1. Proceedings
  2. I3M
  3. 2024
  4. EMSS
  5. 10.46354/i3m.2024.emss.017

Digital Twins in Action: Optimizing FuzbAI Through Simulation and Modeling

  • a Matevž Bošnak  ,
  • a Goran Andonovski, 
  • a Igor Škrjanc 
  • a Faculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, 1000 Ljubljana, Slovenia
Cite as
Bošnak M., Andonovski G., Škrjanc I. (2024). Digital Twins in Action: Optimizing FuzbAI Through Simulation and Modeling. Proceedings of the 36th European Modeling & Simulation Symposium (EMSS 2024), 017. DOI: https://doi.org/10.46354/i3m.2024.emss.017

Abstract

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.

References

  1. Baratta, A., Cimino, A., Gnoni, M. G., Mirabelli, G., Padovano, A., and Talarico, S. (2023). How cognitive capabilities for smart operator enhance human-robot collaboration. In Proceedings of the 35th European Modeling Simulation Symposium (EMSS 2023), 049., volume2023-September
  2. Bergkvist, M. and Johansson, S. (2003). Machine learning in simulated RoboCup Optimizing the decisions of an Electric Field agent. Master thesis, Blekinge Institute of Technology
  3. Bošnak, M. and Klančar, G. (2020). Fast and Reliable Alternative to Encoder-Based Measurements of Multiple 2-DOF Rotary-Linear Transformable Objects Using a Network of Image Sensors with Application to Table Football. Sensors, 20(12):3552
  4. Coumans, E. (2005). Bullet Physics Engine
  5. De Blasi, S., Klöser, S., Müller, A., Reuben, R., Sturm, F., and Zerrer, T. (2021). KIcker: An Industrial Drive and Control Foosball System automated with Deep Reinforcement Learning. Journal of Intelligent and Robotic Systems: Theory and Applications, 102(1).
  6. Haarnoja, T., Moran, B., Lever, G., Huang, S. H., Tirumala, D., Humplik, J., Wulfmeier, M., Tunyasuvunakool, S., Siegel, N. Y., Hafner, R., Bloesch, M., Hartikainen, K., Byravan, A., Hasenclever, L., Tassa, Y., Sadeghi, F., Batchelor, N., Casarini, F., Saliceti, S., Game, C., Sreendra, N., Patel, K., Gwira, M., Huber, A., Hurley, N., Nori, F., Hadsell, R., and Heess, N. (2024). Learning agile soccer skills for a bipedal robot with deep reinforcement learning. Science Robotics, 9(89):eadi8022.
  7. Janssen, R., De Best, J., Van De Molengraft, R., and Steinbuch, M. (2010). The design of a semi-automated football table. Proceedings of the IEEE International Conference on Control Applications, pages 89–94.
  8. Liu, P., Tateo, D., Bou-Ammar, H., and Peters, J. (2021). Efficient and Reactive Planning for High Speed Robot Air Hockey. IEEE International Conference on Intelligent Robots and Systems, pages 586–593.
  9. Ogawa, M., Shimizu, S., Kadogawa, T., Hashizume, T., Ku-doh, S., Suehiro, T., Sato, Y., and Ikeuchi, K. (2011). Development of Air Hockey Robot improving with the human players - Arm control for effective quick draw taking an opponent-s eye movement into account-. IECON Proceedings (Industrial Electronics Conference), pages3364–3369.
  10. Pepelnjak, L. (2023). Implementation of Table Football in Virtual Reality. Batchelor thesis, University of Ljubljana.
  11. Salvato, E., Fenu, G., Medvet, E., and Pellegrino, F. A. (2021). Crossing the reality gap: A survey on sim-toreal transferability of robot controllers in reinforcement learning. IEEE Access, 9:153171–153187.
  12. Zhang, D. and Nebel, B. (2007). Learning a table soccer robot a new action sequence by observing and imitating. Proceedings of the 3rd Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE 2007, (January 2007):61–66.
  13. Zhao, W., Queralta, J. P., and Westerlund, T. (2020). Simto-Real Transfer in Deep Reinforcement Learning for Robotics: A Survey. 2020 IEEE Symposium Series on Computational Intelligence, SSCI 2020, pages 737–744.