An ANFIS-based Optimized Fuzzy-multilayer Decision Approach for a Mobile Robotic System in Ever-changing Environment

In robotics, resolution of several difficult issues requires process intelligence. In many applications, the environment of a robot changes with time in a manner that has not been foreseen by its designer. Additionally, information on the environment is commonly inaccurate and incomplete, which is attributed to the restricted sensory activity of sensors. A new online sensor-based motion planning algorithm, which employs a fuzzy multilayer decision controller, is proposed in this study to enhance the quality of the next position in terms of safety and optimality. Fuzzy logic controller (FLC) utilizes the prediction and priority rules of multilayer approach for an effective and intelligent proposed method. Moreover, an adaptive neuro-fuzzy inference system (ANFIS) is designed, which constructs and optimizes an FLC using a given dataset of input/output variables. The ANFIS shortens the high runtime of fuzzy system, optimizes the parameters of the membership functions of inputs and outputs of the fuzzy-multilayer decision controller, and rearranges the rules to enhance the efficiency of the overall approach. The simulation and comparison results indicate the superiority of the proposed path planning algorithm from other well-known algorithms.