GRAND: Guidance, Rebalancing, and Assignment for Networked Dispatch in Multi-Agent Path Finding
By: Johannes Gaber , Meshal Alharbi , Daniele Gammelli and more
Potential Business Impact:
Robots deliver packages faster in busy warehouses.
Large robot fleets are now common in warehouses and other logistics settings, where small control gains translate into large operational impacts. In this article, we address task scheduling for lifelong Multi-Agent Pickup-and-Delivery (MAPD) and propose a hybrid method that couples learning-based global guidance with lightweight optimization. A graph neural network policy trained via reinforcement learning outputs a desired distribution of free agents over an aggregated warehouse graph. This signal is converted into region-to-region rebalancing through a minimum-cost flow, and finalized by small, local assignment problems, preserving accuracy while keeping per-step latency within a 1 s compute budget. On congested warehouse benchmarks from the League of Robot Runners (LRR) with up to 500 agents, our approach improves throughput by up to 10% over the 2024 winning scheduler while maintaining real-time execution. The results indicate that coupling graph-structured learned guidance with tractable solvers reduces congestion and yields a practical, scalable blueprint for high-throughput scheduling in large fleets.
Similar Papers
Flow-Based Task Assignment for Large-Scale Online Multi-Agent Pickup and Delivery
Multiagent Systems
Helps robots deliver packages faster and smarter.
Sequence Pathfinder for Multi-Agent Pickup and Delivery in the Warehouse
Robotics
Helps robots find the best way to move items.
Multi-Agent Path Finding via Offline RL and LLM Collaboration
Multiagent Systems
Robots learn to move together faster, smarter.