Distributionally Consistent Simulation of Naturalistic Driving Environment for Autonomous Vehicle Testing
This work is significant for autonomous vehicle developers and testers, providing a more accurate and unbiased method for evaluating AV safety performance by ensuring simulated driving environments statistically match real-world conditions.
This paper proposes a framework for simulating naturalistic driving environments (NDE) for autonomous vehicle (AV) testing, ensuring the simulated environment's statistical distributions are consistent with real-world data. It addresses the bias in AV safety evaluation caused by existing traffic models that lack distributional consistency, using large-scale naturalistic driving data to construct stochastic human driving behavior models and an optimization-based method to refine them.
Microscopic traffic simulation provides a controllable, repeatable, and efficient testing environment for autonomous vehicles (AVs). To evaluate AVs' safety performance unbiasedly, the probability distributions of environment statistics in the simulated naturalistic driving environment (NDE) need to be consistent with those from the real-world driving environment. However, although human driving behaviors have been extensively investigated in the transportation engineering field, most existing models were developed for traffic flow analysis without considering the distributional consistency of driving behaviors, which could cause significant evaluation biasedness for AV testing. To fill this research gap, a distributional consistent NDE modeling framework is proposed in this paper. Using large-scale naturalistic driving data, empirical distributions are obtained to construct the stochastic human driving behavior models under different conditions. To address the error accumulation problem during the simulation, an optimization-based method is further designed to refine the empirical behavior models. Specifically, the vehicle state evolution is modeled as a Markov chain and its stationary distribution is twisted to match the distribution from the real-world driving environment. The framework is evaluated in the case study of a multi-lane highway driving simulation, where the distributional accuracy of the generated NDE is validated and the safety performance of an AV model is effectively evaluated.