Event Summer School on Autonomous Systems

Programme

Upon completion of the Summer School, participants will have been exposed to the latest research on autonomous systems and will be able to position their work within the broader ATLAS research framework from a system-level perspective and design high-level architectures of embodied autonomous systems. They will be trained to integrate sensing, perception, decision-making, and actuation within coherent AI-driven autonomous system architectures, and to apply distributed and federated learning approaches in networked and decentralized autonomous systems. Participants will also be able to consider safety constraints and explainability principles into system architectures, formulate cross-domain research concepts spanning Land, Air, and Space, and critically assess simulation-to-real gaps and validation strategies for physical AI systems.

    Venue

    Plan your visit

    Overview

    Each day of the Summer School is dedicated to a key theme, with embodied intelligence running as a common thread throughout:

    • Day 1 explores the compute infrastructure and embodied AI architecture for autonomous systems,
    • Day 2 dives into data-driven and distributed intelligence,
    • Day 3 focuses on safety, validation, and integrating autonomous systems.

    The programme blends expert lectures, academic keynotes, hands-on cross-domain workshops, interactive research sessions, and an industry panel, highlighting real-world challenges and opportunities. The participants will also have the opportunity to present their research work during a poster session on the second day. A jury will evaluate the the different contributions and propose an award for the best poster presentation. The afternoon of the final day will be dedicated to a visit to the historic Belval siderurgical site. See below for more details on the programme.

    08:00-09:00Registration & Coffee
    09:00-09:15Opening Session: ATLAS Ecosystem [Prof. Raphael Frank, University of Luxembourg]
    It offers a comprehensive overview of autonomous systems within the ATLAS ecosystem, presenting the scope of research across Land, Air, and Space domains. It highlights the key challenges, opportunities, and interdisciplinary connections in the development of intelligent, safe, and physical autonomous systems, setting the stage for the themes explored throughout the Summer School.
    09:15-10:30Opening Keynote: Resilient Edge-AI using Virtualized Edge Computing [Prof. Dr. Falko Dressler, TU Berlin]
    This lecture covers the evolution of edge computing in the transition from 5G to 6G, highlighting its role in supporting data-intensive, ML-driven services. It introduces the Virtual Edge (V-Edge) concept, which unifies cloud, edge, and user resources into a flexible and cooperative computing framework. The lecture also explores resilience strategies, including the use of mobile systems to maintain connectivity during infrastructure failures.
    10:30-11:00Coffee Break
    11:00-12:30Lecture: Embodied AI Architectures for Autonomous Systems [TBD]
    The lecture on embodied AI and closed-loop architectures will introduce the core principles of physical AI for autonomous systems, emphasizing how intelligence emerges from the interaction between sensing, actuation, and physical dynamics. It will cover perception-action loops, dynamics-aware and model-based learning, physics-informed AI agents, and the challenges of transferring models from simulation to real-world autonomous systems.
    12:30-14:00Lunch Break
    14:00-16:00Workshop: Advanced Mapping and Scene Reconstruction [TBD]
    This session focuses on advanced environment mapping and real-time scene reconstruction using 3D Gaussian Splatting (3DGS) for autonomous systems such as vehicles, drones, and robots. It explores how a unified Gaussian-based representation enables efficient, high-fidelity mapping and continuous scene updates from sensor data. The session includes a hands-on workshop where participants implement a complete 3DGS pipeline from data capture to reconstruction and visualization in real-world scenarios.
    16:00-16:30Coffee Break
    16:30-17:30 Expert Panel Discussion
    From Prototype to Deployment: Scaling Safe Autonomous Systems in the Real World

    Participants:
    – Prof. Dr. Falko Dressler (TU Berlin, Germany)
    – Christophe Timmermans (CEO SolarCleano, Luxembourg)
    – Joost Ortjens (Director EMEA at Ohmio, Luxembourg)
    – Jean Schiltz (Director Automotive and Smart Mobility at the Ministry of the Economy, Luxembourg)

    Moderator:
    – Prof. Dr. Raphael Frank (SnT / University of Luxembourg)
    17:30-20:00End-of-Day Welcome & Networking Drink

    08:30-09:00Arrival & Networking
    09:00-10:30Lecture: Distributed and Federated Learnng for Autonomous Systems [Prof. Grégoire DANOY, University of Luxembourg]
    This session introduces distributed and federated learning principles for physical autonomous systems, covering collective optimization, swarm intelligence, and privacy-aware learning. Participants will see how these methods enable coordinated intelligence across networked systems, from UAV fleets to multi-agent robotic platforms, including autonomous vehicles.
    10:30-11:00Coffee Break
    11:00-12:30Lecture: Multi-modal Perception for Autonomous Systems [TBD]
    The lecture presents perception as a foundational element of embodied AI, emphasizing multi-modal sensor fusion, active perception, and scene representations and understanding. Participants learn how physically consistent state representations enable robust decision-making in dynamic, real-world environments.
    12:30-14:00Lunch Break
    14:00-16:30Workshop: Building World Models for Embodied Agents [TBD]
    This session explores world models and latent representations in physical AI for modeling environments and agent dynamics. It covers 3D/4D scene modeling, data-driven dynamics, and links between sensing and state representation. Then, participants work in groups to build latent world models with applications.
    16:30-17:00Coffee Break
    17:00-18:30 PhD Students Poster Session
    Doctoral participants present challenges from their thesis work receiving expert feedback to strengthen methodological rigor and cross-domain applicability.
    18:30-22:00Social Event and Best Poster Award

    08:30-09:00Morning Coffee
    09:00-10:30Lecture: Foundations of Trustworthy AI in Physical Systems [Prof. Fabrizio PASTORE, University of Luxembourg]
    This lecture introduces the core principles of trustworthy AI in embodied autonomous systems, including robustness, reliability, accountability, and human oversight. It emphasizes embedding trustworthiness directly into the perception–decision–actuation loop. The session frames trust as a system-level design requirement for safety-critical autonomy.
    10:30-11:00Coffee Break
    11:00-12:30Lecture: Safety, Security and Explainability in Embodied AI [Dr. Safaa MOALLIM, University of Luxembourg]
    This session explores how safety, cybersecurity, and explainability are implemented in AI-driven physical systems. Topics include formal safety layers, runtime monitoring, adversarial robustness, and interpretable decision-making. The focus is on co-designing learning components with verifiable safety and certification pathways.
    12:30-14:00Lunch Break
    14:00-16:00 Visit to the historic Belval siderurgical site