Modernizing ROS 2 Skills:
Hacking and Orchestrating Cloud Brains,
Physical Sensors, and the Network

  UCL CEGE and ARC Teams

FOSDEM 2026; Track: Robotics and Simulation; Brussels / Saturday 31 January

github-repository:UCL-CyberPhysicalSystems/fosdem2026

open-healthcare-slides

Overview

• Introduction
• UCL Infrastructure
• Demos
• Key Takeaways, Calls to Action and Acknowledgements

Introduction

Modernizing ROS 2 Skills

Notes goes here

🔧 Hacking and Orchestrating Cloud Brains, Physical Sensors, and the Network

Figure 1: Cyber physical systems, cloud layer and participants

Speaker notes go here.

UCL Infrastructure

Orchestrating Cloud Brains, Physical Sensors, and the Network

Notes goes here

🤖 Orchestrating UCL infrastructure

Figure 2: Servers in UCL infrastructure and their network communication

Speaker notes go here.

Demos

Orchestrating Cloud Brains, Physical Sensors, and the Network

Notes goes here

Demos: zenoh-plugin-ros2dds

• ROS2 dockercontainer
• Github Container Registry
• VMs managed with terraform and kubernetes (k8s)

Speaker notes go here.

Key Takeaways, Calls to Action and Acknowledgements

Notes goes here

Key Takeaways & Why This Matters

• Lowering the Barrier to Advanced Robotics at Scale

  • Cloud-ready, cost-aware infrastructure enables hands-on robotics training and research using real sensors, networks, and constraints.

• A Proven, Scalable Model for Collaboration

  • High-performance networking and shared platforms make cross-department and cross-institution collaboration practical and repeatable.

• From Training to Innovation

  • The testbed supports skills transfer, research experimentation, and the rapid development of new robotics workflows.

• Call to Action

  • Partner with us to extend the testbed, through collaboration and funding to scale training, expand research use cases, and deploy models beyond a single institution.

Sciortino et al. 2017 in Computers in Biology and Medicine https://doi.org/10.1016/j.compbiomed.2017.01.008;
He et al. 2021 in Front. Med. https://doi.org/10.3389/fmed.2021.729978

1. Lowering the Barrier to Advanced Robotics
2. A Scalable Model for Cross-Department Collaboration
3. Real Sensors, Real Networks, Real Constraints
4. High-Performance Networking Enables New Workflows
5. Cloud-Ready Robotics Training at Scale
6. Hands-On Learning Accelerates Skills Transfer
7. Cost-Aware, Sustainable Infrastructure Design
8. A Testbed for Research, Training, and Innovation
9. Clear Opportunities for Collaboration & Funding

Acknowledgements

• UCL CEGE: UCL Civil, Environmental and Geomatic Engineering:
  Mickey Li, Chris Bendkowski

• UCL ARC: UCL Advanced Research Computing Centre:
  Mack Nixon, Mahmoud Abdelrazek, Sunny Park, Emily Dubrovska, Yagmur Ozdemir, Marlon Wijeyasinghe, Ruaridh Gollifer, James Legg, Samantha Ahern, Miguel Xochicale, James Hetherington

  • Unified-AI team: Andrew Esterson and Sylvie Ramos
  • Condenser team: Sam Reece and Brian Maher

Notes goes here

Extra slides

Notes goes here

Demos: IsaacSim

Figure 3: IsaacSim IDE with robot simple key control

Speaker notes go here.

Action mechanisms of Embodied AI

Figure 4: Fig 15 from Liu et al. 2025 Neural Brain: A Neuroscience-inspired Framework for Embodied Agents arXiv preprint: 2505.07634

Multimodal Sensing

Figure 5: Fig 11 from Liu et al. 2025 Neural Brain: A Neuroscience-inspired Framework for Embodied Agents arXiv preprint: 2505.07634

Speaker notes go here. Getting started documentation provide with a range of links to setup, use, run and debug application including github workflow.

Miguel Xochicale

Notes goes here for my journey