Digital twins in action : optimizing FuzbAI through simulation and modeling

Bošnak, Matevž (author), Andonovski, Goran (author), Škrjanc, Igor (author)

The FuzbAI system represents a fusion of traditional table football with advanced technology, incorporating computer vision, motion control mechanisms, and artificial intelligence algorithms to provide a new take of the human-machine interaction with the exciting gaming experience. This paper presents a short examination of the FuzbAI system, including its architecture, the development of a digital twin for simulation, and the organization of the FuzbAI competition. Initiated in 2019, the FuzbAI project aimed to attract students to electrical engineering while serving as a platform for testing various AI algorithms. Through the integration of cutting-edge components, FuzbAI offers an immersive gaming experience while preserving the essence of table football. The introduction of a digital twin facilitates rigorous algorithm testing, driving advancements in autonomous gaming. The FuzbAI competition, a showcase of talent and innovation, highlights the potential of AI in gaming. The competition results indicate that sim-to-real approach can be effective tool for simulation-based training and obtaining good performance of AI agents in real-world gaming environments.

• Language: English
• Keywords: digital twin, FuzbAI, automated table football
• Typology: 1.08 - Published Scientific Conference Contribution
• Organization: FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2024
• Number of pages: 7 str.
• PID: 20.500.12556/RUL-169472
• UDC: 681.5
• ISSN on article: 2724-0029
• DOI: 10.46354/i3m.2024.emss.017
• COBISS.SI-ID: 236865283
• Publication date in RUL: 29.05.2025

Record is a part of a proceedings

• Title: Proceedings of the 36th European Modeling & Simulation Symposium, EMSS
• COBISS.SI-ID: 236862467

Record is a part of a journal

• Title: The ...European modeling & simulation symposium
• Shortened title: Eur. modeling simul. symp.
• Publisher: Cal-Tek
• ISSN: 2724-0029
• COBISS.SI-ID: 30562051

Licences

• License: CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
• Link: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Description: The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.

Secondary language

• Language: Slovenian
• Keywords: digitalni dvojček, FuzbAI, avtomatiziran namizni nogomet