SVMRobosoc : A Novel Approach Towards Planning Strategy for Robotic Soccer Using Hierarchical Intelligence Systems

Robotic soccer has been an intriguing field of research in artificial intelligence. In this paper we present a novel planning strategy to build a hierarchical intelligence model for two scalable robot teams. This prototype enables the robots to analyze the game states, decide their moves and to take decisions. The system employs the Bayesian-SVM classifier to decide upon subsequent actions and the movement of ball. We have scaled up the robot moves by incorporating the case based reasoning (CBR) for optimized behavior. Simulation results illustrate that SVMRobosoc significantly improves the performance.