Trajectory Guidance: Enhanced Remote Driving of highly-automated Vehicles

TL;DR

This work presents a trajectory-guidance teleoperation framework for highly automated vehicles, integrating trajectory creation, feasibility checks, approval, and tracking within a safety-oriented architecture and HMI. Implemented in a high-fidelity simulation and validated via live ride-hailing demonstrations with autoTAXI prototypes, it demonstrates that TG can safely substitute direct remote driving in challenging disengagement scenarios. The study quantifies planning and driving times, showing that while TG can incur extra planning overhead, its driving phase can be competitive and potentially faster with optimization, alongside more conservative and safer trajectories. The findings underscore a trade-off between safety, operator workload, and responsiveness, and point to concrete future work on planning assistance, dynamic-traffic validation, and enhanced collision avoidance and HMI design to broaden applicability in real-world AV operations.

Abstract

Despite the rapid technological progress, autonomous vehicles still face a wide range of complex driving situations that require human intervention. Teleoperation technology offers a versatile and effective way to address these challenges. The following work puts existing ideas into a modern context and introduces a novel technical implementation of the trajectory guidance teleoperation concept. The presented system was developed within a high-fidelity simulation environment and experimentally validated, demonstrating a realistic ride-hailing mission with prototype autonomous vehicles and onboard passengers. The results indicate that the proposed concept can be a viable alternative to the existing remote driving options, offering a promising way to enhance teleoperation technology and improve overall operation safety.

Figures (9)

• Figure 1: A teleoperated autoTAXI vehicle maneuvering around an improvised construction site on a test track in Aldenhoven, Germany. The vehicle tracks the trajectory defined by the remote operator (path visualized in blue) from the start position to the goal position , effectively solving the AV disengagement scenario. Yellow circles ( ) depict approximate path waypoints specified by a remote operator using the presented teleoperation system.
• Figure 2: Main components of the teleoperation system.
• Figure 3: Trajectory guidance operation logic showcasing the teleoperation concept and safety mechanism elements.
• Figure 4: Reference trajectory, $r_{\textrm{ref}}$ produced during the trajectory creation phase. The vehicle is expected to track this trajectory.
• Figure 5: Simulated execution of the mrm during the trajectory tracking phase.