LASER RANGING PROCESS FOR ROAD AND OBSTACLE DETECTION IN NAVIGATING AN AUTONOMOUS VEHICLE

• US 20100030473A1
• Filed: 07/30/2008
• Published: 02/04/2010
• Est. Priority Date: 07/30/2008
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: SCHEWE, JON, AU, KWONG WING
• Granted Patent: US 8,755,997 B2
• Time in Patent Office: Days
• US Class Current: 701/301
• CPC Class Codes: G01S 17/86 Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
• CPC Class Codes: G01S 17/931 of land vehicles
• CPC Class Codes: G06V 20/56 exterior to a vehicle by using sensors mounted on the vehicle

Abstract

A method and system provide road and obstacle detection in navigating an autonomous vehicle. The method comprises scanning a distance ahead of the autonomous vehicle to obtain a current range scan, and obtaining navigation data, including dynamics, position, and orientation measurements of the autonomous vehicle. The current range scan is transformed to world coordinates with respect to a reference location based on the navigation data, and the transformed current range scan is input into a distance-based accumulator. The transformed current range scan is added to a variable size buffer when the autonomous vehicle is deemed to be non-stationary. A ground plane is estimated from the transformed current range scan and prior range scans stored in the variable size buffer. The estimated ground plane is represented as a constrained quadratic surface, which is classified into one or more of a traversable area, a non-traversable area, or an obstacle area for navigation of the autonomous vehicle.

Claims

1. A method for road and obstacle detection in navigating an autonomous vehicle, the method comprising:

scanning a distance ahead of the autonomous vehicle to obtain a current range scan;

obtaining navigation data, including dynamics, position, and orientation measurements of the autonomous vehicle, during the scanning of the distance ahead;

transforming the current range scan to world coordinates with respect to a reference location based on the navigation data;

inputting the transformed current range scan into a distance-based accumulator;

adding the transformed current range scan to a variable size buffer when the autonomous vehicle is deemed to be non-stationary;

estimating a ground plane from the transformed current range scan and prior range scans stored in the variable size buffer;

representing the estimated ground plane as a constrained quadratic surface; and

classifying the constrained quadratic surface into one or more of a traversable area, a non-traversable area, or an obstacle area for navigation of the autonomous vehicle.

2. The method of claim 1, wherein the distance ahead is scanned by at least one laser scanner mounted on the autonomous vehicle.

3. The method of claim 2, wherein the laser scanner comprises a light detection and ranging device.

4. The method of claim 1, wherein the navigation data is obtained from at least one global positioning system sensor, and at least one inertial navigation system sensor.

5. The method of claim 1, wherein the distance-based accumulator comprises instructions for:

comparing the transformed current range scan with an immediately preceding range scan stored in the variable size buffer to determine whether the autonomous vehicle is stationary or non-stationary;

computing a distance covered by the transformed current range scan and the prior range scans stored in the variable size buffer;

comparing a fixed distance threshold with the distance covered; and

removing one or more of the prior range scans from the variable size buffer when the distance covered is greater than the fixed distance threshold.

6. The method of claim 1, further comprising running a modified RANSAC process to estimate the constrained quadratic surface.

7. The method of claim 1, wherein the estimated ground plane corresponds to a road surface on which the autonomous vehicle is traveling.

8. The method of claim 7, wherein the estimated ground plane is represented by a three-dimensional road model corresponding to the constrained quadratic surface.

9. The method of claim 1, further comprising outputting one or more map labels in world coordinates based on the transformed current range scan and the prior range scans.

10. The method of claim 9, wherein classifying the constrained quadratic surface comprises computing a height of the map labels above the estimated ground plane.

11. The method of claim 10, further comprising comparing the height of the map labels with one or more height thresholds for the traversable area, the non-traversable area, and the obstacle area.

12. A computer program product, comprising:

a computer readable medium having instructions stored thereon for a method according to claim 1.

13. A system for road and obstacle detection in navigating an autonomous vehicle, the system comprising:

at least one laser scanner mounted on an autonomous vehicle, the laser scanner configured to perform mulitple range scans of a fixed size area ahead of the autonomous vehicle;

a navigation unit in the autonomous vehicle, the navigation unit configured to obtain navigation data, including dynamics, position, and orientation measurements of the autonomous vehicle, during the range scans of the fixed size area;

at least one processing unit in the autonomous vehicle and in operative communication with the laser scanner and the navigation unit, the processing unit including a variable size buffer and configured to execute instructions to;

synchronize a current range scan from the laser scanner with navigation data obtained during the current range scan;

transform the current range scan to world coordinates with respect to a reference location based on the navigation data;

input the transformed current range scan into a distance-based accumulator;

add the transformed current range scan to the variable size buffer when the autonomous vehicle is deemed to be non-stationary;

estimate a ground plane from the transformed current range scan and prior range scans stored in the variable size buffer;

represent the estimated ground plane as a constrained quadratic surface; and

classify the constrained quadratic surface into one or more of a traversable area, a non-traversable area, or an obstacle area for navigation of the autonomous vehicle.

14. The system of claim 13, wherein the at least one laser scanner comprises a light detection and ranging device.

15. The system of claim 13, wherein the navigation unit comprises one or more global positioning system sensors, and one or more inertial navigation system sensors.

16. The system of claim 13, wherein the processing unit comprises a computer, a digital signal processor, or a field programmable gate array.

17. The system of claim 13, wherein the distance-based accumulator comprises instructions to:

compare the transformed current range scan with an immediately preceding range scan stored in the variable size buffer to determine whether the autonomous vehicle is stationary or non-stationary;

compute a distance covered by the transformed current range scan and the prior range scans stored in the variable size buffer;

compare a fixed distance threshold with the distance covered; and

remove one or more of the prior range scans from the variable size buffer when the distance covered is greater than the fixed distance threshold.

18. The system of claim 13, wherein the constrained quadratic surface is obtained by a modified RANSAC process.

19. The system of claim 13, wherein the ground plane is represented by a three-dimensional road model corresponding to the constrained quadratic surface.

20. The system of claim 13, wherein the constrained quadratic surface is classified by a height of one or more map labels in world coordinates above the ground plane, the map labels based on the transformed current range scan and the prior range scans.