Hybrid intelligent models for visual servoing

In this paper, we present two methods of performing eye-to-hand visual servoing using vision and tactile information: direct fuzzy servoing and fuzzy correction. The fuzzy methods are tuned by an adaptive neuro-fuzzy inference system (ANFIS). The set-up is part of a humanoid robot, named COERSU (Jafari and Jarvis, 2003). Experimental results from COERSU are provided to validate these methods. An evolved visual perception system based on genetic algorithms was used to obtain the best possible combination of object segmentation and classification parameters. Some simple methods for scene classification and pose detection were also implemented for intelligent grasping. This paper integrates different concepts to perform hand-eye coordination to produce a working system. The experimental results show that these methods represent a significant improvement in terms of speed and reliability