An Accelerated Approach to Safely and Efficiently Test Pre-Production Autonomous Vehicles on Public Streets

TL;DR

This paper introduces an accelerated deployment framework for testing autonomous vehicles on public streets that improves safety, efficiency, and accuracy by adaptively selecting testing environments and gradually increasing deployment complexity.

Contribution

The study presents a novel framework that enhances AV testing by combining safety, efficiency, and statistical reliability through adaptive environment selection and gradual accuracy improvement.

Findings

Faster AV performance estimation with reduced deployment risk

Achieved high accuracy in AV testing through adaptive environment selection

Provided a safe and efficient alternative to traditional on-road testing

Abstract

Various automobile and mobility companies, for instance Ford, Uber and Waymo, are currently testing their pre-produced autonomous vehicle (AV) fleets on the public roads. However, due to rareness of the safety-critical cases and, effectively, unlimited number of possible traffic scenarios, these on-road testing efforts have been acknowledged as tedious, costly, and risky. In this study, we propose Accelerated De- ployment framework to safely and efficiently estimate the AVs performance on public streets. We showed that by appropriately addressing the gradual accuracy improvement and adaptively selecting meaningful and safe environment under which the AV is deployed, the proposed framework yield to highly accurate estimation with much faster evaluation time, and more importantly, lower deployment risk. Our findings provide an answer to the currently heated and active discussions on how to properly test AV performance on public roads so as to achieve safe, efficient, and statistically-reliable testing framework for AV technologies.