Method And System For Correcting A Pre‐Generated Navigation Path For An Autonomous Vehicle

Claims:WE CLAIM 1. A method for correcting a pre-generated navigation path for an autonomous vehicle, the method comprising: receiving, by a navigation device, the pre-generated navigation path on a navigation map, an environmental field of view (FOV) of the autonomous vehicle, and a location of the autonomous vehicle on the pre-generated navigation path; determining, by the navigation device, a set of new data points in a pre-defined region with respect to the location of autonomous vehicle based on the environmental FOV and the navigation map; determining, by the navigation device, an offset of the pre-generated navigation path in the pre-defined region based on the set of new data points; and correcting, by the navigation device, the pre-generated navigation path in the pre-defined region based on the offset.

2. The method of claim 1, wherein the navigation map is a pre-generated light detection and ranging (LIDAR) map, and wherein the environmental FOV is received from a LIDAR scanner.

3. The method of claim 1, wherein the location of the autonomous vehicle is determined using at least one of a Monte Carlo localization algorithm, a geo-positioning system, a visual odometer, and an odometer.

4. The method of claim 1, wherein the pre-defined region is a region up to a certain pre-defined distance in front of the autonomous vehicle based on a curvature of the pre-generated navigation path, along each side of the pre-generated navigation path, from a pre-defined start height above a road surface, and up to a pre-defined end height above the road surface.

5. The method of claim 1, wherein determining the set of new data points comprises: comparing a plurality of data points in the pre-defined region of the environmental FOV with a plurality of data points in the pre-defined region of the navigation map; and based on the comparison, identifying a set of data points in the pre-defined region of the environmental FOV that have no corresponding data points in the navigation map within a pre-defined threshold.

6. The method of claim 1, wherein determining the offset comprises determining a set of offset distances along the pre-generated navigation path with respect to the set of new data points.

7. The method of claim 6, wherein determining each of the set of offset distances comprises: projecting a virtual ray at a pre-defined projection angle from the autonomous vehicle; computing a distances between the autonomous vehicle and a first data point from the set of new data points in the line of the virtual ray; and computing an offset distance between the pre-generated navigation path and the first data point based on the distance and the pre-defined projection angle.

8. The method of claim 6, wherein correcting the pre-generated navigation path comprises: determining an actual drivable road width along the pre-generated navigation path in the pre-defined region based on the set of offset distances; and determining a corrected navigation path, corresponding to the pre-generated navigation path in the pre-defined region, based on the actual drivable road width.

9. The method of claim 6, wherein correcting the pre-generated navigation path comprises: identifying an intended distance of the autonomous vehicle from an obstacle or a no-go region of at least one side along the pre-generated navigation path in the pre-defined region; and determining a corrected navigation path, corresponding to the pre-generated navigation path in the pre-defined region, based on the intended distance and the set of offset distances.

10. A system for correcting a pre-generated navigation path for an autonomous vehicle, the system comprising: a navigation device comprising at least one processor and a computer-readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising: receiving the pre-generated navigation path on a navigation map, an environmental field of view (FOV) of the autonomous vehicle, and a location of the autonomous vehicle on the pre-generated navigation path; determining a set of new data points in a pre-defined region with respect to the location of autonomous vehicle based on the environmental FOV and the navigation map; determining an offset of the pre-generated navigation path in the pre-defined region based on the set of new data points; and correcting the pre-generated navigation path in the pre-defined region based on the offset.

11. The system of claim 10, wherein the pre-defined region is a region up to a certain pre-defined distance in front of the autonomous vehicle based on a curvature of the pre-generated navigation path, along each side of the pre-generated navigation path, from a pre-defined start height above a road surface and up to a pre-defined end height above the road surface.

12. The system of claim 10, wherein determining the set of new data points comprises: comparing a plurality of data points in the pre-defined region of the environmental FOV with a plurality of data points in the pre-defined region of the navigation map; and based on the comparison, identifying a set of data points in the pre-defined region of the environmental FOV that have no corresponding data points in the navigation map within a pre-defined threshold.

13. The system of claim 10, wherein determining the offset comprises determining a set of offset distances along the pre-generated navigation path with respect to the set of new data points.

14. The system of claim 13, wherein determining each of the set of offset distances comprises: projecting a virtual ray at a pre-defined projection angle from the autonomous vehicle; computing a distances between the autonomous vehicle and a first data point from the set of new data points in the line of the virtual ray; and computing an offset distance between the pre-generated navigation path and the first data point based on the distance and the pre-defined projection angle.

15. The system of claim 13, wherein correcting the pre-generated navigation path comprises: determining an actual drivable road width along the pre-generated navigation path in the pre-defined region based on the set of offset distances; and determining a corrected navigation path, corresponding to the pre-generated navigation path in the pre-defined region, based on the actual drivable road width.

16. The system of claim 13, wherein correcting the pre-generated navigation path comprises: identifying an intended distance of the autonomous vehicle from an obstacle or a no-go region of at least one side along the pre-generated navigation path in the pre-defined region; and determining a corrected navigation path, corresponding to the pre-generated navigation path in the pre-defined region, based on the intended distance and the set of offset distances.

Dated this 29th day of September, 2017

Swetha SN Of K&S Partners Agent for the Applicant IN/PA-2123 , Description:TECHNICAL FIELD

This disclosure relates generally to autonomous vehicle, and more particularly to method and system for correcting a pre-generated navigation path for an autonomous vehicle.