System and method for detection of vehicle lane departure

• US 10,352,704 B2
• Filed: 06/26/2018
• Issued: 07/16/2019
• Est. Priority Date: 01/17/2016
• Status: Expired due to Fees

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Motor Engineering & Manufacturing North America Incorporated (Toyota Motor Corporation)
• Inventors: Vladimerou, Vladimeros
• Primary Examiner(s): Ingram, Thomas
• Application Number:
  US16/018,686
• Publication Number:
  US 20180306583A1
• Time in Patent Office: 385 Days
• CPC Class Codes: B60W 2554/80 Spatial relation or speed relative to objects
• CPC Class Codes: B60W 2554/801 Lateral distance
• CPC Class Codes: B60W 2554/803 Relative lateral speed
• CPC Class Codes: B60W 30/0956 the prediction being responsive to traffic or environmental parameters
• CPC Class Codes: B60W 30/18163 Lane change; Overtaking manoeuvres
• CPC Class Codes: G01C 21/16 by integrating acceleration or speed, i.e. inertial navigation
• CPC Class Codes: G01C 21/1652 with ranging devices, e.g. LIDAR or RADAR
• CPC Class Codes: G01C 21/1656 with passive imaging devices, e.g. cameras

Abstract

A lane departure detection computing device for a roadside device is disclosed. The computing device is configured to execute instructions stored in a memory to: calculate a first path geometry relating to a first vehicle traveling in a first lane; calculate a second path geometry relating to a second vehicle traveling in a second lane different from the first lane; evaluate coextensive portions of the first path geometry and the second path geometry for parallelism; if the coextensive portions of the first path geometry and the second path geometry evaluated for parallelism are not parallel, determine that one of the first vehicle and the second vehicle is executing a lane departure; and operate a vehicle configured for autonomous operation responsive to the determination that one of the first vehicle and the second vehicle is executing a lane departure.

Claims

1. A computer-implemented method for operating a vehicle configured for autonomous operation, comprising steps of:

(1) in a lane departure detection computing device of a roadside device;

(a) calculating a first path geometry relating to a first vehicle traveling in a first lane;

(b) calculating a second path geometry relating to a second vehicle traveling in a second lane different from the first lane;

(c) evaluating coextensive portions of the first path geometry and the second path geometry for parallelism;

(d) if the coextensive portions of the first path geometry and the second path geometry evaluated for parallelism are parallel, repeating steps (a)-(d);

(e) if the coextensive portions of the first path geometry and the second path geometry evaluated for parallelism are not parallel, determining that one of the first vehicle and the second vehicle is executing a lane departure; and

(2) operating the vehicle configured for autonomous operation responsive to the determination that one of the first vehicle and the second vehicle is executing a lane departure.

2. The method of claim 1, wherein the step of evaluating coextensive portions of the first path geometry and the second path geometry for parallelism includes the steps of:

calculating a first minimum spacing of the second path geometry from the first path geometry at a first location along the first path geometry;

calculating a second minimum spacing of the second path geometry from the first path geometry at a second location along the first path geometry spaced apart from the first location;

determining a difference between the first minimum spacing and the second minimum spacing; and

if the difference is equal to or greater than a predetermined value, determining that the coextensive portions of the first path geometry and the second path geometry residing between the first minimum spacing and the second minimum spacing are not parallel.

3. The method of claim 1 wherein the step of calculating the first path geometry comprises the step of measuring position coordinates of the first vehicle at a rate such that a maximum distance between sensor measurement locations is a predetermined value.

4. The method of claim 1 wherein the step of evaluating coextensive portions of the first path geometry and the second path geometry for parallelism comprises the step of evaluating coextensive portions of the first path geometry and the second path geometry when the first path geometry and the second path geometry are spaced apart at least a minimum predetermined distance.

5. The method of claim 1 wherein the step of evaluating coextensive portions of the first path geometry and the second path geometry for parallelism comprises the step of evaluating coextensive portions of the first path geometry and the second path geometry for parallelism over at least a predetermined length of the first path geometry and the second path geometry.

6. The method of claim 1 further comprising the step of, prior to the step of calculating the first path geometry relating to the first vehicle, receiving information usable for calculating the first path geometry from the first vehicle.

7. The method of claim 6 further comprising step of, prior to the step of calculating the second path geometry relating to the second vehicle, receiving information usable for calculating the second path geometry from the second vehicle.

8. The method of claim 6 wherein the roadside device includes one or more sensors configured for acquiring information usable for calculating the second path geometry, and wherein the method further comprises the step of, prior to the step of calculating the second path geometry relating to the second vehicle, acquiring vehicle information usable for calculating the second path geometry by the one or more sensors of the roadside device usable for calculating the second path geometry.

9. The method of claim 1 wherein the roadside device includes one or more sensors configured for acquiring information usable for calculating the first path geometry, and wherein the method further comprises the step of, prior to the step of calculating the first path geometry relating to the first vehicle, acquiring vehicle information usable for calculating the first path geometry by the one or more sensors of the roadside device configured for acquiring information usable for calculating the first path geometry.

10. The method of claim 9 further comprising the step of, prior to the step of calculating the second path geometry relating to the second vehicle, receiving information usable for calculating the second path geometry from the second vehicle.

11. The method of claim 9 wherein the roadside device includes one or more sensors configured for acquiring information usable for calculating the second path geometry, and wherein the method further comprises the step of, prior to the step of calculating the second path geometry relating to the second vehicle, acquiring vehicle information usable for calculating the second path geometry by the one or more sensors of the roadside device configured for acquiring information usable for calculating the second path geometry.

12. The method of claim 1 further comprising the step of, prior to at least one of the steps of calculating the first path geometry relating to the first vehicle traveling in the first lane and calculating the second path geometry relating to the second vehicle traveling in the second lane, receiving, from a GPS system, information usable for calculating the at least one of the first path geometry relating to the first vehicle traveling in the first lane and the second path geometry relating to the second vehicle traveling in the second lane.

13. The method of claim 1 wherein the vehicle configured for autonomous operation is a third vehicle separate from the first vehicle and the second vehicle.

14. The method of claim 1 wherein the vehicle configured for autonomous operation is one of the first vehicle and the second vehicle.

15. The method of claim 1 wherein the vehicle configured for autonomous operation includes a vehicle computing device configured for operating the vehicle configured for autonomous operation responsive to a determination by the lane departure detection computing device that one of the first vehicle and the second vehicle is executing a lane departure, wherein the method further comprises transmitting, to the vehicle configured for autonomous operation, information including the determination that one of the first vehicle and the second vehicle is executing a lane departure, and wherein the step of operating the vehicle configured for autonomous operation comprises operating the vehicle configured for autonomous operation by the vehicle computing device.

16. The method of claim 1 wherein the step of operating the vehicle configured for autonomous operation comprises operating the vehicle by the lane departure detection computing device of the roadside device.

17. The method of claim 1 further comprising the step of, after step (1)(c) and before step (1)(d):

if the coextensive portions of the first path geometry and the second path geometry evaluated for parallelism are parallel, determining at least a portion of a road geometry from the coextensive portions of the first path geometry and the second path geometry evaluated for parallelism.

18. A non-transitory computer readable medium with computer executable instructions stored thereon executed by a processor to perform a method of operating a vehicle configured for autonomous operation, the method comprising:

(a) calculating a first path geometry relating to a first vehicle traveling in a first lane;

(b) calculating a second path geometry relating to a second vehicle traveling in a second lane different from the first lane;

(c) evaluating coextensive portions of the first path geometry and the second path geometry for parallelism;

(d) if the coextensive portions of the first path geometry and the second path geometry evaluated for parallelism are parallel, repeating steps (a)-(d);

(e) if the coextensive portions of the first path geometry and the second path geometry evaluated for parallelism are not parallel, determining that one of the first vehicle and the second vehicle is executing a lane departure; and

(f) operating the vehicle configured for autonomous operation responsive to the determination that one of the first vehicle and the second vehicle is executing a lane departure.

19. A lane departure detection computing device for a roadside device, the computing device comprising one or more processors for controlling operation of the computing device, and a memory for storing data and program instructions usable by the one or more processors, wherein the one or more processors are configured to execute instructions stored in the memory to:

calculate a first path geometry relating to a first vehicle traveling in a first lane;

calculate a second path geometry relating to a second vehicle traveling in a second lane different from the first lane;

evaluate coextensive portions of the first path geometry and the second path geometry for parallelism;

if the coextensive portions of the first path geometry and the second path geometry evaluated for parallelism are not parallel, determine that one of the first vehicle and the second vehicle is executing a lane departure; and

operate a vehicle configured for autonomous operation responsive to the determination that one of the first vehicle and the second vehicle is executing a lane departure.