Evaluation of Remote Driver Performance in Urban Environment Operational Design Domains
Ole Hans, Benedikt Walter, Jürgen Adamy
TL;DR
This paper analyzes remote driving performance in an urban ODD by examining how RD experience and targeted ODDS-specific training affect control and efficiency. Using real-world Las Vegas data from 14 remote drivers over more than 24 thousand kilometers, it demonstrates a learning curve where vehicle control improves up to around 600 km and efficiency plateaus beyond 400 km, with substantial inter-driver variability. It then compares three ODDS-training approaches, finding that detailed OD training yields more anticipatory, stable braking, while scenario-based training yields solid performance with higher variability; a hybrid approach may best balance scalability with edge-case preparedness. The work supports the need for tailored RD training protocols to enhance safety, reliability, and scalability of remote driving systems in real urban environments and informs standards development for future RDS deployment.
Abstract
Remote driving has emerged as a solution for enabling human intervention in scenarios where Automated Driving Systems (ADS) face challenges, particularly in urban Operational Design Domains (ODDs). This study evaluates the performance of Remote Drivers (RDs) of passenger cars in a representative urban ODD in Las Vegas, focusing on the influence of cumulative driving experience and targeted training approaches. Using performance metrics such as efficiency, braking, acceleration, and steering, the study shows that driving experience can lead to noticeable improvements of RDs and demonstrates how experience up to 600 km correlates with improved vehicle control. In addition, driving efficiency exhibited a positive trend with increasing kilometers, particularly during the first 300 km of experience, which reaches a plateau from 400 km within a range of 0.35 to 0.42 km/min in the defined ODD. The research further compares ODD-specific training methods, where the detailed ODD training approaches attains notable advantages over other training approaches. The findings underscore the importance of tailored ODD training in enhancing RD performance, safety, and scalability for Remote Driving System (RDS) in real-world applications, while identifying opportunities for optimizing training protocols to address both routine and extreme scenarios. The study provides a robust foundation for advancing RDS deployment within urban environments, contributing to the development of scalable and safety-critical remote operation standards.