---
title: "From Gridworlds to Warehouses: Adapting Lightweight One-shot Multi-Agent Pathfinding for AGVs"
authors:
  - "Hiroki Nagai"
  - "Keisuke Okumura"
doi: "10.24963/ijcai.2026/35"
url: "https://ijcai.org/proceedings/2026/35"
pdf: "https://ijcai.org/proceedings/2026/0035.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "306-313"
track: "Main Track"
keywords:
  - "Agent-based and Multi-agent Systems: Multi-agent planning"
  - "Search: Heuristic search"
  - "Robotics: Motion and path planning"
---

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

Hiroki Nagai, Keisuke Okumura

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 306-313. DOI: [10.24963/ijcai.2026/35](https://doi.org/10.24963/ijcai.2026/35)

## 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.