A Prediction Framework for Autonomous Driving Stress to Support Sustainable Shared Autonomous Vehicle Operations

Shared autonomous vehicle (SAV) services are gaining attention as an innovative urban transportation paradigm due to their potential to lower travel costs and improve operational efficiency. Unlike manually operated vehicles, SAVs exhibit unique behavioral dynamics, including safe passenger pick-up and drop-off processes, as well as strategic repositioning and autonomous parking to anticipate future travel demands. Consequently, effective and dynamic route planning is paramount to optimizing SAV safety and operational efficiency. This study proposes a novel traffic information, termed Autonomous Driving Stress (ADS), designed to enhance the safety and efficiency of SAV route planning by quantitatively capturing the level of driving challenge encountered during autonomous operation. To predict ADS, a machine learning framework was developed, utilizing microscopic traffic simulation data that incorporates a comprehensive set of 22 input features describing SAV driving behavior, roadway characteristics, and prevailing traffic conditions. Among five machine learning algorithms evaluated, Random Forest exhibited superior predictive performance, achieving an accuracy of 80.9%. The proposed framework enables real-time ADS level prediction by continuously integrating streaming traffic data into the trained model. The dissemination of this real-time ADS information to SAVs supports proactive, informed, and dynamic route planning decisions, thereby enhancing operational safety, traffic flow, and the sustainability of SAV operations within urban mobility systems.