卸载或超载：移动机器人操控工作负载的平台测量研究
Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads
AI总结：
本文首次研究了移动机器人操控工作负载在车载、边缘和云GPU平台上的表现，发现小车载GPU无法运行完整工作栈，而大车载GPU会更快耗尽电池，卸载虽缓解约束但引入网络延迟和带宽问题，最终量化了机器人舰队共享计算的机会与风险。
摘要：
移动机器人操控——机器人导航空间和与物体交互的能力——是物理AI的核心能力。基础模型在性能上取得突破，但计算成本显著。我们首次对移动机器人操控工作负载在车载、边缘和云GPU平台进行了测量研究。发现完整工作栈无法在小型车载GPU上运行，而较大的车载GPU使机器人电池数小时耗尽。卸载缓解了这些约束，但引入了自身挑战，额外网络延迟会降低任务精度，带宽需求使简单云卸载不切实际。最后，我们量化了机器人舰队共享计算的机会与陷阱。我们认为我们的测量研究对设计移动机器人的推理系统至关重要。
英文摘要：
Mobile robotic manipulation--the ability of robots to navigate spaces and interact with objects--is a core capability of physical AI. Foundation models have led to breakthroughs in their performance, but at a significant computational cost. We present the first measurement study of mobile robotic manipulation workloads across onboard, edge, and cloud GPU platforms. We find that the full workload stack is infeasible to run on smaller onboard GPUs, while larger onboard GPUs drain robot batteries several hours faster. Offloading alleviates these constraints but introduces its own challenges, as additional network latency degrades task accuracy, and the bandwidth requirement makes naive cloud offloading impractical. Finally, we quantify opportunities and pitfalls of sharing compute across robot fleets. We believe our measurement study will be crucial to designing inference systems for mobile robots.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
