Multi-Agent Embodied Autonomous Driving: From V2X Information Exchange to Shared World Models

2026-06-11

AI Summary

This work addresses the challenge of cooperative decision-making for multi-agent autonomous driving in uncertain environments by proposing a Shared World Model (SWM) as a unified framework that integrates perception, cognition, and decision-making. Through a systematic review of over 380 publications, it synthesizes key technologies including vehicle-to-everything (V2X) communication, collaborative perception, intention inference, and joint planning, highlighting a critical gap: current research heavily relies on simulation and offline evaluation while lacking real-time safety guarantees. The paper identifies three pivotal research directions—verifiable state consistency, robust intention alignment, and safe coordination—and advocates for a foundation-model-driven cooperative paradigm geared toward real-world deployment, thereby providing both theoretical grounding and a technical pathway for end-to-end collaborative driving.

Abstract

Autonomous driving is shifting from isolated vehicle intelligence toward multi-agent embodied systems that share perception, infer intent, and coordinate action under uncertainty. This survey examines this transition through the lens of Shared World Models (SWMs): predictive cross-agent representations maintained across vehicles, infrastructure, and other traffic participants. We review more than 380 publications spanning vehicle-to-everything (V2X) communication, collaborative perception, inter-agent cognition, cooperative planning, end-to-end cooperative driving, and simulation and data engines for closed-loop validation. The organizing question is how exchanged observations become aligned state, intent-aware interaction, and coordinated downstream action. Across the surveyed literature, evaluation remains concentrated in simulation, curated benchmarks, and offline protocols. Foundation-model-based coordination also lacks verified real-time safety guarantees in open traffic. These gaps motivate key research priorities for multi-agent embodied autonomous driving (MAEAD): verifiable shared-state maintenance, robust intent and plan alignment, and safe coordinated action under communication, latency, and deployment constraints.

Problem

• Multi-Agent Embodied Autonomous Driving
• Shared World Models
• V2X Communication
• Cooperative Planning
• Intent Alignment

Innovation

• Shared World Models
• Multi-Agent Embodied Autonomous Driving
• V2X Communication
• Collaborative Perception
• Cooperative Planning