Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908900050075648 |
|---|---|
| author | Pohland, Sara Foukas, Xenofon Ananthanarayanan, Ganesh Kolobov, Andrey Mehrotra, Sanjeev Radunovic, Bozidar Verma, Ankit |
| author_facet | Pohland, Sara Foukas, Xenofon Ananthanarayanan, Ganesh Kolobov, Andrey Mehrotra, Sanjeev Radunovic, Bozidar Verma, Ankit |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_18284 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads Pohland, Sara Foukas, Xenofon Ananthanarayanan, Ganesh Kolobov, Andrey Mehrotra, Sanjeev Radunovic, Bozidar Verma, Ankit Robotics Artificial Intelligence Networking and Internet Architecture Systems and Control 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. |
| title | Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads |
| topic | Robotics Artificial Intelligence Networking and Internet Architecture Systems and Control |
| url | https://arxiv.org/abs/2603.18284 |