Study on Comprehensive Evaluation of L3 Automated Vehicles

Automated vehicle testing and evaluation is an important guarantee for vehicle safety and reliability. The current L3 automated vehicle evaluation and evaluation procedures are not yet perfect. For the field test of L3 automated vehicles, we proposed to establish a comprehensive evaluation index system from the five dimensions of safety, intelligence, experience, energy consumption, and efficiency. A scientific method was designed to select and screen indicators in each dimension, and to preprocess behavior indicators based on effect size. The analytical hierarchy process and entropy method were used to determine the index weight, and the BP neural network and grey relation analysis were used to establish two comprehensive evaluation models for automated vehicles. Taking the comprehensive evaluation of the safety of automated vehicles in highway conditions as an example, two comprehensive evaluation models were established to verify the effectiveness of the models.