Autonomous driving technology is widely recognized as a key solution for enhancing future road safety by preventing traffic accidents caused by human error. However, the widespread adoption of autonomous vehicles (AVs) has not yet been achieved, and traffic accidents involving autonomous vehicles in mixed traffic conditions continue to be reported. This study analyzed conflict events using real-world autonomous driving data and identified AV conflict hotspots. A two-dimensional Time to Collision was employed as a surrogate safety indicator to comprehensively capture various types of conflicts in urban interrupted traffic flow. Analysis of approximately 1000 h of driving data revealed 958,011 conflict events, which were distributed along major AV trajectories. The Network Kernel Density Estimation was applied to identify AV conflict hotspots based on conflict events. The optimal hotspot identification model was determined by evaluating various parameter combinations using the Predictive Accuracy Index validated against real-world accident data. Several hotspots were identified on arterial roads with signalized intersections, nearby bus stops, and frequent access points to roadside facilities such as restaurants, stores, gas stations, and residential complexes. Differences in hotspot patterns by conflict type reveal distinct risk characteristics across road sections, emphasizing the necessity of customized safety countermeasures for each conflict type. The findings of this study are expected to accelerate the deployment and wider adoption of autonomous driving technology, promoting the sustainable operation of AVs.

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.