From Gridworlds to Warehouses: Adapting Lightweight One-shot Multi-Agent Pathfinding for AGVs

2026-05-15

AI Summary

This work addresses the limitations of traditional multi-agent path finding (MAPF), which relies on simplified grid-based assumptions that fail to capture the kinematic and safety constraints of differential-drive automated guided vehicles (AGVs) in real-world warehouses. To bridge this gap, the paper introduces a novel Multi-Agent Warehouse Path Finding (MAWPF) framework tailored for differential-drive AGVs, extending classical MAPF to incorporate four realistic constraints: straight-line motion, in-place rotation, variable-speed time costs, and no-tailgating rules. The authors evaluate several lightweight suboptimal solvers—including PP, LNS2, PIBT, and LaCAM—adapted to this setting. Experimental results demonstrate that PIBT-based methods exhibit superior scalability in large-scale scenarios, achieving significantly better solvability than PP and LNS2 despite slightly higher solution costs.

Abstract

Multi-agent pathfinding (MAPF) under one-shot planning is a core component of warehouse automation, yet classical formulations typically assume four-connected 2D grids with unit-time moves in four directions. To fill reality gaps while still being trackable with discrete combinatorial search, this work proposes a more practical counterpart tailored to differential-drive AGVs. We term this multi-agent warehouse pathfinding (MAWPF), featured with four constraints: (i) agent actions are restricted to straight motion and in-place rotation; (ii) rotations require multi-step costs; (iii) acceleration and deceleration are considered, and; (iv) follower collisions are prohibited to prevent rear-end crashes. To solve MAWPF efficiently, we adapt representative suboptimal MAPF algorithms-PP, LNS2, PIBT, and LaCAM-and conduct comprehensive benchmarking. Our experiments reveal that PP and LNS2 struggle to solve instances with many agents, while PIBT-based approaches achieve preferable scalability with increased solution cost. We believe that these constitute an important step toward adapting classical gridworld MAPF to operational warehouse setups.

Problem

• multi-agent pathfinding
• warehouse automation
• differential-drive AGVs
• one-shot planning
• collision avoidance

Innovation

• Multi-Agent Pathfinding
• Warehouse Automation
• Differential-Drive AGVs
• One-shot Planning
• MAWPF