MULTIDIMENSIONAL EVIDENCE GRIDS AND SYSTEM AND METHODS FOR APPLYING SAME

• US 20090119010A1
• Filed: 11/03/2008
• Published: 05/07/2009
• Est. Priority Date: 02/08/2005
• Status: Active Grant

• Current Assignee: Seegrid Corporation
• Original Assignee: Seegrid Corporation
• Inventors: Moravec, Hans
• Granted Patent: US 8,427,472 B2
• Time in Patent Office: Days
• US Class Current: 701/209
• 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 1/0255 using acoustic signals, e.g. ultra-sonic singals sonar systems designed for anti-collision purposes G01S15/93
• CPC Class Codes: G05D 1/0257 using a radar radar systems designed for anti-collision purposes between land vehicles or between land vehicle and fixed obstacles G01S13/931
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

Mapping, localization, and navigation systems for use with a mobile unit are provided that use a sensor model with adjustable parameters. The system includes range sensors configured to collect range data and a data storage system having stored therein an evidence grid representing an environment and a sensor model comprising adjustable parameters representing inaccuracies of the range sensors. A grid engine adjusts the adjustable parameters based on received range data from the range sensors. A navigation module can direct the mobile unit though the environment using the evidence grid, received range data, and adjustable parameters. The grid engine can also locate the mobile unit within the environment by using the adjusted sensor model parameters to compare the received range data against the evidence grid.

Claims

1. A navigation system for use with a mobile unit, the system comprising:

range sensors configured to collect range data;

a data storage system having stored therein an evidence grid representing an environment and a sensor model comprising adjustable parameters representing inaccuracies of the range sensors;

a grid engine configured to adjust the adjustable parameters based on received range data from the range sensors; and

a navigation module configured to direct the mobile unit though the environment using the evidence grid, received range data, and adjustable parameters.

2. The system of claim 1, wherein the range sensors are stereo sensors and the range data is stereo data.

3. The system of claim 1, wherein the grid engine is configured to locate the mobile unit within the environment by using the adjusted sensor model parameters to compare the received range data against the evidence grid.

4. The system of claim 1, wherein different parameters from the adjustable parameters are used for different functions.

5. The system of claim 4, wherein the different functions include a coarse search.

6. The system of claim 4, wherein the different functions include a fine search.

7. The system of claim 1, wherein the adjustable parameters are stored in a pixel mapping table.

8. The system of claim 1, further comprising:

an automated learning system configured to select a subset of the adjustable sensor model parameters.

9. A mapping system for use with a mobile unit, the system comprising:

range sensors configured to collect range data;

a data storage system having stored therein a sensor model comprising adjustable parameters representing inaccuracies of the range sensors;

a grid engine configured to adjust the adjustable parameters based on received range data from the range sensors; and

a mapping module configured to generate map of the environment using the received range data and adjustable parameters.

10. The system of claim 9, wherein the map is an evidence grid.

11. The system of claim 10, further comprising:

a navigation module configured to direct the mobile unit though the environment using the evidence grid, received range data, and adjustable parameters.

12. The system of claim 10, wherein the grid engine is configured to locate the mobile unit within the environment by using the adjusted sensor model parameters to compare the received range data against the evidence grid.

13. The system of claim 12, wherein the localizing and the mapping use the same adjustable parameters.

14. The system of claim 12, wherein the localizing and the mapping use different adjustable parameters.

15. The system of claim 9, wherein the range sensors are stereo sensors and the range data is stereo data.

16. A method of generating a pixel mapping table comprising adjustable parameters of a sensor model comprises:

activating range sensors;

imaging a calibration array with the range sensors;

generating a rectifying function from the calibration array; and

building a pixel mapping table from the rectifying function.

17. The method of claim 16, wherein the pixel mapping table comprises information for correcting images for distortions related to the range sensors.

18. The method of claim 16, wherein the range sensors are stereo sensors and the range data is stereo data.

19. The method of claim 18, wherein the stereo sensors include stereo cameras.