用环境记忆提升仓库多对多配送效率，让系统自动选好起点终点。
Stigmergic Graph Memory: An Environment-Aware Approach for Many-to-Many Multi-Agent Pickup and Delivery
- 通过动态记忆记录节点和路径的近期使用情况，指导目标选择
- 在5种布局、3种负载下，吞吐量提升20.5%至36.7%
- 适合需要实时避拥堵的自动化仓储系统应用
自动化仓储需持续分配并执行多对多多智能体取送任务，同时避免拥堵。在多对多多智能体取送（MAPD）中，请求指定的是货品单位而非固定端点，控制器需先选定代理、源点和目的地，再进行路径规划。现有图引导方法主要在目标确定后影响路由，未利用最新交通信息指导端点选择。本文提出一种有界衰减的记忆层——刺激式图记忆（Stigmergic Graph Memory, SGM），记录仓库节点与有向边的近期执行信号，用于排序可行端点和路由偏好，不改变碰撞约束或规划器有效性。在五个布局、三种负载水平、每组条件25个随机种子的成对请求流测试中，SGM在全部15种地图-负载组合下均优于两个重构的多对多分配基线，在配对吞吐量上提升20.5%至36.7%。结果表明，近期执行记忆可通过影响进入规划器的可行目标，而非仅优化已有目标的路径，显著提升仓库吞吐量。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。