Cloud Native Robotic Applications with GPU Sharing on Kubernetes
Robotics2022-11-01v2Artificial IntelligenceComputer Vision and Pattern RecognitionDistributed, Parallel, and Cluster ComputingNetworking and Internet Architecture
In this paper we discuss our experience in teaching the Robotic Applications Programming course at ZHAW combining the use of a Kubernetes (k8s) cluster and real, heterogeneous, robotic hardware. We discuss the main advantages of our solutions in terms of seamless simulation-to-real experience for students and the main shortcomings we encountered with networking and sharing GPUs to support deep learning workloads. We describe the current and foreseen alternatives to avoid these drawbacks in future course editions and propose a more cloud-native approach to deploying multiple robotics applications on a k8s cluster.
@article{arxiv.2210.03936,
title = {Cloud Native Robotic Applications with GPU Sharing on Kubernetes},
author = {Giovanni Toffetti and Leonardo Militano and Seán Murphy and Remo Maurer and Mark Straub},
journal= {arXiv preprint arXiv:2210.03936},
year = {2022}
}
Comments
Submission accepted at the IROS'22 Cloud Robotics Workshop