Dates: September 16-20, 2024 

Venue: Dubrovnik, Croatia - University of Zagreb - Centre for Advanced Academic Studies (CAAS)

The Horizon Europe twinning project AIoTwin organised its second summer school on the intersection of Internet of Things (IoT) and Artificial Intelligence (AI) in the enchanting city of Dubrovnik, Croatia. The event took place at the Centre for Advanced Academic Studies (CAAS) of the University of Zagreb, which offers a stunning view of Dubrovnik's Old Town's famous City Walls and Lovrijenac Fortress.

The event was organized in collaboration with the EU funded SmartEdge project. The summer school program included invited talks, technical tutorials, hands-on sessions with advanced hardware, poster sessions showcasing the latest research, and other insightful presentations and discussions. In addition, the program included a technical workshop on “Edge AI meets Swarm Intelligence“, featuring insightful presentations and discussions on cutting-edge research.

Programme Summary

On the first day of the AIoTwin Summer School, the program began with an opening ceremony, followed by a keynote from Aaron Ding (TU Delft) on sustainable and trustworthy edge AI for future computing. A skills tutorial on doctoral education at KTH was delivered by Sarunas Girdzijauskas (RISE), followed by Boris Sedlak (TU Vienna) who presented a tutorial on operating distributed computing continuum systems through active inference. In the afternoon, Lodovico Giaretta (RISE) discussed privacy-preserving computation techniques for edge AI, and the day concluded with hands-on training on the AIoTwin orchestration middleware, the open-source solution enabling edge orchestration of hierarchical Federated Learning workflows developed by researchers from UNIZG-FER and TU Vienna.

On the second day, the day began with two keynotes: Stefan Nastic (TUW) presented computing paradigms for next-generation landscapes of edge environments, and Spyros Lalis (University of Thessaly) focused on drones as first-class citizens in the cloud-edge-IoT continuum. After, Anh Le Tuan and Xuanchi Guo (TUB) led a tutorial on in-network programming with practical examples of P4. The afternoon included a skills tutorial on guidelines for starups delivered by Ivan Voras (Equinox Vision) and concluded with hands-on training on ColonyOS, an event-driven meta-operating system spanning edge and cloud environments, by Johan Kristiansson (RISE), before the official closing of this part of the AIoTwin Summer School.

On the third day, the joint sessions of the project SmartEdge and AIoTwin took place. The day began with a keynote from Carla Ferreira (NOVA University Lisbon) about the techniques for safe and highly available cloud applications. Next, poster sessions and paper presentations took place, creating a vibrant hub of discussion and idea exchange.

On the fourth and fifth day, the SmartEdge project organised two keynote lectures by Philippe Cudre-Mauroux (University of Fribourg) and Trung Kien Tran (Bosch) as well as a series of tutorials on edge AI amd swarm technologies developed for the following use cases: Automotive, Manufacturing and Health.

Programme Overview

🔹 16-17 September – AIoTwin Summer School: Keynote talks, Tutorials, Hands-on sessions
🔹 18 September – Joint Sessions SmartEdge & AIoTwin:
      Technical Workshop on “Edge AI meets Swarm Intelligence”, Poster session, SmartEdge open-door demonstration
🔹 19-20 September – SmartEdge Summer School: Keynote talks, Hands-on sessions

The detailed programme can be found here and a short description of all tutorials, keynote talks, hands on sessions with presentations is available here:

• Keynote talks
• Tutorials
• Hands-on Workshops

Outcomes of the Summer School 

The AIoTwin Summer School successfully achieved its objectives, including:

• Providing participants with a comprehensive understanding of the latest advancements in edge AI, edge computing for IoT environemnts, and privacy-preserving techniques.
• Promoting collaboration and networking between academia and industry professionals through interactive sessions.
• Creating the opportunity for researchers and attendees to network, share insights, and explore potential collaborations.
• Equipping participants with practical skills via hands-on training on AIoTwin orchestration middleware and ColonyOS.
• Inspiring further research and development in AIoTwin-related areas.

Conclusion 

The AIoTwin Summer School successfully built on last year’s event, introducing a new event - a joint technical workshop with the SmartEdge project on “Edge AI meets Swarm Intelligence,” which fostered discussions and exchanges of ideas on practicla use cases for edge AI.

The AIoTwin consortium looks forward to the next edition of the Summer School to further advance research and innovation in AIoT, continuing to strengthen the collaboration among academia and industry in this evolving field.