Accelerated Training for Connected and Automated Vehicles Based on Adaptive Evaluation Method

Abstract

How to generate testing scenario libraries for connected and automated vehicles (CAVs) is a major challenge faced by the industry.In previous studies, to evaluate maneuver challenge of a scenario, surrogate models (SMs) are often used without explicit knowledgeof the CAV under test. However, performance dissimilarities between the SM and the CAV under test usually exist, and it can leadto the generation of suboptimal scenario libraries. In this project, an adaptive testing scenario library generation (ATSLG) methodis proposed to solve this problem. A customized testing scenario library for a specific CAV model is generated through an adaptiveprocess. To compensate for the performance dissimilarities and leverage each test of the CAV, Bayesian optimization techniquesare applied with classification-based Gaussian Process Regression and a newly designed acquisition function. Comparing with a pre-determined library, a CAV can be tested and evaluated in a more efficient manner with the customized library. To validate theproposed method, a cut-in case study is investigated and the results demonstrate that the proposed method can further accelerate theevaluation process by a few orders of magnitude.