Towards Affordable On-track Testing for Autonomous Vehicle - A Kriging-based Statistical Approach

TL;DR

This paper introduces a Kriging-based statistical method to efficiently evaluate autonomous vehicles, reducing the need for extensive testing through adaptive sampling and modeling in lane change scenarios.

Contribution

It presents a novel adaptive sampling scheme for Kriging models to improve the efficiency of autonomous vehicle testing procedures.

Findings

Reduced number of required experiments in lane change scenarios

Effective application of Kriging model for vehicle evaluation

Demonstrated efficiency gains in accelerated testing

Abstract

This paper discusses the use of Kriging model in Automated Vehicle evaluation. We explore how a Kriging model can help reduce the number of experiments or simulations in the Accelerated Evaluation procedure. We also propose an adaptive sampling scheme for selecting samples to construct the Kriging model. Application examples in the lane change scenario are presented to illustrate the proposed methods.