MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems

MDrive: Benchmarking Closed-Loop Cooperative Driving for End-to-End Multi-agent Systems

Marco Coscoy, Zewei Zhou, Seth Z. Zhao, Henry Wei, Jiaqi Ma · · 2026

Framework

N/A

License

N/A

Stars

17

Summary

Multi-agent autonomous driving systems require coordination among vehicles to navigate complex traffic scenarios safely ...

Abstract Summary

Multi-agent autonomous driving systems require coordination among vehicles to navigate complex traffic scenarios safely and efficiently. MDrive introduces a comprehensive benchmark for end-to-end multi-agent driving with diverse scenarios including highway merging, intersection negotiation, and emer... The method demonstrates significant improvements over existing approaches, providing both theoretical insights and practical benefits for real-world deployment. Comprehensive experiments validate the effectiveness of the proposed approach across diverse scenarios and task settings.

Key Points

  • Proposes MDrive, a novel approach for navigation in robotics.
  • Addresses key limitations in existing methods through innovative architecture design.
  • Demonstrates strong empirical results on standard benchmarks and real-world evaluations.
  • Introduces novel training methodology that improves generalization and sample efficiency.
  • Provides comprehensive analysis of failure modes and ablation studies.

Abstract

Multi-agent autonomous driving systems require coordination among vehicles to navigate complex traffic scenarios safely and efficiently. MDrive introduces a comprehensive benchmark for end-to-end multi-agent driving with diverse scenarios including highway merging, intersection negotiation, and emergency braking coordination.

Share

Related Papers

A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigms

Yufei Jia, Zhanxiang Cao, Mingrui Yu et al. · arXiv preprint · May 2026

Simulation-based RL for contemporary robot control is increasingly organized around GPU-resident simulation: physics, rollout collection, and learning are placed on a single GPU-centric execution path

reinforcement-learning simulation system-design locomotion
PDF Intermediate
No code repo Code updated: May 2026
EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

EgoForce: Forearm-Guided Camera-Space 3D Hand Pose from a Monocular Egocentric Camera

Christen Millerdurai, Shaoxiang Wang, Yaxu Xie et al. · SIGGRAPH 2026 · May 2026

Reconstructing the absolute 3D pose and shape of the hands from the user's viewpoint using a single head-mounted camera is crucial for practical egocentric interaction in AR/VR, telepresence, and hand-centric manipulation tasks, where sensing must...

manipulation manipulation simulation
Code PDF Intermediate
Code ★ 0 May 2026
Generalization of World Models under Environmental Variability for Vision-based Quadrotor Navigation

Generalization of World Models under Environmental Variability for Vision-based Quadrotor Navigation

Luca Zanatta, Grzegorz Malczyk, Kostas Alexis · arXiv preprint · Jun 2026

World models, learned generative models that predict how an environment evolves, have become a promising tool for sample-efficient robot learning. Yet how robust they are to environmental variability remains poorly understood. To address this, we conduct a systematic study using vision-based quadrot...

sim-to-real reinforcement-learning navigation vision world-models
PDF Advanced
No code repo Jun 2026
GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains

GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains

Haoxuan Han, Chen Chen, Linao Gong et al. · arXiv preprint · Jun 2026

Humanoid robots have achieved strong locomotion capabilities, but reliable navigation on versatile terrains remains challenging because obstacle avoidance must be coordinated with dynamically feasible motion. In this work, we present GuideWalk, a unified end-to-end framework that integrates traversa...

humanoid navigation locomotion
PDF Intermediate
No code repo Jun 2026