Digest for localization or fingerprinted overlay

• US 8,903,644 B2
• Filed: 11/29/2012
• Issued: 12/02/2014
• Est. Priority Date: 11/29/2011
• Status: Active Grant

• Current Assignee: iRobot Corporation
• Original Assignee: iRobot Corporation
• Inventors: Pack, Robert Todd
• Primary Examiner(s): Badii, Behrang
• Assistant Examiner(s): LANG, MICHAEL DEAN
• Application Number:
  US13/688,933
• Publication Number:
  US 20130138337A1
• Time in Patent Office: 733 Days
• Field of Search: None
• US Class Current: 701/409
• CPC Class Codes: G01C 21/3826 Terrain data
• CPC Class Codes: G01C 21/3844 Data obtained from position sensors only, e.g. from inertial navigation
• CPC Class Codes: G05D 1/024 in combination with a laser lasers per se H01S
• CPC Class Codes: G05D 1/0251 extracting 3D information from a plurality of images taken from different locations, e.g. stereo vision stereoscopic image analysis H04N13/00; depth recovery from images G06T7/593
• 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 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G05D 1/0278 using satellite positioning signals, e.g. GPS

Abstract

A method for mapping an environment proximal to a vehicle includes obtaining a current location of the vehicle according to a map of the environment, detecting at least one characteristic of the environment at the current location, and storing the at least one characteristic in a characteristic digest. The characteristic digest respectively associates one or more locations in the environment to one or more sets of previously detected characteristics in the environment. The method also includes associating the at least one characteristic with the current location in the characteristic digest.

Claims

1. A method for mapping an environment proximal to a vehicle, the method comprising:

while driving about the environment, at least periodically;

obtaining a current location of the vehicle according to a map of the environment;

detecting at least one characteristic of the environment at the current location, the at least one characteristic including an acceleration of the vehicle at the current location when the vehicle is in a rest mode, the acceleration being received from an inertial measurement unit of the vehicle;

storing the at least one characteristic in a characteristic digest, the characteristic digest respectively associating one or more locations in the environment to one or more sets of previously detected characteristics in the environment; and

associating the at least one characteristic with the current location in the characteristic digest; and

in response to determining a loss of localization;

detecting one or more characteristics of the environment;

comparing the one or more characteristics of the environment with the previously detected characteristics stored in the characteristic digest; and

estimating a location of the vehicle based on the comparison.

2. The method of claim 1, wherein the at least one characteristic includes a slope of a terrain beneath the vehicle.

3. The method of claim 2, wherein the at least one characteristic further includes a roughness of the terrain beneath the vehicle.

4. The method of claim 2, wherein the at least one characteristic further includes a friction coefficient of the terrain under the vehicle.

5. The method of claim 1, further comprising:

detecting additional information at the current location;

storing the additional information in the characteristic digest; and

associating the additional information with the current location.

6. The method of claim 5, wherein the additional information includes short-range communication protocol information, the short-range communication protocol information being indicative of whether communication performed using a specific communication protocol can be performed at the current location.

7. The method of claim 1, wherein the at least one characteristic includes at least one of a magnitude of a magnetic field detected at the current location, an amount of visible light detected at the current location, an amount of invisible light detected at the current location, an amount of sound detected at the current location, a temperature detected at the current location, or a humidity detected at the current location.

8. The method of claim 1, wherein the current location is determined from a global positioning system unit of the vehicle, and the current location is indicative of global positioning coordinates of the vehicle.

9. The method of claim 1, wherein the current location is determined from a simultaneous localization and mapping system of the vehicle, and the current location is indicative of simultaneous localization and mapping coordinates of the vehicle.

10. A method for verifying mapping information of an environment proximal to a vehicle, the method comprising:

determining a current location of the vehicle according to a map of the environment;

detecting at least one current characteristic of the environment at the current location, the at least one characteristic including an acceleration of the vehicle at the current location when the vehicle is in a rest mode, the acceleration being received from an inertial measurement unit of the vehicle;

obtaining at least one previously detected characteristic from a characteristic digest based on the current location, the characteristic digest respectively associating one or more locations in the environment to one or more sets of previously detected characteristics in the environment;

comparing the at least one previously detected characteristic with the at least one current characteristic;

determining an accuracy of the determined current location of the vehicle based on the comparing;

in response to the current characteristic matching the previously detected characteristic, indicating that the mapping information is accurate; and

in response to the current characteristic not matching the previously detected characteristic, indicating that the mapping information is inaccurate.

11. The method of claim 10, further comprising determining, for each of the at least one previously detected characteristics, a probability of the previously detected characteristic, the probability being indicative of a likelihood that a value of the characteristic varies over a duration of time.

12. The method of claim 10, wherein the at least one characteristic includes at least one of a slope of a terrain beneath the vehicle, a roughness of the terrain below the vehicle, or a friction coefficient of the terrain beneath the vehicle.

13. The method of claim 10, wherein the at least one characteristic includes at least one of a magnetic field detected at the current location, an amount of visible light detected at the current location, an amount of invisible light detected at the current location, an amount of sound detected at the current location, a temperature detected at the current location, or a humidity detected at the current location.

14. A remote vehicle comprising:

a navigation system configured to determine a current location of the remote vehicle;

a sensor system configured to detect at least one characteristic of the current location, the at least one characteristic including an acceleration of the vehicle at the current location when the vehicle is in a rest mode, the acceleration being received from an inertial measurement unit of the vehicle;

a memory device configured to store a map of an environment of the remote vehicle and a characteristic digest, the characteristic digest respectively associating one or more locations in the environment to one or more sets of previously detected characteristics in the environment; and

a processing device logically coupled to the navigation system, the memory device, and the sensor system and configured to;

while the remote vehicle is driving about the environment, at least periodically;

obtain a current location of the vehicle according to a map of the environment;

detect at least one characteristic of the environment at the current location;

store the at least one characteristic in a characteristic digest; and

associate the at least one characteristic with the current location in the characteristic digest; and

in response to determining a loss of localization;

detect one or more characteristics of the environment;

compare the one or more characteristics of the environment with the previously detected characteristics stored in the characteristic digest; and

estimate a location of the vehicle based on the comparison.

15. The remote vehicle of claim 14, wherein the at least one characteristic includes a slope of a terrain beneath the vehicle.

16. The remote vehicle of claim 14, wherein the at least one characteristic includes a roughness of the terrain beneath the vehicle.

17. The remote vehicle of claim 14, wherein the at least one characteristic includes a friction coefficient of the terrain under the vehicle.

18. The remote vehicle of claim 14, wherein the processing device is further configured to:

detect additional information at the current location;

store the additional information in the characteristic digest; and

associate the additional information with the current location.

19. The remote vehicle of claim 18, wherein the additional information includes short-range communication protocol information, the short-range communication protocol information being indicative of whether communication performed using a specific communication protocol can be performed at the current location.

20. The remote vehicle of claim 14, wherein the at least one characteristic includes at least one of a magnitude of a magnetic field detected at the current location, an amount of visible light detected at the current location, an amount of invisible light detected at the current location, an amount of sound detected at the current location, a temperature detected at the current location, or a humidity detected at the current location.