Neuro-Fuzzy Controller Design to Navigate Unmanned Vehicle with Construction of Traffic Rules to Avoid Obstacles

Abstract

To navigate an autonomous unmanned vehicle (UV) in an obstacle based trajectory, the fuzzy-neural network is very essential. In this paper, we designed a fuzzy inference system to guide an unmanned vehicle for maintaining traffic rules to reach its goal with avoiding obstacles. The fuzzy inference system which we designed, generates fuzzy if then rules and defines a nonlinear mapping of input data. The input data are initial position, velocity of vehicle and whether there is any obstacle. Input data are simulated and trained by hybrid algorithm. The result controls the navigation of UV and also minimizes error performance to reach the goal.