IP Library Granted Patent US 10,353,393
Granted Patent B2
US 10,353,393 · App. 15/394,563 · Granted Jul 16, 2019

Method and system for improving stability of autonomous driving vehicles

Inventor: Fan Zhu (Sunnyvale, CA)
Assignee: BAIDU USA LLC
G05D1/0212B60W30/095B62D6/001B62D6/002G08G1/0125G08G1/056B60W2530/00B60W2530/20B60W2550/10B60W2550/14B60W2550/146B60W2550/148G01S19/42G05D1/0236G05D1/0242G05D1/0257
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,353,393
App. No.
15/394,563
Granted
Jul 16, 2019
Kind
B2
Abstract

In one embodiment, perception information is received, the perception information perceiving a driving scenario of an autonomous driving vehicle (ADV). A path from a first location to a second location is planned and determined based on a driving scenario obtained based on the perception information. A tolerance area along the determined path is determined based on the perception information. The autonomous driving vehicle is driven within the tolerance area according to the path. No lateral error is committed if the autonomous driving vehicle is moving within the tolerance area. A lateral error is considered committed only if the autonomous driving vehicle is moving outside of the tolerance area.

Claims (47)

1. A computer-implemented method for operating an autonomous driving vehicle, the method comprising:

receiving perception information, the perception information perceiving a driving scenario of the autonomous driving vehicle (ADV);

planning a path from a first location to a second location based on a driving scenario obtained based on the perception information;

determining a tolerance area along the determined path based on the perception information, the tolerance area comprising a left curve and a right curve enclosing the determined path; and

driving the ADV within the tolerance area according to the determined path, wherein a lateral error is committed if the ADV moves outside the tolerance area;

performing a lateral error correction of the ADV only in response to the ADV moving outside the tolerance area, thereby minimizing a total number of lateral error corrections while driving the ADV within the tolerance area.

2. The method of claim 1 , wherein determining a tolerance area comprises determining the left curve and the right curve enclosing the determined path sandwiched therein, and wherein the autonomous driving vehicle is driven within the left curve and the right curve.

3. The method of claim 2 , wherein driving the autonomous driving vehicle comprises:

detecting that the autonomous driving vehicle is moving outside of the left curve or the right curve; and

performing a lateral error correction, in response to detecting that the autonomous driving vehicle is moving outside the left curve or the right curve.

4. The method of claim 3 , wherein a size and shape of the tolerance area is dynamically determined for the path based on a perception of the driving environment at a point in time.

5. The method of claim 1 , wherein the tolerance area is determined based on a road width of a road on which the autonomous vehicle is moving.

6. The method of claim 1 , wherein the tolerance area is determined based on a vehicle width of the autonomous driving vehicle.

7. The method of claim 1 , wherein the tolerance area is determined based on a curvature of a road on which the autonomous driving vehicle is moving.

8. The method of claim 1 , wherein the tolerance area is determined based on an opposing traffic of a road on which the autonomous driving vehicle is moving.

9. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:

receiving perception information, the perception information perceiving a driving scenario of an autonomous driving vehicle (ADV);

planning a path from a first location to a second location based on a driving scenario obtained based on the perception information;

determining a tolerance area along the determined path based on the perception information, the tolerance area comprising a left curve and a right curve enclosing the determined path; and

driving the ADV within the tolerance area according to the determined path, wherein a lateral error is committed if the moves outside the tolerance area;

performing a lateral error correction of the ADV only in response to the ADV moving outside the tolerance area, thereby minimizing a total number of lateral error corrections while driving the ADV within the tolerance area.

10. The machine-readable medium of claim 9 , wherein determining a tolerance area comprises determining the left curve and the right curve enclosing the determined path sandwiched therein, and wherein the autonomous driving vehicle is driven within the left curve and the right curve.

11. The machine-readable medium of claim 10 , wherein driving the autonomous driving vehicle comprises:

detecting that the autonomous driving vehicle is moving outside of the left curve or the right curve; and

performing a lateral error correction, in response to detecting that the autonomous driving vehicle is moving outside the left curve or the right curve.

12. The machine-readable medium of claim 11 , wherein a size and shape of the tolerance area is dynamically determined for the path based on a perception of the driving environment at a point in time.

13. The machine-readable medium of claim 9 , wherein the tolerance area is determined based on a road width of a road on which the autonomous vehicle is moving.

14. The machine-readable medium of claim 9 , wherein the tolerance area is determined based on a vehicle width of the autonomous driving vehicle.

15. The machine-readable medium of claim 9 , wherein the tolerance area is determined based on a curvature of a road on which the autonomous driving vehicle is moving.

16. The machine-readable medium of claim 9 , wherein the tolerance area is determined based on an opposing traffic of a road on which the autonomous driving vehicle is moving.

17. A data processing system, comprising:

a processor; and

a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including

receiving perception information, the perception information perceiving a driving scenario of an autonomous driving vehicle (ADV),

planning a path from a first location to a second location based on a driving scenario obtained based on the perception information,

determining a tolerance area along the determined path based on the perception information, the tolerance area comprising a left curve and a right curve enclosing the determined path, and

driving the ADV within the tolerance area according to the determined path, wherein a lateral error is committed if the ADV moves outside the tolerance area;

performing a lateral error correction of the ADV only in response to the ADV moving outside the tolerance area, thereby minimizing a total number of lateral error corrections while drive the ADV within the tolerance area.

18. The system of claim 17 , wherein determining a tolerance area comprises determining the left curve and the right curve enclosing the determined path sandwiched therein, and wherein the autonomous driving vehicle is driven within the left curve and the right curve.

19. The system of claim 18 , wherein driving the autonomous driving vehicle comprises:

detecting that the autonomous driving vehicle is moving outside of the left curve or the right curve; and

performing a lateral error correction, in response to detecting that the autonomous driving vehicle is moving outside the left curve or the right curve.

20. The system of claim 19 , wherein a size and shape of the tolerance area is dynamically determined for the path based on a perception of the driving environment at a point in time.

21. The system of claim 17 , wherein the tolerance area is determined based on a road width of a road on which the autonomous vehicle is moving.

22. The system of claim 17 , wherein the tolerance area is determined based on a vehicle width of the autonomous driving vehicle.

23. The system of claim 17 , wherein the tolerance area is determined based on a curvature of a road on which the autonomous driving vehicle is moving.

24. The system of claim 17 , wherein the tolerance area is determined based on an opposing traffic of a road on which the autonomous driving vehicle is moving.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 29, 2016
From: ZHU, FAN
To: BAIDU USA LLC
Reel/Frame 040806/0992 →
Continuity (1)
Related Publication 20180188734A1 · Jul 5, 2018
Cited By (1)
US 12,384,410