Hybrid Eyes: Design and Evaluation of the Prediction-level Cooperative Driving with a Real-world Automated Driving System

TL;DR

This paper introduces PreCoAD, a cooperative driving system where humans assist automated driving systems at the prediction level, improving performance and user experience in highway scenarios based on simulator studies.

Contribution

The paper presents a novel prediction-level cooperation concept and an interactive prototype that enhances ADS performance through human input, validated by real-world driving simulations.

Findings

PreCoAD improves automated driving performance.

Participants reported increased comfort and positive experience.

System insights were gained from follow-up interviews.

Abstract

Currently, there are still various situations in which automated driving systems (ADS) cannot perform as well as a human driver, particularly in predicting the behaviour of surrounding traffic. As humans are still surpassing state-of-the-art ADS in this task, a new concept enabling human driver to help ADS to better anticipate the behaviour of other road users was developed. Preliminary results suggested that the collaboration at the prediction level can effectively enhance the experience and comfort of ADS. For an in-depth investigation of the concept, we implemented an interactive prototype, called Prediction-level Cooperative Automated Driving system (PreCoAD), adapting an existing ADS that has been previously validated on the public road. The results of a driving simulator study among 15 participants in different highway scenarios showed that PreCoAD could enhance automated driving performance and provide a positive user experience. Follow-up interviews with participants also provided insights into the improvement of the system.