An Incremental Behavior Learning Using Constraint Rules Extraction Mechanism for Autonomous Mobile Robots
Toshiyuki Kondo, Norihiko ITOH, Koji Ito · Transactions of the Society of Instrument and Control Engineers · 2004
In the last decade, a number of skillful robots have been developed. However most of them can so far only demonstrate pre-programmed motions according to the external stimuli. In contrast, humans can learn new motions such as catching a ball in spite of his/her high dimensional sensorimotor DOF. In the learning process, it can be hypothesized that the learner actively constrains the DOF by him/her-self using learning skills, in this paper referred to as “schema”. In this study, a learning method for autonomous mobile robots operating in unknown environments is proposed, where not only a behavior learning mechanism for sensorimotor mappings but also an extraction/re-use mechanism of the schema (i.e. constraint rules for behavior learning) are implemented. Through the results of simulations and real experiments of mobile robot navigation, the validity of the proposed method is clarified.