Method for designing test scene of automatic driving automobile test field

Abstract

The invention relates to the technical field of automatic driving automobile testing, in particular to an automatic driving automobile test field test scene design method, which comprises a V2V technology, a V2I technology, a V2P technology and a V2N technology, and is characterized in that the scenes applied by the V2V technology comprise a straight running application scene, a steering application scene, an intersection auxiliary application scene and a lane changing application scene; the application scenes of the V2I technology comprise weather early warning, lane changing speed limiting early warning, red light early warning, human-shaped crosswalk pedestrian early warning and speed limiting construction area early warning. According to the method for designing the test scene of the automatic driving automobile test field, test cases are obtained through virtual simulation modeling, the test cases are derived from functional scenes and logic scenes, scene parameter distribution has good continuity, scene element permutation and combination have diversity, and a standard driving scene data interface is developed by means of a virtual simulation tool chain. Batch import and modeling of the test cases can be achieved, a high-performance simulation server is used for realizing batch simulation testing, and time cost and labor cost are saved.

Description

technical field [0001] The invention relates to the technical field of self-driving car testing, in particular to a method for designing a test scene of a test field for self-driving cars. Background technique [0002] The speed of research and development of self-driving cars in my country is developing very fast. Many companies have begun to test self-driving cars on the road. However, the current road test has a series of limitations such as high test cost, long test cycle, and many test accidents. Atypical, unable to cover all complex special scenarios. [0003] my country's autonomous driving test has made great progress, but there are still many problems. The scene is a very important part of the automatic driving test system, but the current test scene does not have the characteristics of the Chinese driving scene, and cannot fully comply with the standards, regulations, and artificial experience data at the same time. , China’s traffic accident data, natural driving d...

AI Technical Summary

Problems solved by technology

[0002] The speed of research and development of self-driving cars in my country is developing very fast. Many companies have begun to test self-driving cars on the road. However, the current road test has a series of limitations such as high test cost, long test cycle, and many test accidents. Atypical, unable to cover all complex special scenarios

[0003] my country's autonomous driving test has made great progress, but there are still many problems. The scene is a very important part of the automatic driving test system, but the current test scene does not have the characteristics of the Chinese driving scene, and cannot fully comply with the standards, regulations, and artificial experience data at the same time. , China’s traffic accident data, natural driving data, etc., it is necessary to speed up the construction of scientific and efficient autonomous driving capability test scenarios and build an evaluation environment for autonomous driving capability testing. It is urgently needed in the field of automotive testing technology