Systems and methods for autonomous vehicle path follower correction

Patent metadata

Field	Value
Publication number	US-10976745-B2
Application number	US-201815892911-A
Country	US
Kind code	B2
Filing date	Feb 9, 2018
Priority date	Feb 9, 2018
Publication date	Apr 13, 2021
Grant date	Apr 13, 2021

Abstract

Systems and methods are provided for generating a vehicle path to operate an autonomous vehicle. A method includes using a lateral re-entry planner system to correct for a lateral reentry error. A longitudinal re-entry planner system is used to correct a longitudinal reentry error. Path correction commands are generated based upon the corrections provided by the lateral re-entry planner system and the longitudinal re-entry planner system.

First claim

What is claimed is:

1. A method for generating a vehicle path to operate an autonomous vehicle, comprising:
receiving, by one or more processors, data indicative of a vehicle path and data indicative of an initial position from a localization system for determining a lateral reentry error and a longitudinal reentry error;
using, by the one or more processors, a lateral re-entry planner system for determining a trajectory subject to curvature and heading restraints for following the vehicle path based upon the lateral reentry error, to thereby generate a spatial plan using a first convex quadratic cost function;
using, by the one or more processors, a longitudinal re-entry planner system for determining a trajectory subject to acceleration, velocity, and travel restraints for following the vehicle path based upon the longitudinal reentry error, to thereby generate a temporal plan using a second convex quadratic cost function;
generating path correction commands based upon the determined trajectory of the lateral re-entry planner system and the determined trajectory of the longitudinal re-entry planner system, by fusing results from the spatial plan with results from the temporal plan, generating a series of points along a path of travel for the autonomous vehicle; and
transmitting the generated path correction commands for controlling the autonomous vehicle.

2. The method of claim 1 , wherein the determined trajectory of the lateral re-entry planner system and the determined trajectory of the longitudinal re-entry planner system are combined to generate a local plan for serving as a reference for control of the autonomous vehicle.

3. The method of claim 1 , wherein the trajectory determined by the lateral re-entry planner system corrects for the lateral reentry error by solving for a path reentry plan for placing the autonomous vehicle on a correct path plan.

4. The method of claim 1 , wherein the trajectory determined by the longitudinal re-entry planner system corrects for the longitudinal reentry error by solving for a path reentry plan for placing the autonomous vehicle on a correct path plan.

5. The method of claim 1 , wherein the generated path correction commands are transmitted to control steering, braking, and engine components of the autonomous vehicle.

6. The method of claim 1 , wherein the generating of the path correction commands comprises generating the path correction commands based upon the determined trajectory of the lateral re-entry planner system and the determined trajectory of the longitudinal re-entry planner system, by interpolating values of the spatial plan from the lateral re-entry planner system and the temporal plan from the longitudinal re-entry planner system at predetermined intervals of time and space.

7. The method of claim 1 , wherein each point along the path is being associated with a time, x position, y position, velocity, acceleration, curvature, and heading, and creates a trajectory that is used as a reference for travel for the autonomous vehicle.

8. The method of claim 1 , wherein the first convex quadratic cost function optimizes cost based on smoothness of travel.

9. The method of claim 1 , wherein the first convex quadratic cost function utilizes cross track error (CTE) constraints, including avoidance of lane boundaries, turn radius, steering wheel velocity, and steering wheel acceleration using previous values from the longitudinal re-entry planner system.

10. The method of claim 1 , wherein the first convex quadratic cost function utilizes a kinematic model with the following states: deviation from lane center; heading; curvature; and spatial jerk.

11. The method of claim 1 , wherein the second convex quadratic cost function optimizes cost based on speed limits, acceleration limits, and jerk limits.

12. A system for generating a vehicle path to operate an autonomous vehicle, comprising:
a storage device for storing instructions for generating the vehicle path; and
one or more data processors configured to execute the instructions to:
receive data indicative of a vehicle path and data indicative of an initial position from a localization system for determining a lateral reentry error and a longitudinal reentry error;
use a lateral re-entry planner system for determining a trajectory subject to curvature and heading restraints for following the vehicle path based upon the lateral reentry error, to thereby generate a spatial plan using a first convex quadratic cost function;
use a longitudinal re-entry planner system for determining trajectory subject to acceleration, velocity, and travel restraints for following the vehicle path based upon the longitudinal reentry error, to thereby generate a temporal plan using a second convex quadratic cost function;
generate path correction commands based upon the determined trajectory of the lateral re-entry planner system and the determined trajectory of the longitudinal re-entry planner system, by fusing results from the spatial plan with results from the temporal plan, generating a series of points along a path of travel for the autonomous vehicle; and
transmit the generated path correction commands for controlling the autonomous vehicle.

13. The system of claim 12 , wherein the determined trajectory of the lateral re-entry planner system and the determined trajectory of the longitudinal re-entry planner system are combined to generate a local plan for serving as a reference for control of the autonomous vehicle.

14. The system of claim 12 , wherein the trajectory determined by the lateral re-entry planner system corrects for the lateral reentry error by solving for a path reentry plan for placing the autonomous vehicle on a correct path plan.

15. The system of claim 12 , wherein the trajectory determined by the longitudinal re-entry planner system corrects for the longitudinal reentry error by solving for a path reentry plan for placing the autonomous vehicle on a correct path plan.

16. The system of claim 12 , wherein the generated path correction commands are transmitted to control steering, braking, and engine components of the autonomous vehicle.

17. An autonomous vehicle comprising:
a camera and lidar sensor that provides sensor data; and
a controller that, by a processor and based on the sensor data, is configured to:
receive data indicative of a vehicle path and data indicative of an initial position from a localization system for determining a lateral reentry error and a longitudinal reentry error;
use a lateral re-entry planner system for determining a trajectory subject to curvature and heading restraints for following the vehicle path based upon the lateral reentry error, to thereby generate a spatial plan using a first convex quadratic cost function;
use a longitudinal re-entry planner system for determining trajectory subject to acceleration, velocity, and travel restraints for following the vehicle path based upon the longitudinal reentry error, to thereby generate a temporal plan using a second convex quadratic cost function;
generate path correction commands based upon the determined trajectory of the lateral re-entry planner system and the determined trajectory of the longitudinal re-entry planner system, by fusing results from the spatial plan with results from the temporal plan, generating a series of points along a path of travel for the autonomous vehicle; and
transmit the generated path correction commands for controlling the autonomous vehicle.

Assignees

• Gm Global Tech Operations Llc

Inventors

• Chu Kevin
• Haghighat Sohrab
• Reed Brooks

Classifications

• G08G1/202

  Dispatching vehicles on the basis of a location, e.g. taxi dispatching · CPC title

• B60W2050/0043

  Signal treatments, identification of variables or parameters, parameter estimation or state estimation · 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

• G01C21/3446

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

• G05D1/0217 Primary

  in accordance with energy consumption, time reduction or distance reduction criteria · CPC title