Research on Automatic Generation Method of Scenario Based on Panosim

Abstract

With the development of science and technology, L3 intelligent vehicles are gradually entering the mass production phase. Traditional testing tools and methods can hardly meet the requirements for multiple dimensions, high standard and big data of self-driving vehicles. The scenario-based simulation test method has great technical advantages in terms of test efficiency, verification cost and versatility, and is an important means for automatic driving test verification. However, it has shortcomings such as long scenario construction period and large repeatability. This paper is compiled based on secondary development of the automatic driving simulation software Panosim and presenting the automatic inputting of scenario and rapid adjustment of parameters through the digital twinning technology. In addition, the natural driving scenario database of China Automotive Technology and Research Center is used for verification. The results show that this method can improve the efficiency and accuracy of scenario construction, and greatly shorten the cycle of simulation test.