IP Library Granted Patent US 11,054,518
Granted Patent B2
US 11,054,518 · App. 16/026,328 · Granted Jul 6, 2021

Method and apparatus for determining obstacle speed

Inventors: Yujiang Hui (Beijing, CN); Jun Wang (Beijing, CN); Liang Wang (Beijing, CN)
Assignee: Baidu Online Network Technology (Beijing) Co., Ltd.
G01S13/931G01P3/50G01S7/003G01S13/588G01S13/865G01S17/58G01S17/89G01S17/931G06T7/73G06T2207/10044G06T2207/30261
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 11,054,518
App. No.
16/026,328
Granted
Jul 6, 2021
Kind
B2
Abstract

The disclosure discloses a method and apparatus for determining a speed of an obstacle. An embodiment of the method comprises: acquiring point cloud data and millimeter wave radar data of a driving environment of a vehicle; respectively processing the point cloud data and the millimeter wave radar data to determine speed information and location information of an obstacle in the driving environment; acquiring speed information of the vehicle; and integrating the speed information and the location information of the obstacle, and the speed information of the vehicle to determine the obstacle speed. The embodiment makes full use of point cloud data obtained by a laser radar and millimeter wave radar data obtained by a millimeter wave radar, and improves the accuracy in obstacle speed detection.

Claims (69)

1. A method for determining a speed of an obstacle, comprising:

acquiring point cloud data and millimeter wave radar data of a driving environment of a vehicle;

processing the point cloud data to determine first speed information and first location information of an obstacle in the driving environment, and processing the millimeter wave radar data to determine second speed information and second location information of the obstacle in the driving environment, wherein the second location information comprises a distance between the obstacle and the vehicle and an angle between a line connecting the obstacle to the vehicle and the vehicle driving direction, and the second speed information comprises a relative speed of the obstacle relative to the vehicle in a direction of the line;

acquiring speed information of the vehicle;

determining an absolute speed of the obstacle relative to the earth based on the vehicle speed information, the angle and the relative speed, wherein the absolute speed is based on a same coordinate system as the second location information;

converting the first speed information, the first location information, the absolute speed and the second location information into a world coordinate system based on a preset first conversion matrix and a preset second conversion matrix;

respectively matching the converted first speed information and the converted absolute speed with a preset obstacle information integration list; and

using matched first location information and the matched absolute speed for determining the target speed of the obstacle,

wherein the method is performed by at least one processor.

2. The method according to claim 1 , wherein respectively processing the point cloud data and the millimeter wave radar data comprises:

clustering and tracking the point cloud data to obtain the first speed information and the first location information of the obstacle, and a first obstacle identifier; and

analyzing the millimeter wave radar data to obtain the second speed information and the second location information of the obstacle, and a second obstacle identifier.

3. The method according to claim 1 , wherein the first speed information and the first location information correspond to the first obstacle identifier, the absolute speed and the second location information correspond to the second obstacle identifier, and the obstacle information integration list comprises a historical obstacle identifier, and historical speed information and historical location information corresponding to the historical obstacle identifier; and

wherein respectively matching the converted first speed information and the converted absolute speed with the preset obstacle information integration list comprises:

determining that the obstacle information integration list comprises the first obstacle identifier and the second obstacle identifier based on the historical obstacle identifier, the first obstacle identifier and the second obstacle identifier;

updating the historical speed information and the historical location information corresponding to the first obstacle identifier using the first speed information and the first location information in response to the obstacle information integration list comprising the first obstacle identifier; and

updating the historical speed information and the historical location information corresponding to the second obstacle identifier using the absolute speed and the second location information in response to the obstacle information integration list comprising the second obstacle identifier.

4. The method according to claim 3 , wherein respectively matching the converted first speed information and the converted absolute speed with the preset obstacle information integration list further comprises:

determining third location information based on the first location information, the first speed information and a time differential between a latest set of data in the point cloud data and a latest set of data in the millimeter wave radar data in response to the obstacle information integration list excluding the first obstacle identifier or the second obstacle identifier;

determining a matching degree between the third location information and the converted second location information; and

determining that the first obstacle identifier and the second obstacle identifier indicate a same obstacle, and updating the historical speed information and the historical location information corresponding to the first obstacle identifier based on the first speed information and the first location information, or updating the historical speed information and the historical location information corresponding to the second obstacle identifier based on the absolute speed and the second location information, in response to the matching degree being greater than or equal to a preset threshold.

5. The method according to claim 4 , wherein respectively matching the converted first speed information and the converted absolute speed with the preset obstacle information integration list further comprises:

adding the first location information, the first speed information and the first obstacle identifier or adding the absolute speed, the second location information and the second obstacle identifier to the obstacle information integration list, in response to the matching degree being lower than the preset threshold.

6. The method according to claim 1 , wherein using the matched first location information and the matched absolute speed for determining the target speed of the obstacle comprises:

determining a moving direction of the obstacle in the driving environment based on the first location information; and

integrating the moving direction and the absolute speed to determine the target speed of the obstacle.

7. The method according to claim 1 , wherein the obstacle information integration list comprises a moment of generating at least one of the historical location information or the historical speed information; and

the method further comprises:

determining that a time differential between the moment and the current moment is greater than a preset time length for each piece of at least one of the historical location information or the historical speed information in the obstacle information integration list; and

deleting the piece of the historical location information or the historical speed information in response to the time differential being greater than the preset time length.

8. An apparatus for determining a speed of an obstacle, comprising:

at least one processor; and

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

acquiring point cloud data and millimeter wave radar data of a driving environment of a vehicle;

processing the point cloud data to determine first speed information and first location information of an obstacle in the driving environment, and processing the millimeter wave radar data to determine second speed information and second location information of the obstacle in the driving environment, wherein the second location information comprises a distance between the obstacle and the vehicle and an angle between a line connecting the obstacle to the vehicle and the vehicle driving direction, and the second speed information comprises a relative speed of the obstacle relative to the vehicle in a direction of the line;

acquiring speed information of the vehicle;

determining an absolute speed of the obstacle relative to the earth based on the vehicle speed information, the angle and the relative speed, wherein the absolute speed is based on a same coordinate system as the second location information;

converting the first speed information, the first location information, the absolute speed and the second location information into a world coordinate system based on a preset first conversion matrix and a preset second conversion matrix;

respectively matching the converted first speed information and the converted absolute speed with a preset obstacle information integration list; and

using matched first location information and the matched absolute speed for determining the target speed of the obstacle.

9. The apparatus according to claim 8 , wherein respectively processing the point cloud data and the millimeter wave radar data comprises:

clustering and tracking the point cloud data to obtain the first speed information and the first location information of the obstacle, and a first obstacle identifier; and

analyzing the millimeter wave radar data to obtain the second speed information and the second location information of the obstacle, and a second obstacle identifier.

10. The apparatus according to claim 8 , wherein the first speed information and the first location information correspond to the first obstacle identifier, the absolute speed and the second location information correspond to the second obstacle identifier, and the obstacle information integration list comprises a historical obstacle identifier, and historical speed information and historical location information corresponding to the historical obstacle identifier; and

wherein respectively matching the converted first speed information and the converted absolute speed with the preset obstacle information integration list comprises:

determining that the obstacle information integration list comprises the first obstacle identifier and the second obstacle identifier based on the historical obstacle identifier, the first obstacle identifier and the second obstacle identifier;

updating the historical speed information and the historical location information corresponding to the first obstacle identifier using the first speed information and the first location information in response to the obstacle information integration list comprising the first obstacle identifier; and

updating the historical speed information and the historical location information corresponding to the second obstacle identifier using the absolute speed and the second location information in response to the obstacle information integration list comprising the second obstacle identifier.

11. The apparatus according to claim 10 , wherein respectively matching the converted first speed information and the converted absolute speed with the preset obstacle information integration list further comprises:

determining third location information based on the first location information, the first speed information and a time differential between a latest set of data in the point cloud data and a latest set of data in the millimeter wave radar data in response to the obstacle information integration list excluding the first obstacle identifier or the second obstacle identifier;

determining a matching degree between the third location information and the converted second location information; and

determining that the first obstacle identifier and the second obstacle identifier indicate a same obstacle, and updating the historical speed information and the historical location information corresponding to the first obstacle identifier based on the first speed information and the first location information, or updating the historical speed information and the historical location information corresponding to the second obstacle identifier based on the absolute speed and the second location information, in response to the matching degree being greater than or equal to a preset threshold.

12. The apparatus according to claim 11 , wherein respectively matching the converted first speed information and the converted absolute speed with the preset obstacle information integration list further comprises:

adding the first location information, the first speed information and the first obstacle identifier or adding the absolute speed, the second location information and the second obstacle identifier to the obstacle information integration list, in response to the matching degree being lower than the preset threshold.

13. The apparatus according to claim 8 , wherein using the matched first location information and the matched absolute speed for determining the target speed of the obstacle comprises:

determining a moving direction of the obstacle in the driving environment based on the first location information; and

integrating the moving direction and the absolute speed to determine the target speed of the obstacle.

14. The apparatus according to claim 8 , wherein the obstacle information integration list comprises a moment of generating at least one of the historical location information and the historical speed information; and

the operations further comprise:

determining that a time differential between the moment and the current moment is greater than a preset time length for each piece of at least one of the historical location information or the historical speed information in the obstacle information integration list; and

deleting the piece of the historical location information or the historical speed information in response to the time differential being greater than the preset time length.

15. A non-transitory computer medium, storing a computer program therein, wherein the program, when executed by a processor, causes the processor to perform operations, the operations comprising:

acquiring point cloud data and millimeter wave radar data of a driving environment of a vehicle;

processing the point cloud data to determine first speed information and first location information of an obstacle in the driving environment, and processing the millimeter wave radar data to determine second speed information and second location information of the obstacle in the driving environment, wherein the second location information comprises a distance between the obstacle and the vehicle and an angle, between a line connecting the obstacle to the vehicle and the vehicle driving direction, and the second speed information comprises a relative speed of the obstacle relative to the vehicle in a direction of the line;

acquiring speed information of the vehicle; and

determining an absolute speed of the obstacle relative to the earth based on the vehicle speed information, the angle and the relative speed, wherein the absolute speed is based on a same coordinate system as the second location information;

converting, the first speed information, the first location information, the absolute speed and the second location information into a world coordinate system based on a preset first conversion matrix and a preset second conversion matrix;

respectively matching the converted first speed information and the converted absolute speed with a preset obstacle information integration list; and

using matched first location information and the matched absolute speed for determining the target speed of the obstacle.

Assignments (3)
CORRECTIVE ASSIGNMENT TO CORRECT THE APPLICANT NAME PREVIOUSLY RECORDED AT REEL: 057933 FRAME: 0812. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Dec 28, 2021
From: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
To: APOLLO INTELLIGENT DRIVING TECHNOLOGY (BEIJING) CO., LTD.
Reel/Frame 058594/0836 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 13, 2021
From: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
To: APOLLO INTELLIGENT DRIVING (BEIJING) TECHNOLOGY CO., LTD.
Reel/Frame 057933/0812 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 3, 2018
From: HUI, YUJIANG; WANG, JUN; WANG, LIANG
To: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
Reel/Frame 046259/0700 →
Priority Claims (1)
CN 201710538431.7 · Jul 4, 2017 · national
Continuity (1)
Related Publication 20190011550A1 · Jan 10, 2019
Cited By (1)
US 12,386,071