发表机构
Aditya Dutta, Joon-Seok Kim ∗（Aditya Dutta, Joon-Seok Kim）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究多对多多智能体取货和送货问题，提出SGM方法，通过记录仓库节点和边的近期执行信号排序端点与路由偏好，在多种布局、负载条件下实验，结果显示该方法能提高仓库吞吐量。
AI 中文摘要
自动化履行仓库必须持续分配并执行取货和送货工作，同时避免拥堵。在多对多多智能体取货和送货（MAPD）中，请求指定一个库存单元而非固定端点，这要求控制器在路径规划前选择智能体、源点和目的地。现有图引导方法主要在目标固定后影响路由，端点实例化未考虑近期流量。我们引入stigmergic图记忆（SGM），它是一个有界、衰减的记忆层，记录仓库节点和有向边上的近期执行信号，以对可行端点和路由偏好进行排序，而不改变碰撞约束或规划器有效性。在五种布局、三种负载水平及每种条件25个种子的成对请求流中，SGM在所有15种地图负载条件下均优于两种重构的多对多分配基线，成对吞吐量增益为20.5 - 36.7%。这些结果表明，近期执行记忆可通过影响哪些可行目标进入规划器来提高仓库吞吐量，而不仅是智能体如何前往已固定目标的方式。
英文摘要
Automated fulfillment warehouses must continuously assign and execute pickup-and-delivery work while avoiding congestion. In many-to-many Multi-Agent Pickup and Delivery (MAPD), a request specifies a stock-keeping unit rather than fixed endpoints, requiring the controller to select an agent, source, and destination before path planning. Existing graph-guidance methods primarily influence routing after goals are fixed, leaving endpoint instantiation uninformed by recent traffic. We introduce Stigmergic Graph Memory (SGM), a bounded, decaying memory layer that records recent execution signals on warehouse nodes and directed edges to rank feasible endpoints and route preferences without altering collision constraints or planner validity. Across paired request streams on five layouts, three load levels, and 25 seeds per condition, SGM outperforms two reconstructed many-to-many allocation baselines in all 15 map-load conditions, with paired throughput gains of 20.5-36.7%. These results show that recent execution memory can improve warehouse throughput by shaping which feasible goals enter the planner, not only how agents travel to already fixed goals.
Comments16 pages total: 7 pages main text, 2 pages references, and 7 pages appendix
