Method for evaluating driving ability of automatic driving automobile in hybrid driving environment

Abstract

The invention discloses a method for evaluating the driving ability of an automatic driving automobile in a hybrid driving environment, and the method comprises the steps: constructing a scene modeling method suitable for the testing of the automatic driving automobile according to a scene generation process of a driving simulator, and controlling a background automobile in a scene through the control of the hardware of the driving simulator by a human driver, wherein the driving simulator software enables the external program to control the tested automatic driving automobile in the scene through the API, thereby achieving the testing of the automatic driving automobile in the mixed driving environment; and finally, establishing an evaluation index and an evaluation standard, and visually displaying an evaluation result in a score mode. Compared with a virtual simulation test, the method has the advantages that man-machine interaction can be realized, and the randomness of a human driver is considered. Compared with a field real vehicle test, the method has the advantages of rich and changeable scenes, high repeatability, low cost and high efficiency.

Description

technical field [0001] The invention belongs to the field of self-driving car testing, and relates to a method for evaluating the driving ability of a self-driving car in a mixed driving environment based on a driving simulator. Background technique [0002] Due to the advantages of reducing the accident rate and improving road traffic capacity, self-driving cars have shown increasing advantages in solving many practical problems of traditional cars. However, due to the complexity of the traffic system, self-driving cars are prone to encounter some safety issues when driving in a mixed driving environment. So far, self-driving cars have caused many safety accidents, and their stability and reliability are still difficult to guarantee. Therefore, in order to ensure that autonomous vehicles can operate safely, reliably, and efficiently in various scenarios such as complex traffic environments, random and changeable weather, and diverse driving tasks, it is necessary to compre...

AI Technical Summary

Problems solved by technology

The simulation test cannot fully simulate the randomness of human drivers, and the restoration of the mixed driving environment is limited. The real vehicle test can provide a more realistic scene for human-computer interaction testing, but the test cost is high, the repeatability is low, and it can be covered limited number of scenes

Images