Research on accelerated testing of cut-in condition of electric automated vehicles based on monte carlo simulation

Abstract

Electric automated vehicles are zero-emission, energy-saving, and environmentally friendly vehicles, and testing and verification is an important means to ensure their safety. Because of the scarcity of dangerous scenarios in natural driving roads, it is required to conduct accelerated tests and evaluations for electric automated vehicles. According to the scenario data of the natural road in cut-in conditions, we used the kernel density estimation method to calculate the probability distribution of the scenario parameters. Additionally, we used the Metropolis–Hastings algorithm to sample based on the probability distribution of the parameters, and the Euclidean distance was combined with the paired combination to accelerate the simulation test process. The critical scenarios were screened out by the safety indicator, and the feature distribution of the critical scenario parameters was analyzed based on the Euclidean distance clustering method, so as to design importance sampling parameters and carry out importance sampling. The study obtained the distribution characteristics of critical scenario parameters under cut-in conditions and found that the importance sampling method can accelerate the test under the condition of ensuring that the relative error is small, and the improved accelerated simulation method makes the overall calculation amount smaller.