A GPT-based Decision Transformer for Multi-Vehicle Coordination at Unsignalized Intersections

TL;DR

This paper introduces a GPT-based Decision Transformer for coordinating multiple vehicles at unsignalized intersections, demonstrating improved efficiency and adaptability over traditional reservation systems through extensive experiments.

Contribution

It applies the Decision Transformer architecture to multi-vehicle coordination, showcasing its effectiveness and generalization capabilities in complex intersection scenarios.

Findings

Outperforms reservation-based systems in total travel time

Generalizes well to various traffic scenarios and configurations

Handles noise and continuous interactions effectively

Abstract

In this paper, we explore the application of the Decision Transformer, a decision-making algorithm based on the Generative Pre-trained Transformer (GPT) architecture, to multi-vehicle coordination at unsignalized intersections. We formulate the coordination problem so as to find the optimal trajectories for multiple vehicles at intersections, modeling it as a sequence prediction task to fully leverage the power of GPTs as a sequence model. Through extensive experiments, we compare our approach to a reservation-based intersection management system. Our results show that the Decision Transformer can outperform the training data in terms of total travel time and can be generalized effectively to various scenarios, including noise-induced velocity variations, continuous interaction environments, and different vehicle numbers and road configurations.