Localization by learning of wave-signal distributions

Patent metadata

Field	Value
Publication number	US-8930023-B2
Application number	US-94093710-A
Country	US
Kind code	B2
Filing date	Nov 5, 2010
Priority date	Nov 6, 2009
Publication date	Jan 6, 2015
Grant date	Jan 6, 2015

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.

First claim

What is claimed is:

1. A method for determining a pose (location and orientation) of a mobile device, the method comprising:
dividing a representation of a substantially planar operating environment into a first plurality of cells, wherein a given cell in the first plurality of cells is defined by a set of three or more nodes having respective locations;
associating at least a first node with properties comprising a location and at least one parameter related to a detected signal detected by the mobile device;
computing, while the mobile device is at an actual pose in a first cell, an estimated value of at least one property of the signal at an estimated pose of the mobile device, the computing based at least in part on an estimated location of the estimated pose and one or more of the respective properties associated with two or more of the nodes defining the first cell, wherein computing the estimated value is based at least in part on the estimated orientation of the estimated pose and a rotational variation parameter; and
revising the estimated pose based at least in part on:
the estimated pose, the estimated value of the signal property, and a value of the signal property measured at the actual pose.

2. The method of claim 1 wherein the detected signal is a transmitted radio frequency signal or a light signal.

3. The method of claim 2 wherein the detected signal is a digital signal transmitted by radio.

4. The method of claim 2 wherein the detected signal is a digital signal used in wireless communications.

5. The method of claim 1 wherein the at least one signal property is time invariant relative to a location.

6. The method of claim 1 wherein the rotational variation parameter characterizes a change in a measurement made by a sensor on the mobile device as the sensor is rotated while the mobile device remains in a fixed location.

7. The method of claim 6 , wherein computing the estimated value comprises using the rotational variation parameter to compensate for elevation changes due to variations in manufacturing, calibration errors, or misalignments in mounting the sensor on the mobile device.

8. The method of claim 1 wherein revising the estimated pose further comprises revising at least one of the parameters associated with at least one of the nodes defining the first cell.

9. The method of claim 1 wherein revising the estimated pose comprises applying a SLAM implementation to at least the estimated pose, the estimated value of the signal property, and the value of the signal property measured at the actual pose.

10. The method of claim 1 wherein revising the estimated pose occurs when the value of the signal property at the actual pose is measured.

11. The method of claim 10 wherein the value of the signal property at the actual pose is not retained after a value of the signal property at a second actual pose is measured.

12. The method of claim 1 further comprising preparing instructions to move the mobile device based at least in part on the revised estimated pose.

13. The method of claim 1 wherein associating a node with properties comprises:
associating the node with a node location;
measuring a property of the signal at a first pose of the mobile device, the first pose located within a first cell defined in part by the node;
moving the mobile device to a second pose in the first cell;
measuring the signal property at the second pose;
obtaining a measure of the relative change in location from the first pose to the second pose, said measure not determined by measuring the signal property;
learning a relationship between the signal property and location within the cell;
estimating a value of the signal property at the node location based at least on the node location and the learned relationship between the signal property and location; and
associating the node with the estimated value of the signal property.

14. The method of claim 13 wherein associating a node with properties further comprises:
obtaining a measure of the relative change in orientation from the first pose to the second pose, said measure not determined by measuring the signal property; and
learning a relationship between the signal property and orientation of the mobile device at a location within the cell; and
wherein estimating a value of the signal property at the node location is further based on the learned relationship between the signal property and orientation; and
wherein the node is further associated with a parameter indicative of orientation.

15. The method of claim 14 , further comprising moving the mobile device from a third pose in the first cell to a fourth pose in the first cell; and wherein
computing an estimated value of the signal property at an estimate of the fourth pose of the mobile device comprises interpolating based on a measure of the distance of the estimated pose from the respective nodes of the set of nodes defining the first cell and the estimated value of the signal property associated with the respective nodes of the set;
revising the estimated fourth pose comprises applying a SLAM implementation to a value of the signal property as measured at the fourth pose; the estimated value of the signal property; and a measure, not determined by measuring the signal property, of an estimated change in location from the third pose to the fourth pose.

16. The method of claim 15 , wherein computing the estimated value of the signal property at the estimated pose is further based at least in part on the relationship between the signal property and mobile device orientation.

17. The method of claim 15 , wherein the dividing, associating, computing, revising, obtaining, learning, associating, and moving steps are performed by elements of the mobile device.

18. The method of claim 15 , further comprising:
moving the mobile device from the fourth pose to a charging station at a fourth location;
moving the mobile device from the charging station back to the fourth pose.

19. The method of claim 1 wherein the location of the first node is determined based at least in part on the location of the mobile device at the time the node's location is determined.

20. The method of claim 1 wherein the location of the first node is determined based at least in part on the location of a second node.

21. The method of claim 1 wherein the respective nodes are located at predefined distances from each other.

22. The method of claim 1 , further comprising emitting a signal configured to be detected by the mobile device.

23. The method of claim 1 , wherein the at least one parameter related to a signal and associated with a node comprises one or more parameters for an equation modeling a property of the signal within a cell defined in part by the node.

24. The method of claim 23 wherein the equation is a linear interpolation.

25. The method of claim 23 , wherein the Spline is a Nurbs.

26. The method of claim 23 wherein the equation is a Spline.

27. The method of claim 23 , wherein one or more of the learning or estimating steps are performed by elements distinct from the mobile device.

28. The method of claim 1 , wherein the, dividing, associating, computing, and revising steps are performed by elements of the mobile device.

29. The method of claim 1 , wherein the mobile device is an autonomous robot.

Assignees

• Gutmann Steffen
• Eade Ethan
• Fong Philip
• Munich Mario
• Irobot Corp

Inventors

• Gutmann Steffen
• Eade Ethan
• Fong Philip
• Munich Mario

Classifications

• Y10S901/46

  Sensing device · CPC title

• B25J9/1664 Primary

  characterised by motion, path, trajectory planning · CPC title

• Y10S901/09

  Closed loop, sensor feedback controls arm movement · CPC title

• Y10S901/01

  Mobile robot · CPC title

• B25J9/1694

  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 title