首次测量移动机器人操作任务在不同计算平台的性能与能耗表现。
Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads
- 对比车载、边缘和云端GPU运行机器人操作任务的效率与耗电情况。
- 小尺寸车载显卡无法运行完整任务，大显卡使电池续航缩短数小时。
- 跨机器人共享算力有潜力但受网络延迟和带宽限制，需谨慎设计。
移动机器人操作——即机器人在空间中导航并交互物体的能力——是物理人工智能的核心能力。基础模型虽带来性能突破，但伴随显著的计算开销。本文首次对车载、边缘和云端GPU平台上的移动机器人操作工作负载进行测量研究。结果表明，完整工作负载无法在小型车载GPU上运行，而大尺寸车载GPU会使机器人电池续航缩短数小时。卸载计算可缓解资源压力，但引入额外网络延迟，降低任务准确率，且带宽需求使简单云卸载不切实际。最后，我们量化了跨机器人集群共享计算的机遇与风险。本测量研究对设计移动机器人推理系统具有关键意义。
原文摘要 · Abstract (English)
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.
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。