Autonomous Navigation of Tractor-Trailer Vehicles through Roundabout Intersections

TL;DR

This paper develops specialized models for autonomous tractor-trailer navigation through roundabouts using high-fidelity simulation and trains a reinforcement learning agent that achieves a 73% success rate, addressing a gap in existing research.

Contribution

It introduces tailored models for tractor-trailer vehicles in simulation and applies a reinforcement learning approach for autonomous navigation through roundabouts.

Findings

Achieved a 73% success rate in roundabout navigation.

Developed high-fidelity tractor-trailer models in CARLA.

Established a benchmark dataset for future research.

Abstract

In recent years, significant advancements have been made in the field of autonomous driving with the aim of increasing safety and efficiency. However, research that focuses on tractor-trailer vehicles is relatively sparse. Due to the physical characteristics and articulated joints, such vehicles require tailored models. While turning, the back wheels of the trailer turn at a tighter radius and the truck often has to deviate from the centre of the lane to accommodate this. Due to the lack of publicly available models, this work develops truck and trailer models using the high-fidelity simulation software CARLA, together with several roundabout scenarios, to establish a baseline dataset for benchmarks. Using a twin-q soft actor-critic algorithm, we train a quasi-end-to-end autonomous driving model which is able to achieve a 73% success rate on different roundabouts.