IP Library › Granted Patent US 10,921,461
Granted Patent B2
US 10,921,461 · App. 15/425,109 · Granted Feb 16, 2021

Method and apparatus for determining unmanned vehicle positioning accuracy

Inventor: Chuting Tan (Beijing, CN)
Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
G01S19/47G01C21/28G01C21/3841G01S17/86G01S19/40G01S19/45G01S19/49G01S19/51
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 10,921,461
App. No.
15/425,109
Granted
Feb 16, 2021
Kind
B2
Abstract

Disclosed embodiments include a method and apparatus for determining an unmanned vehicle positioning accuracy. In some embodiments, the method comprises: acquiring positioning coordinate information obtained by real-time positioning based on sensing positioning data of the unmanned vehicle; determining real coordinate information of the unmanned vehicle based on GPS (Global Positioning System) data, IMU (Inertia Measurement Unit) data and laser point cloud data of the unmanned vehicle; matching the obtained positioning coordinate information with the determined real coordinate information, and determining the positioning accuracy of the unmanned vehicle based on a matching result. According to technical solutions of some embodiments, the positioning accuracy of the unmanned vehicle can be determined with a higher accuracy, and preparation is made for determining a travel route of the unmanned vehicle based on the positioning result.

Claims (68)

1. A method for determining an unmanned vehicle positioning accuracy, comprising:

acquiring positioning coordinate information obtained by real-time positioning based on sensing positioning data of the unmanned vehicle;

recognizing an obstacle included in laser point cloud data of the unmanned vehicle, and determining relative position information between the unmanned vehicle and the obstacle at each moment;

determining position information of the unmanned vehicle at each moment based on global positioning system (GPS) data of the unmanned vehicle, and determining movement information of the unmanned vehicle at each moment based on inertia measurement unit (IMU) data of the unmanned vehicle, wherein the determined movement information of the unmanned vehicle includes at least one of: acceleration information, direction information and speed information;

determining a movement error of the unmanned vehicle based on the position information and the determined movement information of the unmanned vehicle at each moment;

determining an observation error of the IMU based on the relative position information between the unmanned vehicle and the obstacle and the determined movement information of the unmanned vehicle at each moment;

determining the real coordinate information of the unmanned vehicle at each moment based on the movement error of the unmanned vehicle and the observation error of the IMU at each moment and the position information of the unmanned vehicle at each moment; and

matching the acquired positioning coordinate information with the determined real coordinate information, and determining the positioning accuracy of the unmanned vehicle based on a matching result.

2. The method according to claim 1 , wherein matching the acquired positioning coordinate information with the determined real coordinate information, and determining the positioning accuracy of the unmanned vehicle based on the matching result comprises:

matching the positioning coordinate information of the unmanned vehicle with the real coordinate information, and determining a positioning error of the unmanned vehicle; and

determining the positioning accuracy of the unmanned vehicle based on the positioning error of the unmanned vehicle.

3. The method according to claim 2 , wherein matching the positioning coordinate information of the unmanned vehicle with the real coordinate information, and determining the positioning error of the unmanned vehicle comprises:

determining, based on the positioning coordinate information and the real coordinate information, a linear error and a height error of the unmanned vehicle under a world coordinate system;

building a movement coordinate system of the unmanned vehicle at a plurality of time intervals based on the real coordinate information of the unmanned vehicle; and

based on the positioning coordinate information and the real coordination information, determining a transverse error and a longitudinal error of the unmanned vehicle under the built movement coordinate system.

4. The method according to claim 1 , wherein determining the movement error of the unmanned vehicle based on the position information and the movement information of the unmanned vehicle at each moment comprises:

determining an estimated position of the unmanned vehicle at each moment based on the movement information of the unmanned vehicle at each moment and the position information at a historical moment preceding each moment; and

determining the movement error of the unmanned vehicle based on the position information and estimated position of the unmanned vehicle at each moment.

5. The method according to claim 1 , wherein determining the observation error of the IMU based on the relative position information between the unmanned vehicle and the obstacle and the movement information at each moment comprises:

determining, based on the movement information of the unmanned vehicle at each moment and the relative position information of the unmanned vehicle and the obstacle at a historical moment preceding this moment, an estimated relative position information of the unmanned vehicle and the obstacle at this moment; and

determining the observation error of the IMU based on the relative position information of the unmanned vehicle and the obstacle at each moment and the estimated relative position information.

6. The method of claim 1 , wherein the determining the real coordinate information of the unmanned vehicle at each moment based on the movement error and the observation error at each moment and the position information of the unmanned vehicle at each moment comprises:

determining a minimum error based on the movement error and the observation error; and

determining the real coordinate information of the unmanned vehicle at each moment based on the minimum error and the position information of the unmanned vehicle at each moment.

7. An apparatus for determining an unmanned vehicle positioning accuracy, comprising:

at least one processor; and

a memory storing instructions, which when executed by the at least one processor, cause the at least one processor to perform operations comprising:

acquiring positioning coordinate information obtained by real-time positioning based on sensing positioning data of the unmanned vehicle;

recognizing an obstacle included in laser point cloud data of the unmanned vehicle, and determining relative position information between the unmanned vehicle and the obstacle at each moment;

determining position information of the unmanned vehicle at each moment based on global positioning system (GPS), data of the unmanned vehicle, and determining movement information of the unmanned vehicle at each moment based on inertia measurement unit (IMU) data of the unmanned vehicle, wherein the determined movement information of the unmanned vehicle includes at least one of: acceleration information, direction information and speed information;

determining a movement error of the unmanned vehicle based on the position information and the determined movement information of the unmanned vehicle at each moment;

determining an observation error of the IMU based on the relative position information between the unmanned vehicle and the obstacle and the determined movement information of the unmanned vehicle at each moment;

determining the real coordinate information of the unmanned vehicle at each moment based on the movement error of the unmanned vehicle and the observation error of the IMU at each moment and the position information of the unmanned vehicle at each moment; and

matching the acquired positioning coordinate information with the determined real coordinate information, and determining the positioning accuracy of the unmanned vehicle based on a matching result.

8. The apparatus according to claim 7 , wherein matching the acquired positioning coordinate information with the determined real coordinate information, and determining the positioning accuracy of the unmanned vehicle based on the matching result comprises:

matching the positioning coordinate information of the unmanned vehicle with the real coordinate information, and determining a positioning error of the unmanned vehicle; and

determining the positioning accuracy of the unmanned vehicle based on the positioning error of the unmanned vehicle.

9. The apparatus according to claim 8 , wherein matching the positioning coordinate information of the unmanned vehicle with the real coordinate information, and determining the positioning error of the unmanned vehicle comprises:

determining based on the positioning coordinate information and the real coordinate information, a linear error and a height error of the unmanned vehicle under a world coordinate system;

building a movement coordinate system of the unmanned vehicle at a plurality of time intervals based on the real coordinate information of the unmanned vehicle; and

determining, based on the positioning coordinate information and the real coordination information, a transverse error and a longitudinal error of the unmanned vehicle under the built movement coordinate system.

10. The apparatus according to claim 7 , wherein determining the movement error of the unmanned vehicle based on the position information and the movement information of the unmanned vehicle at each moment comprises:

determining an estimated position of the unmanned vehicle at each moment based on the movement information of the unmanned vehicle at each moment and the position information at a historical moment preceding each moment; and

determining the movement error of the unmanned vehicle based on the position information and estimated position of the unmanned vehicle at each moment.

11. The apparatus according to claim 7 , wherein determining the observation error of the IMU based on the relative position information between the unmanned vehicle and the obstacle and the movement information at each moment comprises:

determining, based on the movement information of the unmanned vehicle at each moment and the relative position information of the unmanned vehicle and the obstacle at a historical moment preceding this moment, an estimated relative position information of the unmanned vehicle and the obstacle at this moment; and

determining the observation error of the IMU based on the relative position information of the unmanned vehicle and the obstacle at each moment and the estimated relative position information.

12. A non-transitory computer storage medium storing a computer program, which when executed by one or more processors, cause the one or more processors to perform operations comprising:

acquiring positioning coordinate information obtained by real-time positioning based on sensing positioning data of an unmanned vehicle;

recognizing an obstacle included in laser point cloud data of the unmanned vehicle, and determining relative position information between the unmanned vehicle and the obstacle at each moment;

determining position information of the unmanned vehicle at each moment based on global positioning system (GPS) data of the unmanned vehicle, and determining movement information of the unmanned vehicle at each moment based on inertia measurement unit (IMU) data of the unmanned vehicle, wherein the determined movement information of the unmanned vehicle includes at least one of: acceleration information, direction information and speed information;

determining a movement error of the unmanned vehicle based on the position information and the determined movement information of the unmanned vehicle at each moment;

determining an observation error of the IMU based on the relative position information between the unmanned vehicle and the obstacle, and the determined movement information of the unmanned vehicle at each moment;

determining the real coordinate information of the unmanned vehicle at each moment based on the movement error of the unmanned vehicle and the observation error of the IMU at each moment and the position information of the unmanned vehicle at each moment; and

matching the acquired positioning coordinate information with the determined real coordinate information, and determining a positioning accuracy of the unmanned vehicle based on a matching result.

13. The non-transitory computer storage medium according to claim 12 , wherein matching the acquired positioning coordinate information with the determined real coordinate information, and determining the positioning accuracy of the unmanned vehicle based on the matching result comprises:

matching the positioning coordinate information of the unmanned vehicle with the real coordinate information, and determining a positioning error of the unmanned vehicle; and

determining the positioning accuracy of the unmanned vehicle based on the positioning error of the unmanned vehicle.

14. The non-transitory computer storage medium according to claim 13 , wherein matching the positioning coordinate information of the unmanned vehicle with the real coordinate information, and determining the positioning error of the unmanned vehicle comprises:

based on the positioning coordinate information and the real coordinate information, determining a linear error and a height error of the unmanned vehicle under a world coordinate system;

building a movement coordinate system of the unmanned vehicle at a plurality of time intervals based on the real coordinate information of the unmanned vehicle; and

based on the positioning coordinate information and the real coordination information, determining a transverse error and a longitudinal error of the unmanned vehicle under the built movement coordinate system.

15. The non-transitory computer storage medium according to claim 12 , wherein determining the movement error of the unmanned vehicle based on the position information and the movement information of the unmanned vehicle at each moment comprises:

determining an estimated position of the unmanned vehicle at each moment based on movement information of the unmanned vehicle at each moment and the position information at a historical moment preceding each moment; and

determining the movement error of the unmanned vehicle based on the position information and estimated position of the unmanned vehicle at each moment.

16. The non-transitory computer storage medium according to claim 12 , wherein determining the observation error of the IMU based on the relative position information between the unmanned vehicle and the obstacle and the movement information at each moment comprises:

based on the movement information of the unmanned vehicle at each moment and the relative position information of the unmanned vehicle and the obstacle at a historical moment preceding this moment, determining an estimated relative position information of the unmanned vehicle and the obstacle at this moment; and

determining the observation error of the IMU based on the relative position information of the unmanned vehicle and the obstacle at each moment and the estimated relative position information.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 21, 2017
From: TAN, CHUTING
To: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD
Reel/Frame 041324/0965 →
Priority Claims (1)
CN 2016 1 0551165 · Jul 13, 2016 · national
Continuity (1)
Related Publication 20180017682A1 · Jan 18, 2018