A fuzzy approach to collision avoidance for automated guided vehicle (AGV) navigation has been proposed in our earlier work. By fuzzy inference, an AGV was guided from the starting point toward the target without colliding with any static obstacle as well as moving obstacle. In the present study, emphasis is on some difficult issues concerning AGV navigation, including sensor modeling and trap recovering. In sensor modeling, we wish to find the minimum number of sensors and their optimal arrangement on an AGV, so that the views of all angles can be seen by the AGV. In trap recovering, fuzzy logic and crisp reasoning are combined to guide an AGV to get out of a trap. Moreover, the AGV's ability to avoid collision with unknown moving obstacles is improved in the study. Simulation results are presented to show the feasibility of the proposed approach.
Relation:
Fuzzy Logic for the Applications to Complex Systems
