Initiated and developed the complete robotic soccer system as a test bed for cooperative robotic research. 

The robot soccer teams developed has won two awards:

1. Second prize (2nd) in FIRA Robot World Cup Beijing 2001
2. Second prize in Singapore Robotic Games 2002.

The robot soccer system consists of 5 bi-wheel type robots with RF receiver, a host computer and RF-transmitters.  The robots receive two parameters (right and left wheel velocities) via the RF-receivers. The host computer uses Visual C++ as its programming platform.  The robot soccer system is associated with cooperation, decision-making, planning, modeling, learning, robot architecture, vision tracking algorithm, sensing, communication, and so forth. In this system each of the robots has its own driving mechanism, communication part and CPU board. The computational part controls the robot’s velocity according to the command data received from the host computer. All calculations on vision data processing, strategies, and position control of the robots are done in the host computer.

Present industrial systems are much complex and multiple mobile robots are increasingly preferred.  Multiple mobile robots are not spatially constrained and performance benefits are manifold. The robots/agents equipped with knowledge, motivations, reasoning and planning capabilities may communicate each other and, share data and information. Cooperation protocol by distributed control; effective communication and fault tolerance while having efficiency of cooperation, adaptation and robustness are some of the research directions associated with multi-robot/agent systems.

The micro-robot soccer platform serves as a test bed to study and research on the issues pertaining to cooperative mobile robots.  A robot team needs to coordinate its actions while competing with another.  The robot soccer system also has an explicit performance measure, the match score. Cooperation, decision making, planning, modeling, learning, robot architecture, vision tracking algorithm, sensing, communication, and so forth are some of the directions of study.

Dynamic path planning based on fuzzy behavior fusion; electrostatic potential field (EPF) and evolutionary artificial potential field (EAPF) are used to plan each individual robot’s path. Hierarchical and fuzzy behavior based strategies are employed to effectively optimizes the objectives. In addition, the robot soccer system is also used as a laboratory experiment to facilitate better understanding for undergraduates in the field of distributed robotic control system.