Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads

Sara Pohland, Xenofon Foukas, Ganesh Ananthanarayanan, Andrey Kolobov, Sanjeev Mehrotra, Bozidar Radunovic, Ankit Verma

Abstract

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.

Offload or Overload: A Platform Measurement Study of Mobile Robotic Manipulation Workloads

Abstract

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.
Paper Structure (42 sections, 17 figures, 4 tables)

This paper contains 42 sections, 17 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Background & Motivation
  3. Mobile robotic manipulation
  4. Advances in robotics capabilities
  5. Experimental Setup
  6. Robotic platforms
  7. Compute & network infrastructure
  8. Robot onboard compute:
  9. Edge compute:
  10. Cloud compute:
  11. Connectivity:
  12. Workloads Under Study and Methodology
  13. Semantic mapping and planning
  14. VLMaps:
  15. GraphEQA:
  16. ...and 27 more sections

Figures (17)

  • Figure 1: Robotic platforms used for evaluating workloads.
  • Figure 2: Experimental setup of robots, edge compute with Wi-Fi and 5G connectivity, and cloud compute.
  • Figure 3: Trajectory of TurtleBot for navigation task and unmapped hidden obstacle.
  • Figure 4: GPU and CPU memory consumption of workloads.
  • Figure 5: VLMaps execution time across compute platforms.
  • ...and 12 more figures