🤖 AI Summary
This work addresses the safety and reliability requirements of 5G-based remote driving by systematically evaluating human operators’ ability to remotely take over autonomous vehicles in complex scenarios. We develop an end-to-end experimental system using a real-world Kia Soul EV, integrated with 5G standalone (SA) networking, real-time video streaming, ROS-based actuation interfaces, and a custom-built remote control platform. For the first time, we quantitatively measure and attribute the glass-to-glass (G2G) latency—the end-to-end delay from video capture to vehicle response—under operational conditions. Results show an average G2G latency of 202 ms (with round-trip time of 47 ms), identifying it as the primary performance bottleneck; meanwhile, high steering command accuracy confirms the feasibility of low-latency remote control. Key contributions include: (1) the first empirical, full-stack G2G latency measurement and root-cause analysis on a live 5G SA network; (2) identification of 202 ms as a critical latency threshold for safe接管; and (3) a communication-control co-design framework for safety-critical handover optimization.
📝 Abstract
Teleoperated driving enables remote human intervention in autonomous vehicles, addressing challenges in complex driving environments. However, its effectiveness depends on ultra-low latency, high-reliability communication. This paper evaluates teleoperated driving over 5G networks, analyzing key performance metrics such as glass-to-glass (G2G) latency, RTT and steering command delay. Using a real-world testbed with a Kia Soul EV and a remote teleoperation platform, we assess the feasibility and limitations of 5G-enabled teleoperated driving. Our system achieved an average G2G latency of 202ms and an RTT of 47ms highlighting the G2G latency as the critical bottleneck. The steering control proved to be mostly accurate and responsive. Finally, this paper provides recommendations and outlines future work to improve future teleoperated driving deployments for safer and more reliable autonomous mobility.