IntNet: A communication-driven multi-agent reinforcement learning framework for cooperative autonomous driving
File(s)
Accepted version
Author(s)
Parada, Leandro
Yu, Kevin
Angeloudis, panagiotis
Parada Pradenas, Leandro
Type
Journal Article
Abstract
Achieving safety in autonomous driving through Multi-Agent Reinforcement Learning (MARL) is a critical yet challenging task due to non-stationarity, partial observability, and the need for effective coordination among agents. Although earlier cooperative MARL methods have aimed to improve coordination by sharing encoded state observations, we find these strategies are insufficient in safety-critical scenarios. To address this gap, we present IntNet, a novel MARL framework that enhances safety by incorporating the transmission of vehicle intent and adaptive communication scheduling into a unified end-to-end learning paradigm, jointly optimising all components for safe coordination. Central to our approach is an observation prediction module that enables agents to forecast subsequent policy outputs, which they can then share across a vehicle-to-vehicle network. Our model-free architecture employs a Graph Attention Network to process incoming messages and a scheduler component to dynamically optimise the communication graph for bandwidth efficiency. We compare IntNet against state-of-the-art communicative MARL methods in complex urban environments with both autonomous and human-operated vehicles, achieving improved coordination, lower collision rates, and reducing communication efforts by up to 60%. Through extensive experiments, we assess the framework's learning efficiency, scalability, and the balance between information sharing and bandwidth usage for collision-free trajectories.
Date Issued
2025-03-01
Date Acceptance
2025-01-06
Citation
IEEE Robotics and Automation Letters, 2025, 10 (3), pp.2478-2485
ISSN
2377-3766
Publisher
Institute of Electrical and Electronics Engineers
Start Page
2478
End Page
2485
Journal / Book Title
IEEE Robotics and Automation Letters
Volume
10
Issue
3
Copyright Statement
© 2025, IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Publication Status
Published
Date Publish Online
2025-01-17