Test track dynamic planning method and system for automatic driving test vehicle

Abstract

The invention provides a test track dynamic planning method and system for an automatic driving test vehicle, and the method comprises the steps: carrying out the information extraction of an obtainedhigh-precision map of a test field, dividing the map into different types of road segments, and building a test road segment library; based on the information of the test road section library, establishing a basic test library according to test rules, and establishing a danger library and an extreme library according to danger and accident videos screened out in traffic monitoring; and determining a test item by the test vehicle test unit according to the test level, generating a global test path, driving the test vehicle test path according to the global test path, and performing local pathadjustment through a loaded sensing module. According to the technical scheme, through track splicing, the test process is coherent and smooth, the test is efficient, the test result is more systematic and accurate, and the labor and time cost is reduced. Different tested vehicles are tested in a graded manner, and the obtained test data is more valuable. And the test process does not need workersto directly intervene in the test site, so that the test safety is higher.

Description

technical field [0001] The present disclosure relates to the technical field of automatic driving test, in particular to a method and system for dynamic planning of a test track of an automatic driving test vehicle. Background technique [0002] Autonomous vehicles are developing rapidly, and autonomous driving technology is an inevitable trend in the development of vehicle engineering. Autonomous driving technology conforms to the concept of environmental friendliness, complies with the requirements of high efficiency and low cost of social development, and is more convenient for people's work and life. Autonomous driving technology includes four modules: positioning, perception, decision-making and control. The positioning module obtains the precise position of the vehicle on a specific map, the perception module dynamically collects surrounding environment information data, and the decision-making module processes the collected positioning and perception information. To ...

AI Technical Summary

Problems solved by technology

The current autonomous driving test is not perfect, the test environment is single, lacks real road condition simulation, and the problems encountered in mixed driving with human-driven vehicles cannot be reproduced well; the test road is long, the test items are few, the time is long, and the efficiency is low; there are many personnel interventions , high risk factor; there is no systematic and coherent one-time testing process

Images