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

arXiv: https://arxiv.org/abs/2603.18284 · HTML: https://mlsanity.com/paper/2603.18284/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 52 references that are in the map.
- First posted on arXiv 18 Mar 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithms](https://mlsanity.com/paper/1907.03146/) (2019)
- [RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation](https://mlsanity.com/paper/2403.06341/) (2024)
- [VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference](https://mlsanity.com/paper/2512.01031/) (2025)
- [GraphEQA: Using 3D Semantic Scene Graphs for Real-time Embodied Question Answering](https://mlsanity.com/paper/2412.14480/) (2024)
- [Towards a Unified Understanding of Robot Manipulation: A Comprehensive Survey](https://mlsanity.com/paper/2510.10903/) (2025)
- [nvblox: GPU-Accelerated Incremental Signed Distance Field Mapping](https://mlsanity.com/paper/2311.00626/) (2023)
- [A Survey of Robotic Language Grounding: Tradeoffs between Symbols and Embeddings](https://mlsanity.com/paper/2405.13245/) (2024)
- [How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf](https://mlsanity.com/paper/2602.18397/) (2026)
- [cuVSLAM: CUDA accelerated visual odometry and mapping](https://mlsanity.com/paper/2506.04359/) (2025)
- [Distributed AI Platform for the 6G RAN](https://mlsanity.com/paper/2410.03747/) (2024)
- [Benchmarking local motion planners for navigation of mobile manipulators](https://mlsanity.com/paper/2211.01812/) (2022)

## Built on by (most cited first, 2 of 2)

- [Efficient Vision-Language-Action Management and Serving for Robot Factories](https://mlsanity.com/paper/2609.12075/) (2026)
- [VLA-ULAP: Interleaving Cloud VLA Calls with Ultra-Lightweight Local Action Prediction at the Edge](https://mlsanity.com/paper/2609.18663/) (2026)

## Abstract (arXiv)

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.