Accelerated Evaluation of Automated Vehicles Using Piecewise Mixture Models

Abstract

The process to certify highly Automated Vehicles has not yet been defined by any country in the world. Currently, companies test Automated Vehicles on public roads, which is time-consuming and inefficient. We proposed the Accelerated Evaluation concept, which uses a modified statistics of the surrounding vehicles and the Importance Sampling theory to reduce the evaluation time by several orders of magnitude, while ensuring the evaluation results are statistically accurate. In this paper, we further improve the accelerated evaluation concept by using Piecewise Mixture Distribution models, instead of Single Parametric Distribution models. We developed and applied this idea to forward collision control system reacting to vehicles making cut-in lane changes. The behavior of the cut-in vehicles was modeled based on more than 403,581 lane changes collected by the University of Michigan Safety Pilot Model Deployment Program. Simulation results confirm that the accuracy and efficiency of the Piecewise Mixture Distribution method outperformed single parametric distribution methods in accuracy and efficiency, and accelerated the evaluation process by almost four orders of magnitude.

Evaluation Uncertainty in Data-Driven Self-Driving Testing

“…We use ξ i to denote a realization of the random vector ξ. In Accelerated Evaluation approaches [1], [5], [7], the traffic environment is considered an uncertainty for the AV system under study and is represented by ξ.…”

“…The goal of this paper is to provide a way to construct a confidence interval for the evaluation results as a quantitative measurement of the input uncertainty. In AV safety evaluation, since the experiment or simulation can be quite expensive, the accelerated evaluation approach studied in [7], [1], [5] was proposed to increase the efficiency of safety evaluation. Similarly, for input uncertainty quantification, an ideal method should "minimize" the number of experiments and computing time to be computationally economic.…”

Evaluation of automated vehicles encountering pedestrians at unsignalized crossings

“…One approach to decreasing traffic deaths is to use automated vehicles, which do not suffer from challenges such as fatigue, distraction and drunk driving that humans might face. Researches have been conducted on the interaction between vehicles and vehicles [2], [3], [4]. What is not yet known, however, is exactly how automated vehicles will interact with pedestrians.…”

Accelerated Evaluation of Automated Vehicles in Car-Following Maneuvers

“…In our previous work [32], [33], the AE approach is applied to study AV behavior in lane change scenarios. In this paper, we extend the AE concept to the car-following scenarios, which is a more challenging problem, as in the lane change scenarios, the randomness of the motion of the lane-changing vehicle is modeled as a set of distributions but sampled only once at the lane change moment.…”