Fuzzy target based soft decision for mobile vehicle in dynamic environment

Abstract

This paper addresses the problem of real time flexible operation of a mobile vehicle in dynamic environment which is still a very challenging problem because the surrounding situations are not qualified in static, knowledge is only partial and the execution is often associated with uncertainty. It is difficulty to select appropriate sub-target in real-time to obtain a collision-free and low cost path. A conventional control method usually sets only a best control target beforehand based on the control purpose and object’s characteristics. For many real systems, the situations always change with constraints or disturbances, which result in the necessary to set sub-targets between current state and final target. Thus recalculation of new target is necessary the best target becomes unavailable because of the constraints or disturbances. And the recalculation is costly and involves time lags. Human decisions to act are based on broad targets and respond flexibly in different situations. Responding flexibly to the dynamic environment change like human is considered in this paper. We propose a fuzzy target based intelligent soft decision-making predictive fuzzy controller for differential drive mobile vehicle in dynamic environment to realize autonomous navigation. Simulation in Webots demonstrated the validity and feasibility of our fuzzy target based soft decision controller.