Path determining apparatus for autonomous driving vehicle and path determining method

Patent metadata

Field	Value
Publication number	US-10073458-B2
Application number	US-201715462612-A
Country	US
Kind code	B2
Filing date	Mar 17, 2017
Priority date	Nov 11, 2016
Publication date	Sep 11, 2018
Grant date	Sep 11, 2018

Abstract

A path determining apparatus for an autonomous driving vehicle includes a path generator periodically generating a plurality of autonomous driving paths, an adaptive likelihood field (ALF) detector detecting an ALF on a road based on road information and obstacle information, a weight setter applying the ALF detected by the ALF detector to each of the autonomous driving paths generated by the path generator to set a weight with respect to each of the autonomous driving paths, and a path determiner determining a final autonomous driving path based on the weight set with respect to each of the autonomous driving paths by the weight setter.

First claim

What is claimed is:

1. A path determining apparatus for an autonomous driving vehicle, the apparatus comprising:
a processor; and
a memory storing a program to be executed in the processor, the program comprising instructions for:
periodically generating a plurality of autonomous driving paths,
detecting an adaptive likelihood field (ALF) on a road based on road information and obstacle information, wherein the instructions for detecting the ALF comprise instructions for detecting the ALF based on the road information such that the autonomous driving vehicle drives along a center of a lane,
applying the detected ALF to each of the autonomous driving paths generated and setting a weight with respect to each of the autonomous driving paths, and
determining a final autonomous driving path based on the weight set with respect to each of the autonomous driving paths.

2. The path determining apparatus of claim 1 , wherein the instructions for periodically generating the plurality of autonomous driving paths comprise instructions for:
calculating target positions at a current time point based on target positions calculated at a previous time point and present driving information, and
updating the autonomous driving paths.

3. The path determining apparatus of claim 2 , wherein the driving information comprise a speed of the vehicle, an azimuth of the vehicle, and model information of the vehicle.

4. The path determining apparatus of claim 1 , wherein the obstacle information comprise static obstacle information and dynamic obstacle information.

5. The path determining apparatus of claim 4 , wherein the instructions for detecting the ALF comprise instructions for:
detecting a first ALF based on the road information such that the vehicle drives along the center of the lane;
detecting a second ALF based on the static obstacle information such that the vehicle avoids a collision with a static obstacle;
detecting a third ALF based on the dynamic obstacle information such that the vehicle avoids a collision with a dynamic obstacle; and
integrating the first ALF, the second ALF, and the third ALF to generate a final ALF.

6. The path determining apparatus of claim 5 , wherein the road information comprise at least one of a lane of the road, a width of the road, or a shape of the road.

7. The path determining apparatus of claim 5 , wherein the static obstacle information comprise at least one of a position, a size, or a shape of the static obstacle on the road.

8. The path determining apparatus of claim 5 , wherein the dynamic obstacle information comprise at least one of a position, a speed, a direction, a size, or a shape of the dynamic obstacle on the road.

9. The path determining apparatus of claim 1 , wherein instructions for applying the detected ALF to each of the autonomous driving paths generated and setting a weight with respect to each of the autonomous driving paths comprise instructions for:
giving a high weight to an autonomous driving path in which the autonomous driving vehicle has a low probability of collision with an obstacle among the autonomous driving paths.

10. The path determining apparatus of claim 9 , wherein instructions for determining a final autonomous driving path comprise instructions for:
determining the autonomous driving path given with the high weight as the final autonomous driving path.

11. An autonomous driving vehicle comprising:
a path determining apparatus comprising a processor and a memory storing a program to be executed in the processor, the program comprising instructions for:
periodically generating a plurality of autonomous driving paths,
detecting an adaptive likelihood field (ALF) on a road based on road information and obstacle information, wherein the instructions for detecting the ALF comprise instructions for detecting the ALF based on the road information such that the autonomous driving vehicle drives along a center of a lane,
applying the detected ALF to each of the autonomous driving paths generated and setting a weight with respect to each of the autonomous driving paths, and
determining a final autonomous driving path based on the weight set with respect to each of the autonomous driving paths.

12. The autonomous driving vehicle of claim 11 , wherein the instructions for periodically generating the plurality of autonomous driving paths comprise instructions for:
calculating target positions at a current time point based on target positions calculated at a previous time point and present driving information, and
updating the autonomous driving paths.

13. The autonomous driving vehicle of claim 12 , wherein the driving information comprise a speed of the vehicle, an azimuth of the vehicle, and model information of the vehicle.

14. The autonomous driving vehicle of claim 11 , wherein instructions for applying the detected ALF to each of the autonomous driving paths generated and setting a weight with respect to each of the autonomous driving paths comprise instructions for:
giving a high weight to an autonomous driving path in which the autonomous driving vehicle has a low probability of collision with an obstacle among the autonomous driving paths.

15. The autonomous driving vehicle of claim 14 , wherein instructions for determining a final autonomous driving path comprise instructions for:
determining the autonomous driving path given with the high weight as the final autonomous driving path.

16. An autonomous driving vehicle comprising:
a path determining apparatus comprising a processor and a memory storing a program to be executed in the processor, the program comprising instructions for:
periodically generating a plurality of autonomous driving paths,
detecting an adaptive likelihood field (ALF) on a road based on road information and obstacle information, wherein the obstacle information comprise static obstacle information and dynamic obstacle information, wherein the instructions for detecting the ALF comprise instructions for detecting the ALF based on the road information such that the autonomous driving vehicle drives along a center of a lane,
applying the detected ALF to each of the autonomous driving paths generated and setting a weight with respect to each of the autonomous driving paths, and
determining a final autonomous driving path based on the weight set with respect to each of the autonomous driving paths.

17. The autonomous driving vehicle of claim 16 , wherein the instructions for detecting the ALF comprise instructions for:
detecting a first ALF based on the road information such that the drives along the center of the lane;
detecting a second ALF based on the static obstacle information such that the vehicle avoids a collision with a static obstacle;
detecting a third ALF based on the dynamic obstacle information such that the vehicle avoids a collision with a dynamic obstacle; and
integrating the first ALF, the second ALF, and the third ALF to generate a final ALF.

18. The autonomous driving vehicle of claim 17 , wherein the road information comprise at least one of a lane of the road, a width of the road, or a shape of the road.

19. The autonomous driving vehicle of claim 17 , wherein the static obstacle information comprise at least one of a position, a size, or a shape of the static obstacle on the road.

20. The autonomous driving vehicle of claim 17 , wherein the dynamic obstacle information comprise at least one of a position, a speed, a direction, a size, or a shape of the dynamic obstacle on the

Assignees

• Hyundai Motor Co Ltd

Inventors

• Kim Jun Soo

Classifications

• G01C21/3446 Primary

  Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags or using precalculated routes · CPC title

• G08G1/165

  for passive traffic, e.g. including static obstacles, trees · CPC title

• G08G1/166

  for active traffic, e.g. moving vehicles, pedestrians, bikes · CPC title

• G01C21/3415

  Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents · CPC title

• B60W60/001

  Planning or execution of driving tasks · CPC title