发表机构
Georgia Institute of Technology（佐治亚理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出从远程GPU向多机器人提供策略服务的调度问题，构建Armory系统，提出考虑机器人异构性的调度算法，使真实场景系统吞吐量最高提升18%。
AI 中文摘要
大规模部署机器人基础模型是实现通用机器人潜力的下一步，但视觉-语言-动作（VLA）等基础模型计算需求高，而设备端计算受功率和空间限制。本文提出从远程GPU向多台机器人提供机器人策略服务的问题，并将其建模为调度问题。我们构建了Armory服务系统，已在仿真和真实机器人集群上验证。实验表明，当所有机器人相同时，简单调度启发式算法表现良好，但当机器人以不同速率消耗动作块时则表现不佳，暴露了传统批量处理方法与机器人策略执行闭环需求之间的不匹配。为解决此问题，我们提出一种考虑异构性的调度算法，在真实实验中可将整体系统吞吐量提升最高达18%，更多细节可访问此https URL。
英文摘要
Deploying robot foundation models at scale is the next step towards realizing the potential of general-purpose robots. However, Vision-Language-Action (VLA) and other foundation models are computationally demanding, and on-device compute is constrained by power and space. In this paper, we introduce the problem of serving a robot policy to multiple robots from a remote GPU and formulate it as a scheduling problem. We build Armory, a serving system validated on fleets of both simulated and real robots. Our experiments show that naive scheduling heuristics perform well when all robots are the same, but fall short when robots consume action chunks at different rates, uncovering a mismatch between conventional batching methods and the closed-loop requirements of robot policy execution. To address this, we propose a scheduling algorithm that accounts for this heterogeneity and improves overall system throughput by up to $18\%$ in real-world experiments. Additional details are available at https://gatech-rl2.github.io/actionchunkscheduling.
