OpenCDA-MARL: A Unified Benchmarking Framework for Cooperative Autonomous Intersection Management With Multi-Agent Reinforcement Learning
L. Guo, L. Liu, J. Tang, B. Liu, S. Cao
IEEE Robotics and Automation Letters, 2026 , Vol. 11 (4) , pp. 4291-4298
Abstract
Single-vehicle autonomy remains constrained by perception errors and uncoordinated maneuvers, resulting in avoidable collisions and throughput losses at intersections. Cooperative Driving Automation (CDA) offers substantial gains, yet fragmented toolchains hinder progress: industry develops closed systems, while academic studies rely on simplified simulators that lack realistic dynamics. We introduce OpenCDA-MARL, an open-source extension of OpenCDA that transforms the high-fidelity CARLA simulator into a unified benchmarking platform for autonomous intersection management (AIM). The framework provides a modular multi-agent reinforcement learning (MARL) API enabling reproducible training and comparison of cooperative policies under identical physical conditions. Building upon OpenCDA's integration and scenario managers, OpenCDA-MARL provides an additional MARL Adapter Interface layer, along with MARL scenario and environment managers for custom traffic conditions, performance tracking, baseline agents, and standard MARL algorithms, to support a comprehensive MARL evaluation suite in AIM.
Citation
L. Guo, L. Liu, J. Tang, B. Liu, S. Cao. "OpenCDA-MARL: A Unified Benchmarking Framework for Cooperative Autonomous Intersection Management With Multi-Agent Reinforcement Learning." IEEE Robotics and Automation Letters 11(4): 4291-4298, 2026. DOI: 10.1109/LRA.2026.3664656
Publication Snapshot
- Authors
- L. Guo, L. Liu, J. Tang, B. Liu, S. Cao
- Venue
- IEEE Robotics and Automation Letters
- Published
- 2026
- Pages
- 4291-4298