Employing ANFIS for Object Detection in Robo-Pong.

Abstract

This paper presents a vision system for a PingPong player robot, called Robo-Pong. The robot employs color object detection techniques based on fuzzy neural networks in its vision system. In this research a neuro-fuzzy approach is employed to detect and localize objects in robot’s work space and map them in real world coordinates. The architecture is designed to be efficient and also surprisingly fast to work on such a real-time system. Also a mapping system is attached to the object detection one, in order to estimate object locations. To increase the real-time in-field train capabilities of the system some early stopping methods were exploited to deal with such vast train data.