IP Library Granted Patent US 11,400,928
Granted Patent B2
US 11,400,928 · App. 15/991,399 · Granted Aug 2, 2022

Driverless vehicle testing method and apparatus, device and storage medium

Inventor: Taiqun Hu (Beijing, CN)
Assignee: APOLLO INTELLIGENT DRIVING TECHNOLOGY (BEIJING) CO., LTD.
B60W30/0956G07C5/0841B60W2050/0031B60W2050/0088
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 11,400,928
App. No.
15/991,399
Granted
Aug 2, 2022
Kind
B2
Abstract

The present disclosure provides a driverless vehicle testing method and apparatus, a device and a storage medium, wherein the method comprises: obtaining traffic scenario data of a traffic accident happening on a real road; constructing sensor data needed by travel of the driverless vehicle according to the traffic scenario data; performing simulation of a testing scenario according to the traffic scenario data; performing test for the driverless vehicle's capability of dealing with the traffic accident according to the sensor data and testing scenario. The solution of the present disclosure may be applied to improve accuracy of testing results.

Claims (48)

1. A method comprising:

obtaining traffic scenario data of a traffic accident on a real road involving a plurality of vehicle roles, wherein the traffic scenario data is obtained in a predetermined time period until the moment of the traffic accident;

constructing, on a simulation platform, a testing scenario according to the traffic scenario data, wherein the testing scenario includes positions, travel speed, and directions of the plurality of vehicle roles which change over time;

constructing, according to the traffic scenario data, sensor data needed to simulate driving of an autonomous vehicle which is to be set as replacing a vehicle role of the plurality of vehicle roles for the testing scenario on the simulation platform according to the traffic scenario data; and

performing, on the simulation platform, a simulation test for the autonomous vehicle in the testing scenario by replacing the vehicle role in the traffic accident with the autonomous vehicle which performs decision-making control operations according to the sensor data over time, so as to avoid the traffic accident.

2. The method according to claim 1 , wherein the obtaining the traffic scenario data of the traffic accident on the real road comprises:

obtaining vehicle data collected by vehicles in the traffic accident, and

obtaining monitoring data of a traffic monitoring platform.

3. The method according to claim 1 , wherein the constructing the sensor data needed to simulate the driving of the autonomous vehicle for the testing scenario according to the traffic scenario data comprises:

setting the autonomous vehicle as playing different roles in the traffic accident, and

constructing the sensor data needed to simulate the driving of the autonomous vehicle with respect to each role; and

the performing the simulation test for the autonomous vehicle's capability of dealing with the traffic accident according to the sensor data and the testing scenario comprises:

with respect to each role, using the autonomous vehicle to replace a vehicle playing in the role, and

testing the autonomous vehicle's capability of dealing with the traffic accident according to the sensor data and testing scenario corresponding to the role.

4. The method according to claim 1 , wherein after testing the autonomous vehicle's capability of dealing with the traffic accident, the method further comprises:

if the simulation test passes, providing the sensor data to an on-the-spot testing system so that the on-the-spot testing system tests the autonomous vehicle's capability of dealing with the traffic accident in a real testing scenario according to the sensor data.

5. A computer device, comprising a memory, a processor, and a computer program which is stored on the memory and runs on the processor, wherein the processor, upon executing the program, implements the following operation:

obtaining traffic scenario data of a traffic accident on a real road involving a plurality of vehicle roles, wherein the traffic scenario data is obtained in a predetermined time period until the moment of the traffic accident;

constructing, on a simulation platform, a testing scenario according to the traffic scenario data, wherein the testing scenario includes positions, travel speed, and directions of the plurality of vehicle roles which change over time;

constructing, according to the traffic scenario data, sensor data needed to simulate driving of an autonomous vehicle which is to be set as replacing a vehicle role of the plurality of vehicle roles for the testing scenario on the simulation platform; and

performing, on the simulation platform, a simulation test for the autonomous vehicle in the testing scenario by replacing the vehicle role in the traffic accident with the autonomous vehicle which performs decision-making control operations according to the sensor data over time, so as to avoid the traffic accident.

6. The computer device according to claim 5 , wherein the obtaining the traffic scenario data of the traffic accident on the real road comprises:

obtaining vehicle data collected by vehicles in the traffic accident, and

obtaining monitoring data of a traffic monitoring platform.

7. The computer device according to claim 5 , wherein the constructing the sensor data needed to simulate the driving of the autonomous vehicle for the testing scenario according to the traffic scenario data comprises:

setting the autonomous vehicle as playing different roles in the traffic accident, and

constructing the sensor data needed to simulate the driving of the autonomous vehicle with respect to each role; and

the performing the simulation test for the autonomous vehicle's capability of dealing with the traffic accident according to the sensor data and the testing scenario comprises:

with respect to each role, using the autonomous vehicle to replace a vehicle playing in the role, and

testing the autonomous vehicle's capability of dealing with the traffic accident according to the sensor data and testing scenario corresponding to the role.

8. The computer device according to claim 5 , wherein after testing the autonomous vehicle's capability of dealing with the traffic accident, the method further comprises:

if the simulation test passes, providing the sensor data to an on-the-spot testing system so that the on-the-spot testing system tests the autonomous vehicle's capability of dealing with the traffic accident in a real testing scenario according to the sensor data.

9. A non-transitory computer-readable storage medium on which a computer program is stored, wherein the computer program, when executed by the processor, implements the following operation:

obtaining traffic scenario data of a traffic accident on a real road involving a plurality of vehicle roles, wherein the traffic scenario data is obtained in a predetermined time period until the moment of the traffic accident;

constructing, on a simulation platform, a testing scenario according to the traffic scenario data, wherein the testing scenario includes positions, travel speed and directions of the plurality of vehicle roles which change over time;

constructing, according to the traffic scenario data, sensor data needed to simulate driving of an autonomous vehicle which is to be set as replacing a vehicle role of the plurality of vehicle roles for the testing scenario on the simulation platform; and

performing, on the simulation platform, a simulation test for the autonomous vehicle in the testing scenario by replacing the vehicle role in the traffic accident with the autonomous vehicle which performs decision-making control operations according to the sensor data.

10. The non-transitory computer-readable storage medium according to claim 9 , wherein the obtaining the traffic scenario data of the traffic accident on the real road comprises:

obtaining vehicle data collected by vehicles in the traffic accident, and

obtaining monitoring data of a traffic monitoring platform.

11. The non-transitory computer-readable storage medium according to claim 9 , wherein the constructing the sensor data needed to simulate the driving of the autonomous vehicle for the testing scenario according to the traffic scenario data comprises:

setting the autonomous vehicle as playing different roles in the traffic accident, and

constructing the sensor data needed to simulate the driving of the autonomous vehicle with respect to each role; and

the performing the simulation test for the autonomous vehicle's capability of dealing with the traffic accident according to the sensor data and the testing scenario comprises:

with respect to each role, using the autonomous vehicle to replace a vehicle playing in the role, and

testing the autonomous vehicle's capability of dealing with the traffic accident according to the sensor data and testing scenario corresponding to the role.

12. The non-transitory computer-readable storage medium according to claim 9 , wherein after testing the autonomous vehicle's capability of dealing with the traffic accident, the method further comprises:

if the simulation test passes, providing the sensor data to an on-the-spot testing system so that the on-the-spot testing system tests the autonomous vehicle's capability of dealing with the traffic accident in a real testing scenario according to the sensor data.

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 Jun 4, 2018
From: HU, TAIQUN
To: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
Reel/Frame 045978/0094 →
Priority Claims (1)
CN 201710431818.2 · Jun 9, 2017 · national
Continuity (1)
Related Publication 20180354512A1 · Dec 13, 2018
Cited By (1)
US 12,454,272