An intelligent interface processor for a behavior-based control robot

A behaviour-based control is considered as the best approachto control autonomous robots. In the near future, autonomous robots likemobile service robots are expected to assist people in a common environmentsuch as houses or offices. Such situations require natural interactionbetween people and the robots. One way to facilitate this is by using anatural language interface (NLI). Unfortunately the major problem withnatural language is that it is always ambiguous. Up to now, there is noexisting NLI processor that can well solve the ambiguity problems forhuman-robot interface. This paper presents a new methodology for creating anintelligent NLI processor for a mobile service robot that uses abehaviour-based control. The methodology uses a fuzzy approach and historyknowledge. The history knowledge is an innovation in this work.