Auto-driving vehicle testing method, device and system

Abstract

The invention provides an auto-driving vehicle testing method, device and system. The method comprises: performing obstacle labeling on each of the acquired perceptual data to obtain a corresponding standard obstacle labeling result; acquiring obstacle labeling results generated by using an environment sensing system to perform obstacle labeling on the perceptual data; determining that the environmental sensing system is normal when each obstacle labeling result is identical to the corresponding standard obstacle labeling result; transmitting at least one virtual environment data to a vehiclecontrol system of an auto-driving vehicle after it is determined that the environmental sensing system is normal so as to allow the vehicle control system to control the auto-driving vehicle to travelon a test field without obstacles according to the virtual environment data; acquiring travelling condition data of the auto-driving vehicle traveling on the test field; and determining that the vehicle control system is normal when each traveling condition data matches the corresponding virtual environment data. The solution can reduce the cost of auto-driving vehicle testing.

Description

technical field [0001] The invention relates to the technical field of vehicle engineering, and in particular, to a test method, device and system for an automatic driving vehicle. Background technique [0002] An autonomous vehicle, also known as an unmanned vehicle, a computer-driven vehicle or a wheeled mobile robot, is an intelligent vehicle that realizes unmanned driving through a computer system. Autonomous driving vehicles usually include an environmental perception system and a vehicle control system. The environmental perception system is used to collect environmental data and mark roads, obstacles, etc. according to the collected environmental data, and the vehicle control system is used to collect environmental data. The markings carried out plan a reasonable path and control the driving of the vehicle. In order to ensure the safety of autonomous vehicles, it is necessary to test their perception systems and control systems during the development of autonomous ve...

AI Technical Summary

Problems solved by technology

[0004] In view of the current testing methods for the perception system and control system of autonomous vehicles, since the driving conditions of autonomous vehicles are determined by the perception system and the control system, any abnormality in the perception system and control system may cause the autonomous vehicle to fail. A collision occurs, causing damage to the self-driving vehicle, so testing is costly

Images