Path planning for autonomous driving

• US 10,274,961 B2
• Filed: 07/26/2017
• Issued: 04/30/2019
• Est. Priority Date: 07/26/2017
• Status: Active Grant

• Current Assignee: GM Global Technology Operations LLC (General Motors Company)
• Original Assignee: GM Global Technology Operations LLC (General Motors Company)
• Inventors: Lee, Jin-Woo
• Primary Examiner(s): Arthur Jeanglaude, Gertrude
• Application Number:
  US15/660,115
• Publication Number:
  US 20190033871A1
• Time in Patent Office: 643 Days
• Field of Search: 701 23, 701 26, 701532
• CPC Class Codes: G01C 21/38 Electronic maps specially adapted for navigation; Updating thereof
• 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 1/0212 with means for defining a desired trajectory involving a plurality of land vehicles G05D1/0287
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 20/58 Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

System and methods are provided for path finding for autonomous driving systems. The systems and methods receive a set of way points defining path segments between adjacent way points, formulate a b-spline function as a function of the path segments, and determine path data based on the formulated b-spline function. Autonomous driving systems use the output path data for controlling a vehicle.

Claims

1. A computer implemented method for finding a path for an autonomous driving system, comprising:

receiving, by a processor, a set of way points defining path segments between adjacent way points;

formulating, by a processor, a baseline b-spline function of b-spline basis terms, the baseline b-spline function formulated as a function of the path segments, the baseline b-spline function having parametric coefficients associated with each of the b-spline basis terms;

determining, by a processor, initial conditions to include an offset to a target path y₀, a heading angle φ

₀, and initial curvature ρ

₀ at a time t equal to zero;

determining, by a processor, boundary conditions to include an offset y_f, a heading angle φ

_f, an initial curvature ρ

_f at t=t_f, where t_f and t₀ are times at the start and end of a segment;

solving, by a processor, the baseline b-spline function based on the initial conditions and the boundary conditions at each way point to provide second order parametric curve continuity;

determining, by a processor, path data based on results of the solved baseline b-spline function; and

controlling, by a processor, a path of the vehicle based on the path data.

2. The method of claim 1, wherein the way points each include x and y coordinates.

3. The method of claim 1, wherein the path data corresponds to a path that includes at least one turn that is 90°

or smaller or greater.

4. The method of claim 1, configured to receive at least one additional way point after the path data has been determined, and adjust the determined path data by formulating and solving an adjusted b-spline function.

5. A computer implemented system for controlling a vehicle, comprising:

a path finding engine configured to, by a processor;

receive a set of way points defining path segments between adjacent way points;

formulate a baseline b-spline function of b-spline basis terms, the baseline b-spline function formulated as a function of the path segments, the baseline b-spline function having parametric coefficients associated with each of the b-spline basis terms;

determine initial conditions to include an offset to a target path y₀, a heading angle φ

₀, and initial curvature ρ

₀ at a time t equal to zero;

determine boundary conditions to include an offset y_f, a heading angle φ

_f, an initial curvature ρ

_r at t=t_f, where t_f and t₀ are times at the start and end of a segment;

solve the baseline b-spline function based on the initial conditions and the boundary conditions at each way point to provide second order parametric curve continuity;

determine path data based on results of the solved baseline b-spline function; and

output path data; and

an autonomous driving system configured to, by a processor, control a vehicle to traverse a path defined by the path data output by the path finding engine.

6. The system of claim 5, comprising an object detection system configured to detect at least one object along the path and to determine at least one additional way point to avoid the obstacle, wherein the path finding engine is configured to determine and output adjusted path data using the at least one additional way point, and wherein the autonomous driving system is configured to control the vehicle to traverse an adjusted path defined by the adjusted path data.

7. The system of claim 6, wherein the object detection system is configured to detect the at least one object using data from an object sensing system comprising at least one of a camera, radar, Lidar, ultrasonic sensor, any type of range finding sensor, any type of object detection sensor, and a fusion thereof.

8. The system of claim 6, comprising a lane detection system configured to detect at least one of lane and road boundaries based on data from at least one of a lane sensing system and a road sensing system comprising at least one of a camera, radar, Lidar, ultrasonic sensor and a fusion thereof, wherein the objection detection system and the lane detection system are configured to determine the at least one additional way point to avoid the obstacle.

9. The system of claim 5, comprising a navigation system configured to receive destination data, roadway networks, and to determine the set of way points leading the vehicle to a destination corresponding to the destination data.

10. A vehicle, comprising:

a path finding engine configured to, by a processor;

receive a set of way points defining path segments between adjacent way points;

formulate a baseline b-spline function of b-spline basis terms, the baseline b-spline function formulated as a function of the path segments, the baseline b-spline function having parametric coefficients associated with each of the b-spline basis terms;

determine initial conditions to include an offset to a target path y₀, a heading angle φ

₀, and initial curvature ρ

₀ at a time t equal to zero;

determine boundary conditions to include an offset y_f, a heading angle φ

_f, an initial curvature ρ

_f at t=t_f, where t_f and t₀ are times at the start and end of a segment;

solve the baseline b-spline function based on the initial conditions and the boundary conditions at each way point to provide second order parametric curve continuity;

determine path data based on results of the solved baseline b-spline function;

an autonomous driving system configured to, by a processor, receive the path data and to output control commands based on the path data; and

an actuator system configured to, by a processor, receive the control commands and to control the vehicle to traverse a path defined by the path data.

11. The vehicle of claim 10, wherein the actuator system includes at least one of:

a steering control actuator, a shifter control actuator, a throttle control actuator, and a brake control actuator.

12. The vehicle of claim 10, comprising an obstacle detection system configured to detect at least one object along the path and to determine at least one additional way point to avoid the obstacle, wherein the path finding engine is configured to determine and output adjusted path data using the at least one additional way point, and wherein the autonomous driving system is configured to control the vehicle to traverse an adjusted path defined by the adjusted path data.