# Network Offloading Policies for Cloud Robotics: a Learning-based Approach

arXiv: https://arxiv.org/abs/1902.05703 · HTML: https://mlsanity.com/paper/1902.05703/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Feb 2019.

## Built on by (most cited first, 17 of 17)

- [Semantics for Robotic Mapping, Perception and Interaction: A Survey](https://mlsanity.com/paper/2101.00443/) (2021)
- [Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence](https://mlsanity.com/paper/2105.01798/) (2021)
- [Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-world](https://mlsanity.com/paper/2212.00972/) (2022)
- [Learning to Cascade: Confidence Calibration for Improving the Accuracy and Computational Cost of Cascade Inference Systems](https://mlsanity.com/paper/2104.09286/) (2021)
- [Cloud-Device Collaborative Learning for Multimodal Large Language Models](https://mlsanity.com/paper/2312.16279/) (2023)
- [Federated Imitation Learning: A Privacy Considered Imitation Learning Framework for Cloud Robotic Systems with Heterogeneous Sensor Data](https://mlsanity.com/paper/1909.00895/) (2019)
- [Small-Large Collaboration: Training-efficient Concept Personalization for Large VLM using a Meta Personalized Small VLM](https://mlsanity.com/paper/2508.07260/) (2025)
- [A Reinforcement Learning Approach to Sensing Design in Resource-Constrained Wireless Networked Control Systems](https://mlsanity.com/paper/2204.00703/) (2022)
- [Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization](https://mlsanity.com/paper/2608.00569/) (2026)
- [Federated Reinforcement Learning at the Edge](https://mlsanity.com/paper/2112.05908/) (2021)
- [To Compute or not to Compute? Adaptive Smart Sensing in Resource-Constrained Edge Computing](https://mlsanity.com/paper/2209.02166/) (2022)
- [Data Games: A Game-Theoretic Approach to Swarm Robotic Data Collection](https://mlsanity.com/paper/2303.03602/) (2023)
- [Sim-Anchored Learning for On-the-Fly Adaptation](https://mlsanity.com/paper/2301.06987/) (2023)
- [Mobility-Aware Computation Offloading for Swarm Robotics using Deep Reinforcement Learning](https://mlsanity.com/paper/2308.11154/) (2023)
- [Distributed No-Regret Learning for Multi-Stage Systems with End-to-End Bandit Feedback](https://mlsanity.com/paper/2404.04509/) (2024)
- [vAccSOL: Efficient and Transparent AI Vision Offloading for Mobile Robots](https://mlsanity.com/paper/2603.16685/) (2026)
- [RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution](https://mlsanity.com/paper/2608.15924/) (2026)

## Abstract (arXiv)

Today's robotic systems are increasingly turning to computationally expensive models such as deep neural networks (DNNs) for tasks like localization, perception, planning, and object detection. However, resource-constrained robots, like low-power drones, often have insufficient on-board compute resources or power reserves to scalably run the most accurate, state-of-the art neural network compute models. Cloud robotics allows mobile robots the benefit of offloading compute to centralized servers if they are uncertain locally or want to run more accurate, compute-intensive models. However, cloud robotics comes with a key, often understated cost: communicating with the cloud over congested wireless networks may result in latency or loss of data. In fact, sending high data-rate video or LIDAR from multiple robots over congested networks can lead to prohibitive delay for real-time applications, which we measure experimentally. In this paper, we formulate a novel Robot Offloading Problem --- how and when should robots offload sensing tasks, especially if they are uncertain, to improve accuracy while minimizing the cost of cloud communication? We formulate offloading as a sequential decision making problem for robots, and propose a solution using deep reinforcement learning. In both simulations and hardware experiments using state-of-the art vision DNNs, our offloading strategy improves vision task performance by between 1.3-2.6x of benchmark offloading strategies, allowing robots the potential to significantly transcend their on-board sensing accuracy but with limited cost of cloud communication.