Multi-Agent Reinforcement Learning-based Cooperative Autonomous Driving in Smart Intersections
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913825232519168 |
|---|---|
| author | Yu, Taoyuan Wang, Kui Li, Zongdian Yu, Tao Sakaguchi, Kei |
| author_facet | Yu, Taoyuan Wang, Kui Li, Zongdian Yu, Tao Sakaguchi, Kei |
| contents | Unsignalized intersections pose significant safety and efficiency challenges due to complex traffic flows. This paper proposes a novel roadside unit (RSU)-centric cooperative driving system leveraging global perception and vehicle-to-infrastructure (V2I) communication. The core of the system is an RSU-based decision-making module using a two-stage hybrid reinforcement learning (RL) framework. At first, policies are pre-trained offline using conservative Q-learning (CQL) combined with behavior cloning (BC) on collected dataset. Subsequently, these policies are fine-tuned in the simulation using multi-agent proximal policy optimization (MAPPO), aligned with a self-attention mechanism to effectively solve inter-agent dependencies. RSUs perform real-time inference based on the trained models to realize vehicle control via V2I communications. Extensive experiments in CARLA environment demonstrate high effectiveness of the proposed system, by: \textit{(i)} achieving failure rates below 0.03\% in coordinating three connected and autonomous vehicles (CAVs) through complex intersection scenarios, significantly outperforming the traditional Autoware control method, and \textit{(ii)} exhibiting strong robustness across varying numbers of controlled agents and shows promising generalization capabilities on other maps. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_04231 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Reinforcement Learning-based Cooperative Autonomous Driving in Smart Intersections Yu, Taoyuan Wang, Kui Li, Zongdian Yu, Tao Sakaguchi, Kei Robotics Multiagent Systems Systems and Control Unsignalized intersections pose significant safety and efficiency challenges due to complex traffic flows. This paper proposes a novel roadside unit (RSU)-centric cooperative driving system leveraging global perception and vehicle-to-infrastructure (V2I) communication. The core of the system is an RSU-based decision-making module using a two-stage hybrid reinforcement learning (RL) framework. At first, policies are pre-trained offline using conservative Q-learning (CQL) combined with behavior cloning (BC) on collected dataset. Subsequently, these policies are fine-tuned in the simulation using multi-agent proximal policy optimization (MAPPO), aligned with a self-attention mechanism to effectively solve inter-agent dependencies. RSUs perform real-time inference based on the trained models to realize vehicle control via V2I communications. Extensive experiments in CARLA environment demonstrate high effectiveness of the proposed system, by: \textit{(i)} achieving failure rates below 0.03\% in coordinating three connected and autonomous vehicles (CAVs) through complex intersection scenarios, significantly outperforming the traditional Autoware control method, and \textit{(ii)} exhibiting strong robustness across varying numbers of controlled agents and shows promising generalization capabilities on other maps. |
| title | Multi-Agent Reinforcement Learning-based Cooperative Autonomous Driving in Smart Intersections |
| topic | Robotics Multiagent Systems Systems and Control |
| url | https://arxiv.org/abs/2505.04231 |