended behavior; and

a cognitive level configured for defining a plurality of cognitive conduct modules, each cognitive conduct module configured for blending an adaptive interaction between at least one predefined decision function and at least one of the plurality of robot behaviors; and

a dynamic autonomy structure configured for modifying a transaction capacity between an operator intervention and a robot initiative, the dynamic autonomy structure comprising;

a teleoperation mode configured to maximize the operator intervention and minimize the robot initiative; and

an autonomous mode configured to minimize the operator intervention and maximize the robot initiative;

wherein the cognitive level includes the dynamic autonomy structure.

16. The computer readable medium of claim 15, wherein the robot behavior level includes the dynamic autonomy structure.

17. The computer readable medium of claim 15, wherein the plurality of robot behaviors includes reactive behaviors and deliberative behaviors.

18. The computer readable medium of claim 15, wherein the plurality of robot behaviors is selected from the group consisting of obstacle avoidance, guarded motion, visual tracking, laser tracking, get-unstuck behavior, reactive path planning, waypoint navigation, global path planning, and occupancy change detection.

19. The computer readable medium of claim 15, wherein the dynamic autonomy struture further comprises:

a safe mode configured to include less of the operator intervention and more of the robot initiative relative to the teleoperation mode;

a collaborative tasking mode configured to include more of the operator intervention and less of the robot initiative relative to the autonomous mode; and

a shared mode configured to include less of the operator intervention and more of the robot initiative relative to the safe mode and configured to include more of the operator intervention and less of the robot initiative relative to the collaborative tasking mode.

20. The computer readable medium of claim 19, wherein the robot behavior level includes the dynamic autonomy structure.

21. The computer readable medium of claim 15, wherein modifying the transaction capacity is configured to be performed by an operator selecting one of the available autonomy modes or by the operator adjusting the robot initiative, the operator intervention, or combinations thereof.

22. The computer readable medium of claim 21, wherein change in a dynamic autonomy level is requested by a robot.

23. The computer readable medium of claim 15, wherein the multi-level architecture further comprises:

a hardware abstraction level configured for developing a plurality of hardware abstractions for defining, monitoring, and controlling a plurality of hardware modules available on a robot platform; and

a robot abstraction level configured for defining a plurality of robot attributes comprising at least one of the plurality of hardware abstractions, each robot attribute configured for use by the plurality of robot behaviors, the plurality of cognitive conduct modules, and others of the plurality of robot attributes.

24. The computer readable medium of claim 23, wherein the plurality of hardware abstractions is selected from the group consisting of manipulation abstractions of manipulation type devices, communication abstractions of communication media and communication protocols, locomotion abstractions of locomotion hardware, and perception abstractions of perception type devices.

25. The computer readable medium of claim 23, wherein the plurality of robot attributes are selected from the group consisting of robot health, robot position, robot motion, robot bounding shape, environmental occupancy grid, and range.

26. The computer readable medium of claim 23, wherein the dynamic autonomy structure further comprises:

a safe mode configured to include less of the operator intervention and more of the robot initiative relative to the teleoperation mode;

a collaborative tasking mode configured to include more of the operator intervention and less of the robot initiative relative to the autonomous mode; and

a shared mode configured to include less of the operator intervention and more of the robot initiative relative to the safe mode and configured to include more of the operator intervention and less of the robot initiative relative to the collaborative tasking mode.

27. The computer readable medium of claim 26, wherein the robot abstraction level includes the dynamic autonomy structure.

28. The computer readable medium of claim 26, wherein the hardware abstraction level includes the dynamic autonomy structure.

29. A robot platform, comprising:

at least one perceptor configured for perceiving environmental variables of interest;

at least one locomotor configured for providing mobility to the robot platform;

a system controller configured for executing a robot intelligence kernel, the robot intelligence kernel comprising;

a multi-level architecture, comprising;

a robot behavior level configured for defining a plurality of robot behaviors, each robot behavior configured for incorporating at least one robot attribute to cause the robot to perform an intended behavior; and

a cognitive level configured for defining a plurality of cognitive conduct modules, each cognitive conduct module configured for blending an adaptive interaction between at least one predefined decision function and at least one of the plurality of robot behaviors; and

a dynamic autonomy structure configured for modifying a transaction capacity between an operator intervention and a robot initiative, the dynamic autonomy structure comprising;

a teleoperation mode configured to maximize the operator intervention and minimize the robot initiative; and

an autonomous mode configured to minimize the operator intervention and maximize the robot initiative;

wherein the cognitive level includes the dynamic autonomy structure.

30. The robot platform of claim 29, wherein the at least one perceptor is selected from the group consisting of inertial sensors, thermal sensors, tactile sensors, compasses, range sensors, sonar perceptors, global positioning systems, ground penetrating radars, laser perceptors, and imaging devices.

31. The robot platform of claim 29, wherein the at least one locomotor is selected from the group consisting of wheels, tracks, legs, rollers, and propellers.

32. The robot platform of claim 29, further comprising at least one communication device configured for communicating information across a communication channel to a robot controller, at least one additional robot platform, or combinations thereof.

33. The robot platform of claim 29, further comprising at least one manipulator coupled to the robot platform.

34. The robot platform of claim 29, wherein the dynamic autonomy structure further comprises:

a safe mode configured to include less of the operator intervention and more of the robot initiative relative to the teleoperation mode;

a collaborative tasking mode configured to include more of the operator intervention and less of the robot initiative relative to the autonomous mode; and

a shared mode configured to include less of the operator intervention and more of the robot initiative relative to the safe mode and configured to include more of the operator intervention and less of the robot initiative relative to the collaborative tasking mode.

35. The robot platform of claim 34, wherein the robot behavior level includes the dynamic autonomy structure.

36. The robot platform of claim 29, wherein modifying the transaction capacity is configured to be performed by an operator selecting one of the available autonomy modes or by the operator adjusting the robot initiative, the operator intervention, or combinations thereof.

37. The robot platform of claim 36, wherein change in a dynamic autonomy level is requested by a robot.

38. The robot platform of claim 29, wherein the multi-level architecture further comprises:

a hardware abstraction level configured for developing a plurality of hardware abstractions for defining, monitoring, and controlling a plurality of hardware modules available on a robot platform; and

a robot abstraction level configured for defining a plurality of robot attributes comprising at least one of the plurality of hardware abstractions, each robot attribute configured for use by the plurality of robot behaviors, the plurality of cognitive conduct modules, and others of the plurality of robot attributes.

39. The robot platform of claim 38, wherein the dynamic autonomy structure further comprises:

a safe mode configured to include less of the operator intervention and more of the robot initiative relative to the teleoperation mode;

a collaborative tasking mode configured to include more of the operator intervention and less of the robot initiative relative to the autonomous mode; and

a shared mode configured to include less of the operator intervention and more of the robot initiative relative to the safe mode and configured to include more of the operator intervention and less of the robot initiative relative to the collaborative tasking mode.