Automatic Intersection Management in Mixed Traffic Using Reinforcement Learning and Graph Neural Networks

TL;DR

This paper introduces a reinforcement learning and graph neural network-based approach for automatic intersection management in mixed traffic, improving efficiency and reducing delays for both automated and human-driven vehicles.

Contribution

It extends scene representation to mixed traffic with uncertainty modeling and demonstrates significant throughput and delay improvements over baseline methods.

Findings

Increased vehicle throughput with more automated vehicles.

Reduced delays for both automated and human-driven vehicles.

Effective handling of uncertainty in human driver behavior.

Abstract

Connected automated driving has the potential to significantly improve urban traffic efficiency, e.g., by alleviating issues due to occlusion. Cooperative behavior planning can be employed to jointly optimize the motion of multiple vehicles. Most existing approaches to automatic intersection management, however, only consider fully automated traffic. In practice, mixed traffic, i.e., the simultaneous road usage by automated and human-driven vehicles, will be prevalent. The present work proposes to leverage reinforcement learning and a graph-based scene representation for cooperative multi-agent planning. We build upon our previous works that showed the applicability of such machine learning methods to fully automated traffic. The scene representation is extended for mixed traffic and considers uncertainty in the human drivers' intentions. In the simulation-based evaluation, we model measurement uncertainties through noise processes that are tuned using real-world data. The paper evaluates the proposed method against an enhanced first in - first out scheme, our baseline for mixed traffic management. With increasing share of automated vehicles, the learned planner significantly increases the vehicle throughput and reduces the delay due to interaction. Non-automated vehicles benefit virtually alike.