MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems
2026-05-11 • Robotics
Robotics
AI summaryⓘ
The authors created MDrive, a new testing system for cars that talk to each other (V2X) while driving autonomously. They point out that past tests didn't fully capture real driving behavior or interactions between cars. Their results show that cars working together usually do better than alone, but sharing what they see doesn't always help with planning, and negotiating between cars can sometimes make things worse in busy traffic. MDrive also offers tools for making new test scenarios and simulating human drivers to help improve future cooperative driving systems.
Vehicle-to-Everything (V2X)Autonomous DrivingMulti-Agent SystemsClosed-Loop EvaluationPerception SharingPlanningNegotiationSimulation BenchmarkNHTSA Pre-crash TypologiesHuman-in-the-Loop Simulation
Authors
Marco Coscoy, Zewei Zhou, Seth Z. Zhao, Henry Wei, Angela Magtoto, Johnson Liu, Rui Song, Walter Zimmer, Zhiyu Huang, Chen Tang, Bolei Zhou, Jiaqi Ma
Abstract
Vehicle-to-Everything (V2X) communication has emerged as a promising paradigm for autonomous driving, enabling connected agents to share complementary perception information and negotiate with each other to benefit the final planning. Existing V2X benchmarks, however, fall short in two ways: (i) open-loop evaluations fail to capture the inherently closed-loop nature of driving, leading to evaluation gaps, and (ii) current closed-loop evaluations lack behavioral and interactive diversity to reflect real-world driving. Thus, it is still unclear the extent of benefits of multi-agent systems for closed-loop driving. In this paper, we introduce MDrive, a closed-loop cooperative driving benchmark comprising 225 scenarios grounded in both NHTSA pre-crash typologies and real-world V2X datasets. Our benchmark results demonstrate that multi-agent systems are generally better than single-agent counterparts. However, current multi-agent systems still face two important challenges: (i) perception sharing enhances perceptions, but doesn't always translate to better planning; (ii) negotiation improves planning performance but harms it in complex and dense traffic scenarios. MDrive further provides an open-source toolbox for scenario generation, Real2Sim conversion, and human-in-the-loop simulation. Together, MDrive establishes a reproducible foundation for evaluating and improving the generalization and robustness of cooperative driving systems.