MAPF-World：面向多智能体路径规划的动作世界模型

View PDF HTML (experimental)

Abstract:Multi-agent path finding (MAPF) studies the problem of planning conflict-free paths for multiple agents from given start locations to designated goals, with applications in robot-assisted logistics and social navigation. Recent decentralized learned solvers have shown promise for large-scale MAPF, particularly when leveraging foundation models and large datasets. However, most existing methods rely on reactive policies, often resulting in congestion, deadlocks, and degraded generalization in high agent-density environments. To address these limitations, we propose MAPF-World, an autoregressive action world model for MAPF that unifies short-horizon local future prediction and action generation, enabling decision-making beyond immediate local observations. MAPF-World models short-horizon local dynamics by predicting the next local observation and neighboring agents' action intentions, capturing both spatial structures and temporal interaction patterns. We further introduce a spatio-agent positional encoding that integrates spatial awareness with agent-level semantics in Transformer-based architectures, facilitating more coordinated multi-agent behaviors. In addition, we augment existing MAPF benchmarks by introducing an automated map generator grounded in real-world urban layouts, aiming to narrow the gap between synthetic simulation and practical deployment scenarios. Extensive experiments across diverse map types and interaction settings demonstrate that MAPF-World achieves strong performance compared with existing learned solvers. Notably, it exhibits robust zero-shot generalization and maintains a high success rate even as agent density increases.

Submission history

From: Zhanjiang Yang [view email]
[v1] Sat, 16 Aug 2025 15:50:26 UTC (4,215 KB)
[v2] Sun, 7 Sep 2025 04:05:16 UTC (3,825 KB)
[v3] Thu, 8 Oct 2026 03:29:23 UTC (2,379 KB)