Cooperative multiagent robotic systems
Artificial intelligence and mobile robots
Artificial Intelligence - Special issue on Robocop: the first step
The Spirit of Bolivia: Complex Behavior Through Minimal Control
RoboCup-97: Robot Soccer World Cup I
Big Red: The Cornell Small League Robot Soccer Team
RoboCup-99: Robot Soccer World Cup III
Using Decision Tree Confidence Factors for Multiagent Control
RoboCup-97: Robot Soccer World Cup I
Hi-index | 0.00 |
Robot soccer is a challenging research domain, which involves multiple agents (physical robots or "softbots") to work together in a dynamic, noisy, cooperative and adversarial environment to achieve specific objectives. The paper focuses on the design and implementation of an effective system for developing a small-size physical soccer team for the competition of RoboCup. There are three goals preset in our research, that is, robust individual behaviors, controllable cooperation and behavioral learning. The system is therefore required to collect data in real-time situations and repeat experiments accurately, which are found difficult to be achieved in pure physical or simulated case. A distinct feature of our system is that it is a close combination of three functional parts: physical test platform, simulation platform and measurement platform, which support each other to overcome many defects inherent in traditional physical system or simulation system.