5G-Enabled Teleoperated Driving: An Experimental Evaluation

TL;DR

The paper addresses the challenge of enabling safe teleoperated driving over 5G by deploying a real-world testbed based on a Kia Soul EV with a drive-by-wire system and a RoboCar ROS2 ADS. The authors design a complete teleoperation framework and evaluate it under live 5G conditions, measuring glass-to-glass latency, round-trip time, jitter, and steering response. They find an average G2G latency of about $202.41$ ms and RTT around $46.67$ ms, with steering delays reaching up to $750$ ms, indicating that G2G latency is the primary bottleneck for high-speed teleoperation. The work demonstrates the feasibility of 5G-enabled teleoperation at low speeds while identifying key bottlenecks and outlining concrete avenues for streaming optimizations, adaptive networking, and future long-distance trials to enable safer, scalable autonomous mobility."

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.

Figures (5)

• Figure 1: Experimental vehicle based on Kia Soul EV with the teleoperated driving interface.
• Figure 2: Description of the hardware and software architecture of the experimental setup for teleoperated driving.
• Figure 3: RTT measured as the time elapsed between a sent teleoperation command and a corresponding reply from the remote vehicle. The achieved RTT enables safe teleoperated driving at moderate to high speeds.
• Figure 4: G2G latency between the vehicle camera and the teleoperated driving interface monitor. The achieved G2G latency enables safe teleoperated driving for low speed.
• Figure 5: Realized vehicle steering angle and steering command sent from teleoperation interface, both normalized to [-1, 1].