Lane change path planning algorithm for autonomous driving vehicle

• US 9,428,187 B2
• Filed: 06/05/2014
• Issued: 08/30/2016
• Est. Priority Date: 06/05/2014
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Lee, Jin-Woo
• Primary Examiner(s): Kan, Yuri
• Application Number:
  US14/297,415
• Publication Number:
  US 20150353085A1
• Time in Patent Office: 817 Days
• Field of Search: 701/36, 701/93, 701/117, 701/118, 701/400, 701/445, 701/490, 701/532, 701/533, 362/494
• US Class Current: 1/1
• CPC Class Codes: B60W 2420/403 Image sensing, e.g. optical camera
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: B60W 30/12 Lane keeping

Abstract

A system and method for providing path planning and generation for automated lane centering and/or lane changing purposes for a vehicle traveling on a roadway, where the method employs roadway measurement values from a vision camera within an effective range of the camera and roadway measurement values from a map database beyond the range of the camera. The method uses the roadway measurement values from the camera to determine a desired path along a first segment of the roadway and identifies an end of the first segment based on how accurately the camera defines the roadway. The method then uses the roadway measurement values from the map database to determine the desired path along a second segment of the roadway that begins at the end of the first segment, where a transition from the first segment to the second segment is smooth.

Claims

1. A method for generating a desired path for a vehicle to follow along a roadway, said vehicle including at least one forward-looking camera and a map database, said method comprising:

providing roadway measurement values from the camera that identifies locations on the roadway;

providing roadway measurement values from the map database that identifies locations on the roadway;

determining the desired path along a first segment of the roadway using the roadway measurement values from the camera;

identifying an end of the first segment based on an effective range of the camera; and

determining the desired path along a second segment of the roadway using the roadway measurement values from the map database, where the second segment begins at the end of the first segment.

2. The method according to claim 1 wherein the method automatically calculates multiple segments to define the desired path for the vehicle to follow for both lane centering and lane changing purposes.

3. The method according to claim 1 wherein determining the desired path along multiple segments includes solving a fifth-order polynomial equation.

4. The method according to claim 1 wherein identifying the end of the first segment includes determining an error between the roadway measurement values from the camera and the desired path along the first segment.

5. The method according to claim 4 wherein identifying the end of the first segment includes employing a cost function that identifies the difference between the measured values and the desired path and determining when the cost function exceeds a predetermined cost function threshold.

6. The method according to claim 5 wherein identifying the end of the first segment includes minimizing the cost function J as:

7. The method according to claim 1 wherein determining the desired path along the second segment of the roadway using the roadway measurement values from the map database includes using roadway measurement values at a last location point in the first segment as roadway measurement values as a first location point in the second segment.

8. The method according to claim 7 wherein determining the desired path along the second segment of the roadway using the roadway measurement values from the map database includes matching a slope of the desired path at the end of the first segment to a slope of the desired path at the beginning of the second segment.

9. The method according to claim 1 further comprising determining the desired path along a third segment of the roadway that begins at the end of the second segment using the roadway measurement values from the map database, wherein a transition between the second segment and the third segment occurs if a curvature of the roadway exceeds a predetermined threshold.

10. The method according to claim 9 wherein the roadway measurement values are used to determine a first location point in the third segment as a last location point in the second segment.

11. The method according to claim 10 wherein the first location point in the third segment is calculated from roadway measurement points from the map database and by solving a cost function.

12. The method according to claim 11 wherein the cost function J is defined as:

13. The method according to claim 1 further comprising determining that a vehicle lane change has been commanded, determining how many segments are required to make the lane change and making the lane change over multiple segments.

14. The method according to claim 13 wherein determining how many segments are required to make the lane change includes determining a time required for making the lane change at a current vehicle speed and how far from a current vehicle position the lane change will end.

15. The method according to claim 14 wherein making the lane change includes using the roadway measurement values from the camera to initiate the lane change and using the roadway measurement values from the map database to end the lane change.

16. A method for generating a desired path for a vehicle to follow along a roadway, said vehicle including at least one forward-looking camera and a map database, said method comprising:

providing roadway measurement values from the camera that identifies locations on the roadway;

providing roadway measurement values from the map database that identifies locations on the roadway;

determining the desired path along a first segment of the roadway using the roadway measurement values from the camera by solving a fifth order polynomial equation;

identifying an end of the first segment based on an effective range of the camera where an error between the roadway measurement values from the camera and the desired path along the first segment exceeds a predetermined cost function threshold; and

determining the desired path along a second segment of the roadway using the roadway measurement values from the map database, where the second segment of the roadway begins at the end of the first segment, and wherein determining the desired path along the second segment of the roadway using the roadway measurement values from the map database includes using roadway measurement values at a last location point in the first segment as roadway measurement values as a first location point in the second segment and matching a slope of the desired path at the end of the first segment to a slope of the desired path at the beginning of the second segment.

17. The method according to claim 16 further comprising determining the desired path along a third segment of the roadway using the roadway measurement values from the map database, where the third segment begins at the end of the second segment, wherein a transition between the second segment and the third segment occurs if a curvature of the roadway exceeds a predetermined threshold.

18. The method according to claim 16 further comprising determining that a vehicle lane change has been commanded, determining how many segments are required to make the lane change and making the lane change.

19. The method according to claim 18 wherein determining how many segments are required to make the lane change includes determining a time required for making the lane change at a current vehicle speed and how far from a current vehicle position the lane change will end.

20. A system for generating a desired path for a vehicle to follow along a roadway, said vehicle including at least one forward looking camera and a map database, said system comprising:

means for providing roadway measurement values from the camera that identifies locations on the roadway;

means for providing roadway measurement values from the map database that identifies locations on the roadway;

means for determining the desired path along a first segment of the roadway using the roadway measurement values from the camera;

means for identifying an end of the first segment based on an effective range of the camera; and

means for determining the desired path along a second segment of the roadway using the roadway measurement values from the map database, where the second segment begins at the end of the first segment.