Learning-guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation

Computer Science > Artificial Intelligence [Submitted on 25 Mar 2026] Learning-guided Prioritized Planning for Lifelong Multi-Agent Path Finding in Warehouse Automation Han Zheng, Yining Ma, Brandon Araki, Jingkai Chen, Cathy Wu Lifelong Multi-Agent Path Finding (MAPF) is critical for modern warehouse automation, which requires multiple robots to continuously navigate conflict-free paths to optimize the overall system throughput. However, the complexity of warehouse environments and the long-term dynamics of lifelong MAPF often demand costly adaptations to classical search-based solvers. While machine learning methods have been explored, their superiority over search-based methods remains inconclusive. In this paper, we introduce Reinforcement Learning (RL) guided Rolling Horizon Prioritized Planning (RL-RH-PP), the first framework integrating RL with search-based planning for lifelong MAPF. Specifically, we leverage classical Prioritized Planning (PP) as a backbone for its simplicity and flexibility in integrating with a learning-based priority assignment policy. By formulating dynamic priority assignment as a Partially Observable Markov Decision Process (POMDP), RL-RH-PP exploits the sequential decision-making nature of lifelong planning while delegating complex spatial-temporal interactions among agents to reinforcement learning. An attention-based neural network autoregressively decodes priority orders on-the-fly, enabling efficient sequential single-agent planning by the PP planner. Evaluations in realistic warehouse simulations show that RL-RH-PP achieves the highest total throughput among baselines and generalizes effectively across agent densities, planning horizons, and warehouse layouts. Our interpretive analyses reveal that RL-RH-PP proactively prioritizes congested agents and strategically redirects agents from congestion, easing traffic flow and boosting throughput. These findings highlight the potential of learning-guided approaches to augment traditional heuristics in modern warehouse automation. Subjects: Artificial Intelligence (cs.AI); Robotics (cs.RO) Cite as: arXiv:2603.23838 [cs.AI]   (or arXiv:2603.23838v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.23838 Focus to learn more Journal reference: Journal of Artificial Intelligence Research, Vol. 85, Article 28. Publication date: March 2026 Related DOI: https://doi.org/10.1613/jair.1.20611 Focus to learn more Submission history From: Han Zheng [view email] [v1] Wed, 25 Mar 2026 01:46:35 UTC (1,132 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.RO References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)