VEHICLE TRAJECTORY PLANNING FOR AUTONOMOUS VEHICLES

• US 20150346723A1
• Filed: 05/30/2014
• Published: 12/03/2015
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan North America Incorporated (Nissan Motor Co., Ltd.)
• Inventors: Pedersen, Liam
• Granted Patent: US 9,244,462 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: B60W 30/10 Path keeping cruise control for automatically following a preceding vehicle B60W30/165
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0217 in accordance with energy consumption, time reduction or distance reduction criteria

Abstract

A method for controlling an autonomous vehicle includes obtaining, by one or more processors, information describing a current state of the autonomous vehicle and a goal state of the autonomous vehicle; determining, by the one or more processors, an initial vehicle trajectory from the current state of the autonomous vehicle to the goal state of the autonomous vehicle; and determining, by the one or more processors, an optimized vehicle trajectory based the initial trajectory and a velocity profile by applying numerical minimization to minimize a trajectory length value and a lateral acceleration value.

Claims

1. A method for controlling an autonomous vehicle, comprising:

obtaining, by one or more processors, information describing a current state of the autonomous vehicle and a goal state of the autonomous vehicle;

determining, by the one or more processors, an initial vehicle trajectory from the current state of the autonomous vehicle to the goal state of the autonomous vehicle; and

determining, by the one or more processors, an optimized vehicle trajectory based the initial trajectory and a velocity profile by applying numerical minimization to minimize a trajectory length value and a lateral acceleration value.

2. The method of claim 1, wherein the optimized vehicle trajectory corresponds to a set of control inputs.

3. The method of claim 1, wherein the set of control inputs includes a plurality steering angle values that are each associated with a discrete location along the optimized vehicle trajectory.

4. The method of claim 1, wherein the velocity profile is predetermined, and determining the optimized vehicle trajectory does not include modifying the velocity profile.

5. The method of claim 1, wherein the trajectory length value is a function of a length from the current state to the goal state and a trajectory length weighting factor, and the lateral acceleration value is a function of a maximum lateral acceleration value from the current state to the goal state and a lateral acceleration weighting factor.

6. The method of claim 1, wherein the determining the initial vehicle trajectory fitting the trajectory to the current state of the autonomous vehicle and the goal state of the autonomous vehicle using a vehicle dynamics model.

7. The method of claim 1, wherein determining the optimized vehicle trajectory is performed by applying Levenberg-Marquardt minimization.

8. A control apparatus for an autonomous vehicle, comprising:

one or more processors; and

one or more memory devices for storing program instructions used by the one or more processors, wherein the program instructions, when executed by the one or more processors, cause the one or more processors to;

obtain information describing a current state of the autonomous vehicle and a goal state of the autonomous vehicle,

determine an initial vehicle trajectory from the current state of the autonomous vehicle to the goal state of the autonomous vehicle, and

determine an optimized vehicle trajectory based the initial trajectory and a velocity profile by applying numerical minimization to minimize a trajectory length value and a lateral acceleration value.

9. The control apparatus of claim 8, wherein the optimized vehicle trajectory corresponds to a set of control inputs.

10. The control apparatus of claim 8, wherein the set of control inputs includes a plurality steering angle values that are each associated with a discrete location along the optimized vehicle trajectory.

11. The control apparatus of claim 8, wherein the velocity profile is predetermined, and determining the optimized vehicle trajectory does not include modifying the velocity profile.

12. The control apparatus of claim 8, wherein the trajectory length value is a function of a length from the current state to the goal state and a trajectory weighting factor, and the lateral acceleration value is a function of a maximum lateral acceleration value from the current state to the goal state and a lateral acceleration weighting factor.

13. The control apparatus of claim 8, wherein the determining the initial vehicle trajectory fitting the trajectory to the current state of the autonomous vehicle and the goal state of the autonomous vehicle using a vehicle dynamics model.

14. The control apparatus of claim 8, wherein determining the optimized vehicle trajectory is performed by applying Levenberg-Marquardt minimization.

15. An autonomous vehicle, comprising:

a trajectory planning system that includes one or more processors and one or more memory devices for storing program instructions used by the one or more processors, wherein the program instructions, when executed by the one or more processors, cause the one or more processors to;

obtain information describing a current state of the autonomous vehicle and a goal state of the autonomous vehicle,

determine an initial vehicle trajectory from the current state of the autonomous vehicle to the goal state of the autonomous vehicle, and

determine an optimized vehicle trajectory based the initial trajectory and a velocity profile by applying numerical minimization to minimize a trajectory length value and a lateral acceleration value;

a steering device that is operable to change a steering angle of at least one steered wheel; and

a steering control system operable output a steering control signal to the steering device for controlling operation of the steering device, wherein the steering control system generates the steering control signal based on the optimized trajectory.

16. The autonomous vehicle of claim 15, wherein the optimized vehicle trajectory corresponds to a set of control inputs.

17. The control apparatus of claim 15, wherein the set of control inputs includes a plurality steering angle values that are each associated with a discrete location along the optimized vehicle trajectory.

18. The autonomous vehicle of claim 15, wherein the velocity profile is predetermined, and determining the optimized vehicle trajectory does not include modifying the velocity profile.

19. The autonomous vehicle of claim 15, wherein the trajectory length value is a function of a length from the current state to the goal state and a trajectory weighting factor, and the lateral acceleration value is a function of a length from the current state to the goal state and a lateral acceleration weighting factor.

20. The autonomous vehicle of claim 15, wherein the determining the initial vehicle trajectory fitting the trajectory to the current state of the autonomous vehicle and the goal state of the autonomous vehicle using a vehicle dynamics model.

21. The autonomous vehicle of claim 15, wherein determining the optimized vehicle trajectory is performed by applying Levenberg-Marquardt minimization.