Localization by learning of wave-signal distributions

• US 9,440,354 B2
• Filed: 01/05/2015
• Issued: 09/13/2016
• Est. Priority Date: 11/06/2009
• Status: Active Grant

• Current Assignee: iRobot Corporation
• Original Assignee: iRobot Corporation
• Inventors: Gutmann, Steffen, Eade, Ethan, Fong, Philip, Munich, Mario
• Primary Examiner(s): MOYER, DALE S
• Application Number:
  US14/589,429
• Publication Number:
  US 20150197011A1
• Time in Patent Office: 617 Days
• US Class Current: 1/1
• CPC Class Codes: B25J 9/1664 characterised by motion, path, trajectory planning
• CPC Class Codes: B25J 9/1694 characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
• CPC Class Codes: G05D 1/0234 using optical markers or beacons optical beacons per se G01S1/70
• CPC Class Codes: G05D 1/0261 using magnetic plots
• CPC Class Codes: G05D 1/027 comprising intertial navigation means, e.g. azimuth detector inertial navigation G01C21/16; inertial navigation combined with non-inertial navigation instruments G01C21/165
• CPC Class Codes: G05D 1/0272 comprising means for registering the travel distance, e.g. revolutions of wheels measuring distance traversed on the ground by vehicles, e.g. using odometers G01C22/00
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G05D 1/028 using a RF signal
• CPC Class Codes: Y10S 901/01 Mobile robot
• CPC Class Codes: Y10S 901/09 Closed loop, sensor feedback controls arm movement
• CPC Class Codes: Y10S 901/46 Sensing device

Abstract

A robot having a signal sensor configured to measure a signal, a motion sensor configured to measure a relative change in pose, a local correlation component configured to correlate the signal with the position and/or orientation of the robot in a local region including the robot'"'"'s current position, and a localization component configured to apply a filter to estimate the position and optionally the orientation of the robot based at least on a location reported by the motion sensor, a signal detected by the signal sensor, and the signal predicted by the local correlation component. The local correlation component and/or the localization component may take into account rotational variability of the signal sensor and other parameters related to time and pose dependent variability in how the signal and motion sensor perform. Each estimated pose may be used to formulate new or updated navigational or operational instructions for the robot.

Claims

1. A robot configured to determine its location and orientation in an environment in which a signal, external to the robot, is present, the robot comprising:

a signal sensor configured to detect a property of the signal;

a movement system configured to move the robot from a first pose comprising a first location in the environment at a first time to a second pose comprising a second location at a second time, the second location proximate to the first location;

a motion sensor configured to detect a change in location between the first pose and the second pose;

a local signal estimator configured to predict the value of the signal property at a plurality of poses, the plurality of poses comprising poses with respective predefined locations proximate to the first pose; and

a localization component configured to estimate the robot'"'"'s second pose based at least in part on a value of the signal property as detected by the signal sensor at the second pose, the change in pose between the first pose and the second pose as detected by the motion sensor, and a predicted value of the signal property at the estimated second pose based at least in part on one or more of the values predicted by the local signal estimator.

2. The robot of claim 1, wherein the motion sensor is configured to detect the change in location between the first pose and the second pose by detecting a relative change in location.

3. The robot of claim 1, wherein two locations are proximate only if they are less than 2 meters apart.

4. The robot of claim 3, wherein two locations are proximate only if they are less than 2 feet apart.

5. The robot of claim 1, wherein:

the movement system is further configured to move the robot from the second location at the second time to a third pose comprising a third location in the environment at a third time, the third location not proximate to the first location;

the motion sensor is further configured to detect a change in location between the second location and the third location;

the local signal estimator is further configured to predict values of the signal property at a plurality of locations proximate to the third location based, at least in part, on extrapolating from previously predicted values at one or more locations proximate to both the first location and the third location; and

the localization component is further configured to estimate the robot'"'"'s third location based at least in part on a value of the signal property as detected by the signal sensor at the third location, the change in location between the second location and the third location as detected by the motion sensor, and a value of the signal property at the estimated third location as predicted by the local signal estimator.

6. The robot of claim 5, wherein the local signal estimator is further configured to introduce noise into the extrapolation.

7. The robot of claim 1, wherein the motion sensor is further configured to detect a relative change in orientation between the first pose and the second pose.

8. The robot of claim 7, wherein the localization component is further configured to estimate the robot'"'"'s second pose based at least in part on a rotational variance measure associated with how the value of the signal property detected by the signal sensor depends on the orientation of the robot.

9. The robot of claim 1, wherein the local signal estimator is further configured to detect and reject outliers of the predicted values of the signal property.

10. The robot of claim 1, wherein the estimated second pose is based at least in part on a calibration parameter of at least one of the signal sensor and the motion sensor.

11. An autonomous robot comprising:

a movement system configured to move the robot within an environment from a first pose to a second pose and from the second pose to a third pose, the first pose comprising a first location in the environment at a first time, the second pose comprising a second location at a second time, and the third pose comprising a third location at a third time, wherein the second location is proximate to the first location and the third location is not proximate to the first location;

a signal sensor configured to be responsive to a property of a signal in the environment;

a motion sensor configured to detect a change in location between the first pose and the second pose, and to detect a change in location between the second pose and the third pose;

a local signal estimator configured to predict values of the signal property at a plurality of locations proximate to the first location and to predict values of the signal property at a plurality of locations proximate to the third location, the values at the plurality of locations proximate to the third location being based, at least in part, on extrapolating from previously predicted values at one or more locations proximate to both the first location and the third location; and

a localization component configured to;

estimate the second location of the robot based at least in part on a value of the signal property as detected by the signal sensor at the second location, the change in location between the first pose and the second pose as detected by the motion sensor, and a predicted value of the signal property at the estimated second location as predicted by the local signal estimator, and to

estimate the third location of the robot based at least in part on a value of the signal property as detected by the signal sensor at the third location, the change in location between the second pose and the third pose as detected by the motion sensor, and a predicted value of the signal property at the estimated third location as predicted by the local signal estimator.

12. The robot of claim 11, wherein the localization component is further configured to estimate at least one of the second pose and the third pose based at least in part on a rotational variance measure associated with how the value of the signal property detected by the signal sensor depends on an orientation of the robot.

13. The robot of claim 11, wherein the localization component is further configured to estimate at least one of the second pose and the third pose based at least in part on a calibration parameter of at least one of the signal sensor and the motion sensor.

14. The robot of claim 11, wherein the first and third locations are not proximate in that they are greater than 2 meters apart.

15. The robot of claim 11, wherein the local signal estimator is further configured to introduce noise into the extrapolation.

16. The robot of claim 11, wherein the motion sensor is further configured to detect a relative change in orientation between the first pose and the second pose and between the second pose and the third pose.

17. The robot of claim 11, wherein the localization component is further configured to revise the second pose by applying a SLAM implementation to at least the estimated second location, the predicted value of the signal property at the estimated second location, and the value of the signal property at the estimated second location.

18. The robot of claim 11, wherein the localization component is further configured to revise the third pose by applying a SLAM implementation to at least the estimated third location, the predicted value of the signal property at the estimated third location, and the value of the signal property at the estimated third location.

19. The robot of claim 11, wherein the local signal estimator is further configured to detect and reject outliers of the predicted values of the signal property.

20. The robot of claim 11, wherein at least one of the estimated second location and the estimated third location is based at least in part on a calibration parameter of at least one of the signal sensor and the motion sensor.