TEMPORAL TRACKING ROBOT CONTROL SYSTEM

• US 20110231016A1
• Filed: 03/17/2010
• Published: 09/22/2011
• Est. Priority Date: 03/17/2010
• Status: Active Grant

• Current Assignee: Raytheon Company (Rtx Corporation)
• Original Assignee: Raytheon Company (Rtx Corporation)
• Inventors: GOULDING, John R.
• Granted Patent: US 8,706,298 B2
• Time in Patent Office: Days
• US Class Current: 700/246
• CPC Class Codes: G01C 21/20 Instruments for performing navigational calculations G01C21/24, G01C21/26 take precedence
• 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: G05D 1/0231 using optical position detecting means position-fixing by using electromagnetic waves other than radio waves, e.g. optical position detecting means G01S5/16
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• 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 temporal controller for mobile robot path planning includes a sensor module for receiving data corresponding to spatial locations of at least one object, and a temporal control module operatively coupled to the sensor module, the temporal control module configured to predict future locations of the at least one object based on data received by the sensor module. The controller further includes a temporal simulation module operatively coupled to the temporal control module, wherein the temporal simulation module configured to use the predicted future locations of the at least one object to simulate multiple robot motion hypothesis for object avoidance and trajectory planning.

Claims

1. A temporal controller for mobile robot path planning, comprising:

a sensor module for receiving data corresponding to a state of at least one object;

a temporal control module operatively coupled to said sensor module, the temporal control module configured to predict future locations of the at least one object in three-dimensional space based on data received by the sensor module; and

a temporal simulation module operatively coupled to said temporal control module, the temporal simulation module configured to use the predicted future locations of the at least one object to simulate multiple robot motion hypothesis for object avoidance and trajectory planning.

2. The controller according to claim 1, wherein the temporal simulation module is configured to time-propagate locations of the at least one object based on the received data corresponding to spatial locations, a priori map data, and a location of the robot in a common robot-centric representation.

3. The controller according to claim 1, further comprising a track file module operatively coupled between the sensor module and the temporal control module, the track file module configured to analyze data received by the sensor module and associate the data into tracks produced by the at least one object.

4. The controller according to claim 3, wherein the temporal simulation module is configured to further use the tracks and the predicted locations of the at least one object to simulate actions taken by the at least one object in response to robot actions.

5. The controller according to claim 3, wherein each track includes data corresponding to at least one of position, velocity, acceleration or heading.

6. The controller according to claim 3, wherein the temporal control module is configured to use the tracks to predict future locations of the at least one object.

7. The controller according to claim 3, further comprising a storage and maintenance module operatively coupled to the track file module, the storage and maintenance module configured to delete tracks based on expected or probable trajectory and motion control.

8. The controller according to claim 1, further comprising a scoring module operatively coupled to the temporal control module, the scoring module configured to provide a ranking indicative of a likelihood that the at least one object will occupy each predicted locations.

9. The controller according to claim 8, wherein the scoring module is further configured to provide a ranking indicative of a likelihood that the at least one object will follow a path through two or more predicted locations.

10. The controller according to claim 8, further comprising a memory, wherein the ranking is stored in the memory and associated with each predicted location.

11. The controller according to claim 1, wherein the temporal simulation module is configured to predict actions of the at least one object based on the state of the robot.

12. The controller according to claim 11, further comprising a scoring module operatively coupled to the temporal simulation loop, the scoring module configured to provide a ranking indicative of a likelihood that the at least one object will act as predicted.

13. The controller according to claim 1, wherein the temporal simulation module is configured to simulate the multiple robot motion hypotheses from a robot-centric point of view.

14. The controller according to claim 1, wherein the temporal control module includes a Kalman filter, the temporal control module configured to use the Kalman filter to predict future locations of the at least one object.

15. The controller according to claim 1, wherein the temporal simulation module executes asynchronously from the temporal control module.

16. The controller according to claim 1, further comprising a storage device for storing the predicted future locations.

17. The controller according to claim 1, wherein the temporal simulation loop is configured to use a behavior model to generate multiple action hypotheses for the robot.

18. The controller according to claim 1, wherein the temporal control module is configured to operate in a sensor-centric reference frame.

19. A method for simulating multiple robot motion hypotheses for obstacle avoidance and trajectory planning, comprising:

receiving data corresponding to a state of at least one object;

predicting future locations of the at least one object in three-dimensional space based on data received by the sensor module;

using the predicted future locations of the at least one object to simulate multiple robot motion hypothesis for object avoidance and trajectory planning.

20. The method according to claim 19, further comprising time-propagating locations of the at least one object based on the received data corresponding to spatial locations, a priori map data, and a location of the robot in a common robot-centric representation.

21. The method according to claim 19, further comprising associating the received the data into tracks produced by the at least one object.

22. The method according to claim 21, further comprising using the tracks and the predicted locations of the at least one object to simulate actions taken by the at least one object in response to robot actions.

23. The method according to claim 21, wherein each track includes data corresponding to at least one of position, velocity, acceleration or heading.

24. The method according to claim 21, further comprising using the tracks to predict future locations of the at least one object.

25. The method according to claim 21, further comprising deleting tracks based on expected or probable trajectory and motion control.

26. The method according to claim 19, further comprising providing a ranking indicative of a likelihood that the at least one object will occupy each predicted locations.

27. The method according to claim 26, further comprising providing a ranking indicative of a likelihood that the at least one object will follow a path through two or more predicted locations.

28. The method according to claim 19, further comprising predicting actions of the at least one object based on the state of the robot.

29. The method according to claim 28, further comprising providing a ranking indicative of a likelihood that the at least one object will act as predicted.

30. The method according to claim 19, wherein simulating multiple robot motion hypothesis includes simulating the multiple robot motion hypotheses from a robot-centric point of view.

31. The method according to claim 19, further comprising using a behavior model to generate multiple action hypotheses for the robot.