Abstract
The test of intelligent driving systems is faced with the challenges of efficiency because real traffic scenarios are infinite, uncontrollable and difficult to be precisely defined. Based on the complexity index of scenario designed to measure the test effect indirectly, a new combinational generation algorithm of test cases is proposed to make a balance between multiple objects including coverage, case number and test effect. Then a joint simulation platform based on Matlab, PreScan and Carsim is set up to realize the automatic construction of 3D test environment from the generated scenarios, conduction of test and evaluation of test results seamlessly. The proposed strategy has been validated by application to a traffic jam pilot system and the results show that it is beneficial to improve the complexity of scenario and the designed scenarios can find system faults effectively, and the required time to conduct tests is reduced obviously by automation.
Funding Information
  • Natural Science Foundation of Chongqing Municipality (cstc2019jcyj-zdxmX0018)
  • Sichuan Science and Technology Program (2020YFSY0070)

This publication has 32 references indexed in Scilit: