THE DEVELOPMENT OF AN ARTIFICIAL INTELIGENT FOR SMART MOBILE ROBOT USING SCHEMA EXTRACTION MECHANISM

Abstract

Abstract: Recently, a number of skillful robots have been developed. One of them can walk and move upstairs just like human beings. However it can so far only demonstrate preprogrammed motions according to the external commands. Therefore an autonomous adaptation ability has been highly anticipated. Meanwhile, humans can learn new motions such as catching or kicking a ball, in spite of their high dimensional sensorimotor degree of freedom. In this learning process, it can be hypothesized that the learner actively constrains the DOF by their self using learning skills, in this paper referred to as schema. In this study, a learning method for smart mobile robots operating in unknown environments is proposed, where not only a learning mechanism for sensorimotor mappings but also an extraction or reuse mechanism of the schemata is implemented. Through the results of simulations and real experiments of smart mobile robot navigation, the validity of the proposed method is clarified.