Trajectory planner for autonomous driving using bézier curves

• US 10,427,676 B2
• Filed: 05/31/2017
• Issued: 10/01/2019
• Est. Priority Date: 05/31/2017
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Jafari Tafti, Sayyed Rouhollah, Mehdi, Syed B., Palanisamy, Praveen
• Primary Examiner(s): Elchanti, Hussein
• Assistant Examiner(s): Berns, Michael A
• Application Number:
  US15/609,344
• Publication Number:
  US 20180348767A1
• Time in Patent Office: 853 Days
• CPC Class Codes: B60W 2520/06 Direction of travel
• CPC Class Codes: B60W 2520/10 Longitudinal speed
• CPC Class Codes: B60W 2520/105 Longitudinal acceleration
• CPC Class Codes: B60W 2554/4041 Position
• CPC Class Codes: B60W 2554/804 Relative longitudinal speed
• CPC Class Codes: B60W 2556/50 of positioning data, e.g. GPS [Global Positioning System] data
• CPC Class Codes: B60W 2556/65 Data transmitted between vehicles
• CPC Class Codes: B60W 2756/10 Involving external transmission of data to or from the vehicle
• CPC Class Codes: B60W 30/0953 the prediction being responsive to vehicle dynamic parameters
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: G05D 1/0217 in accordance with energy consumption, time reduction or distance reduction criteria
• CPC Class Codes: G08G 1/161 Decentralised systems, e.g. inter-vehicle communication
• CPC Class Codes: G08G 1/163 involving continuous checking
• CPC Class Codes: G08G 1/165 for passive traffic, e.g. including static obstacles, trees
• CPC Class Codes: G08G 1/166 for active traffic, e.g. moving vehicles, pedestrians, bikes
• CPC Class Codes: G08G 1/202 Dispatching vehicles on the basis of a location, e.g. taxi dispatching

Abstract

Systems and methods are provided for controlling a vehicle. In one embodiment, a method includes receiving vehicle state data, high-definition map data, and vehicle object environment data, generating a trajectory path that is optimal with respect to the received data, determining whether to update the trajectory path using Bézier curves based on the received data, performing an assessment of the trajectory using properties of Bézier curves, and generating an updated trajectory.

Claims

1. A processor-implemented method for automated driving of a vehicle, comprising:

receiving, by one or more data processors, vehicle state data, map data, and vehicle object environment data;

generating, by the one or more data processors, a first trajectory path using trajectory waypoints determined via a graph-based approach that is optimal with respect to the vehicle state data, the map data, and the vehicle object environment data;

generating, by the one or more data processors, an updated trajectory path based on the vehicle state data and the vehicle object environment data, including performing a trajectory assessment using properties of Bé

zier curves such that the updated trajectory path matches a current vehicle state;

determining, by the one or more data processors, whether the updated trajectory path satisfies an environmental constraint

in response to the updated trajectory path not satisfying the environmental constraint, updating a speed profile of the updated trajectory path using properties of Bé

zier curves;

determining, by the one or more data processors, whether the updated trajectory path with the updated speed profile satisfies the environmental constraint;

in response to the updated trajectory path with the updated speed profile not satisfying the environmental constraint, updating a spatial component of the updated trajectory path using properties of Bé

zier curves;

determining, by the one or more data processors, whether the updated trajectory path with the updated speed profile and the updated spatial component satisfies the environmental constraint;

in response to the updated trajectory path with the updated speed profile and the updated spatial component not satisfying the environmental constraint, generating a second trajectory path using trajectory waypoints determined via a graph-based approach; and

in response to the updated trajectory path with the updated speed profile and the updated spatial component satisfying the environmental constraint, providing the updated trajectory path to a controller of the vehicle for implementing a driving scenario plan.

2. The method of claim 1, wherein the vehicle object environment data includes data related to other vehicles in the vicinity of the first trajectory path.

3. The method of claim 2, further comprising reviewing and checking the updated trajectory path for possible collisions with other vehicles detected in the vicinity of the updated trajectory path based on the vehicle object environment data.

4. The method of claim 3, wherein reviewing and checking the updated trajectory includes assessing the updated trajectory with a projected trajectory of a target vehicle using Bé

zier curves.

5. The method of claim 1, wherein the received vehicle state data, map data, and vehicle object environment data are provided by one of the following modules:

a sensor fusion module for listing detected remote road users and obstacles on the road;

a map module which includes details about a road network and traffic flow restrictions; and

a vehicle state module for determining a current state of the vehicle.

6. The method of claim 5, wherein the current state of the vehicle includes one or more of a vehicle position, a vehicle heading, a vehicle velocity, and a vehicle acceleration.

7. An autonomous vehicle, comprising:

at least one sensor that provides sensor data about objects within the vehicle'"'"'s environment and about a vehicle state; and

a controller that, by a processor and based on the sensor data, is configured to

generate a first trajectory path using trajectory waypoints determined via a graph-based approach that is optimal with respect to the received sensor data;

generate an updated trajectory path based on the sensor data by performing a trajectory assessment using properties of Bé

zier curves;

determine if the updated trajectory path satisfies an environmental constraint;

in response to the updated trajectory path not satisfying the environmental constraint, generate, using properties of Bé

zier curves, a second updated trajectory path having one or more of a speed profile update and a spatial component update;

verify the second updated trajectory path satisfies the environmental constraint; and

provide the updated trajectory path to a controller of the vehicle for implementing a driving scenario plan.

8. The autonomous vehicle of claim 7, wherein the vehicle object environment data includes data related to other vehicles in the vicinity of the first trajectory path.

9. The autonomous vehicle of claim 7, wherein the vehicle state data includes one or more of a vehicle position, a vehicle heading, a vehicle velocity, and a vehicle acceleration.

10. The autonomous vehicle of claim 7, wherein the controller is further configured to review and check the updated trajectory path for possible collisions with other vehicles detected in the vicinity of the updated trajectory path based on the vehicle environment data.

11. The autonomous vehicle of claim 10, wherein reviewing and checking the updated trajectory includes assessing the updated trajectory with a projected trajectory of a target vehicle using Bé

zier curves.

12. A system for automated driving of a vehicle, comprising;

a data communication pathway for transmitting vehicle state data, map data, and vehicle object environment data; and

one or more data processors configured to generate a first trajectory path using trajectory waypoints determined via a graph-based approach based the received vehicle state data, map data, and vehicle object environment data;

generate an updated trajectory path based on the vehicle state data and the vehicle object environment data by performing a trajectory assessment using properties of Bezier curves, the updated trajectory path including changes to one or more of a speed profile and a spatial path;

determine if the updated trajectory path satisfies an environmental constraint;

in response to the updated trajectory path not satisfying the environmental constraint, generate, using properties of Bezier curves, a second updated trajectory path having one or more of a speed profile update and a spatial component update;

verify the second updated trajectory path satisfies the environmental constraint; and

provide the updated trajectory path to a controller of the vehicle for implementing a driving scenario plan.

13. The system of claim 12, wherein the vehicle object environment data includes one or more of position and velocity data related to other vehicles in the vicinity of the first trajectory path.

14. The system of claim 13, wherein the one or more data processors are further configured to review and check the updated trajectory path for possible collisions with other vehicles detected in the vicinity of the updated trajectory path based on the vehicle object environment data.

15. The system of claim 14, wherein reviewing and checking the updated trajectory includes assessing the updated trajectory with a projected trajectory of a target vehicle using Bé

zier curves.

16. The system of claim 12, wherein the vehicle state data includes one or more of a vehicle position, a vehicle heading, a vehicle velocity, and a vehicle acceleration.

17. The system of claim 12, wherein the map data includes one or more of road network details and traffic flow restrictions.