Recently, human-friendly robots are expected to support human daily life at home, office, medical treatment and welfare scene with rapid development of declining children population and increasing aging community. Our research addresses to develop the guide robot that can be used in hospitals, welfare facilities, and etc. In order to achieve the same performance as human guidance on a robot, it is necessary to extract human's guidance knowledge. In this paper, firstly, the advanced guidance knowledge is formulated using production rules based on linguistic variables. Secondly, the trajectory planning of guide robot is implemented by the quantified knowledge and Distance-Type Fuzzy Reasoning method. The Distance-Type Fuzzy Reasoning method is a fuzzy reasoning method by considering the distance value between two fuzzy sets, and is effective even when the common set between an antecedent and a fact is an empty set. Finally, the effectiveness of the proposed trajectory planning method is illuminated by the experiment of guidance considering relative distance and speed to person.
