Model and implementation of an anthropomorphic system for sensory-motor perception

A general framework of artificial perception for personal robots is proposed, and a subset of the framework, devoted to the face problem of robotic grasping and manipulation, is implemented. A series of experiments has been carried out using an anthropomorphic approach, both in the sensory system and in the processing modules. In particular planning of the pre-grasping hand shaping, learning of motor co-ordination strategies, exploration and grasping of an object and object classification based on the visuo-tactile information perceived during the exploration phase are described. Experiments indicate that the proposed framework may lead to practical results towards the implementation of "humanoid" robots.