Automatic driving simulation test method and device for scene library

Abstract

The embodiment of the invention discloses an automatic driving simulation test method and device for a scene library, and the method comprises the steps: determining a traffic test scene based on a target scene template and a modification instruction corresponding to the target scene template, wherein the modification instruction is an instruction for modifying a scene element corresponding to thetarget scene template; triggering a test process corresponding to a preset test event if it is detected that the position relationship with the tested vehicle exists in the scene objects of the traffic test scene and the scene object of the test triggering condition corresponding to the preset test event is reached; and monitoring the behavior state of the tested vehicle in the test process corresponding to the preset test event, and obtaining the behavior state parameter corresponding to the behavior state of the tested vehicle, so as to determine the test result of the tested algorithm of the tested vehicle through the behavior state parameter, thereby achieving the automatic and comprehensive construction of the automatic driving scene. The test efficiency of the automatic driving algorithm is improved while the automatic driving algorithm is tested more comprehensively.

Description

technical field [0001] The invention relates to the technical field of testing, in particular to a method and device for an automatic driving simulation test of a scene library. Background technique [0002] At present, driving simulation technology is generally used to test the automatic driving algorithm set for the automatic driving vehicle. In the process of using driving simulation technology to test the autonomous driving algorithm, it is generally necessary to use manually set scene data or use scene data collected for actual driving scenes to simulate the driving scene of the autonomous driving vehicle, and then conduct simulation tests. [0003] However, the number of driving scenarios constructed by using the above process is relatively limited, and because different test events correspond to different driving scenarios, the workload of configuring the driving scenarios is heavy and cumbersome, and the efficiency of manual setting is low. However, using scene data...

AI Technical Summary

Problems solved by technology

[0003] However, the number of driving scenarios constructed by using the above process is relatively limited, and because different test events correspond to different driving scenarios, the workload in the configuration process of driving scenarios is heavy and cumbersome, and the efficiency of manual setting is low

However, using scene data collected for actual driving scenes to construct driving scenes, the types of driving scenes constructed are limited and cannot reflect the more comprehensive performance of autonomous driving algorithms.

Images