a) Team Description Paper
b) Scientific Papers
M. Tominaga, Y. Takemura, and K. Ishii, “Modeling and Predicting Human Actions in Soccer Using Tensor-SOM,” Applied Sciences, vol. 15, no. 9, p. 5088, May 2025.
Abstract: As robots become increasingly integrated into society, a future in which humans and robots collaborate is expected. In such a cooperative society, robots must possess the ability to predict human behavior. This study investigates a human–robot cooperation system using RoboCup soccer as a testbed, where a robot observes human actions, infers their intentions, and determines its own actions accordingly. Such problems have typically been addressed within the framework of multi-agent systems, where the entity performing an action is referred to as an ‘agent’, and multiple agents cooperate to complete a task. However, a system capable of performing cooperative actions in an environment where both humans and robots coexist has yet to be fully developed. This study proposes an action decision system based on self-organizing maps (SOM), a widely used unsupervised learning model, and evaluates its effectiveness in promoting cooperative play within human teams. Specifically, we analyze futsal game data, where the agents are professional futsal players, as a test case for the multi-agent system. To this end, we employ Tensor-SOM, an extension of SOM that can handle multi-relational datasets. The system learns from this data to determine the optimal movement speeds in x and y directions for each agent’s position. The results demonstrate that the proposed system successfully determines optimal movement speeds, suggesting its potential for integrating robots into human team coordination.
M. Tominaga, A. Tominaga, Y. Takemura, and K. Ishii, “Proposal of a Method for Acquiring Characteristics of Large-Diameter Solenoids,” in RoboCup 2024: Robot World Cup XXVII, vol. 15570, Lecture Notes in Computer Science, vol. 15570, pp. 200–211, Apr. 2025.
Abstract: The solenoids used in the RoboCup soccer middle-sized league are large-diameter push solenoids, which are not widely available in the market as a product. Therefore, the relationship between input and output can only be obtained through experiments by researchers who have manufactured the solenoids. Until now, simulations have been performed using FEM and other methods, but it was not possible to analyze the actual plunger motion. In this study, the motion of a plunger is observed using an actual solenoid, and the input-output relationship is clarified. This will allow us to clarify the equation relating ball flight distance and self-inductance as an actual ball ejection device. This research can be utilized not only for Robocup but also for the injection mechanism of Elide Fire Ball and inexpensive and compact ball ejector.
M. Tominaga, “The 27th RoboCup International Symposium 2024,” Jan. 01, 2025, The Japanese Society for Artificial Intelligence: 1.
Abstract: The 27th RoboCup International Symposium was held on July 22, 2024, in Eindhoven, Netherlands, to advance the project’s mission of defeating human soccer champions by 2050. The program featured 9 oral and 25 poster presentations across diverse domains, including soccer, rescue, and domestic service robotics. Keynote addresses explored AI-driven suitcase navigation for the visually impaired and decision-making strategies for autonomous agents. Technical contributions highlighted event-based vision for dynamic environments, digital twin-based semantic path planning, and Quantized Neural Networks (QNN) specifically optimized for Intel Atom processors in NAO robots. Best Paper honors were awarded to research on whistle event estimation. The symposium successfully facilitated international collaboration and scientific exchange among researchers.
M. Tominaga, Y. Takemura, and K. Ishii, “Behavior Learning System for Robot Soccer Using Neural Network,” JRM, vol. 35, no. 5, pp. 1385–1392, Oct. 2023.
Abstruct: With technological developments, the prospect of a human-robot symbiotic society has emerged. A soccer game has characteristics similar to those expected in such a society. Soccer is a multiagent game in which the strategy employed depends on each agent’s position and actions. This paper discusses the results of the development of a learning system that uses a self-organizing map to select behaviors depending on the scenario (two-dimensional absolute coordinates of the agent, other agents, and the ball). The system can reproduce the action-selection algorithms of all the players on a certain team, and the robot can instantly select the next cooperative action from information obtained during the game. Thus, common-sense rules can be shared to learn an action-selection algorithm for a set of both human and robot agents.
M. Tominaga, J. Ahn, Y. Takemura, and K. Ishii, “Inter-University Collaboration Aimed at Integrating Different Robotic Field: Development of Underwater Robots and Soccer Robots Though these Competitions,” Proceedings of International Conference on Artificial Life and Robotics, vol. 27, pp. 365–368, Jan. 2022.
Abstruct: In robotics, the problems and solutions to be focused on may differ due to the different fields of robots to be developed. In this research, we will verify the effect of exchanging opinions and sharing knowledge by collaborating withstudents aiming to participate in different robot competitions between underwater robots and soccer robots. As a result of analysis using neural networks, it was found that collaborative research between universities contributes to maintaining student motivation.
c) Results and Awards
- 2024
- RoboCup 2025: Soccer Competition 7th place
- RoboCup 2025 : Technical Challenge 8th place
- RoboCup 2025: Scientific Challenge 4th place
- RoboCup 2025 : Ambition Challenge 3rd place
- RoboCup Japan Open: Soccer Competition 2nd place
- RoboCup Japan Open: Technical Challenge 1st place
- 2023
- RoboCup Asia-Pacific Tianjin Invitational Tournament: Soccer Competition 2nd place
- 2021
- RoboCup Asia-Pacific : Video Challenge 1st place
- RoboCup Asia-Pacific : Technical Challenge 1st place
- RoboCup Asia-Pacific JSAI Award
- World Championship Online: Technical Challenge 7th place
- World Championship Online: Scientific Challenge 6th place
d) Video
Video showing the capabilities of our robots(youtube)
e) Contributions of the RoboCup MSLCommunity
- 2025
- RoboCup WorldCup MSL Technical Committee Member: Moeko Tominaga
- 2024
- RoboCup WorldCup MSL Technical Committee Member: Moeko Tominaga
- 2023
- RoboCup WorldCup MSL Organizing Committee Member: Moeko Tominaga
- 2022
- RoboCup WorldCup MSL Organizing Committee Member: Moeko Tominaga
- 2021
- RoboCup WorldCup MSL Organizing Committee Member: Moeko Tominaga
- RoboCup Asia-Pacific MSL Organizing Committee Local Chair: Yasunori Takemura
- RoboCup Asia-Pacific MSL Organizing Committee Member: Moeko Tominaga
f) Declaration of a Mixed Team
Our team will not join the mixed team.
g) Mechanical and Electrical Description together with a Software Flow Chart
Mechanical and electrical description of the robot and software flow chart
Kyushu institute of Technology has the intellectual property right. So, we can not open our sourse code freely. But we will try to share the infomation with MSL members.
g) MAC Addresses
Hidden
h) The Size and Weight of Each Robot
500x500x800[mm]