An Accelerated Testing Approach for Automated Vehicles with Background Traffic Described by Joint Distributions

TL;DR

This paper introduces a joint statistical modeling framework for accelerated testing of automated vehicles in naturalistic traffic, improving risk evaluation efficiency and reducing testing costs.

Contribution

It extends accelerated evaluation methods from independent models to joint distributions using Gaussian Mixture models and Importance Sampling, addressing high-dimensional challenges.

Findings

Effective risk evaluation in naturalistic traffic environments

Significant reduction in test costs for automated vehicle validation

Validation of the approach through simulation results

Abstract

This paper proposes a new framework based on joint statistical models for evaluating risks of automated vehicles in a naturalistic driving environment. The previous studies on the Accelerated Evaluation for automated vehicles are extended from multi-independent-variate models to joint statistics. The proposed toolkit includes exploration of the rare event (e.g. crash) sets and construction of accelerated distributions for Gaussian Mixture models using Importance Sampling techniques. Furthermore, the monotonic property is used to avoid the curse of dimensionality introduced by the joint distributions. Simulation results show that the procedure is effective and has a great potential to reduce the test cost for automated vehicles.