Kremer, Philipp (Technische Universität Berlin), Gingell, Daniel (TU Berlin), Park, Sangyoung (Technical University of Berlin)

Fuzzy Shared-Control for Digital Twin-Based Teleoperated Driving under Network Delay

Scheduled for presentation during the Poster Session "Operation and navigation of automated vehicles" (FrAT16), Friday, September 27, 2024, 10:30−12:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 3, 2024

Abstract

Teleoperated driving, where a remote human operator remains in charge of critical driving decisions, is a promising solution to overcome the technical and legal hurdles autonomous vehicles are facing in public traffic. However, network induced latency and available bandwidth are critical constraints in teleoperated driving (ToD), as it relies on high definition video streams sent to the operator and steering and acceleration control commands transmitted back to the vehicle. In this work, we propose fuzzy controllers capable of combining the control output from the human teleoperator with information from a real-time digital twin, i.e., driving lanes, intended routes and network characteristics. The real-time digital twin is a digital copy of the physical vehicle maintained on the teleoperator workstation. An experimental user study in a driving simulator with 10 participants reveals a 31% increase in lane-keeping accuracy, a significant reduction of crashes and a decrease of teleoperator workload.