Image processing based obstacle avoidance control for mobile robot by recurrent fuzzy neural network

The e-puck (TM) mobile robot is used and an intelligent obstacle avoidance algorithm is developed in this paper. The image data are processed by edge detection method. By using the recurrent fuzzy neural network (RFNN), the horizontal edge (HE) and vertical edge (VE) are feed into RFNN to train the control rules such as to control the right and left wheels of e-puck robot to avoid obstacles. The good control performances and effectiveness are demonstrated by the simulations of Matlab (TM) and Webots (TM); meanwhile, the empirical tests are also implemented to verify these performances.