부산대학교 도서관

This paper proposes a local path planning method that utilizes the distance-type fuzzy reasoning method for the navigation of mobile robots in unstructured and dynamic environments. By using a distance-based fuzzy reasoning method: (i) both non-sparse and sparse input fuzzy sets representing sensor readings can be properly processed; (ii) benefiting from the modus ponens, when the input exactly matches one of the rules in the fuzzy rule base, the reasoning result is guaranteed to be the same as the consequent of that rule. Furthermore, we propose a behavioral controller that adopts the reasoning results to achieve efficient and safe local path planning. The presented approach has been evaluated by extensive experiments with our newly developed material transportation robots in real construction sites.