Neural-network-based Fuzzy Logic Tracking Control of Mobile Robots

In this paper, a novel hybrid biologically inspired neural network based fuzzy logic tracking control method to real-time navigation of a nonholonomic mobile robot is proposed by combining a fuzzy logic technique and a biologically inspired neural network model. The tracking control algorithm is derived from the error dynamics analysis of the mobile robot and the stability analysis of the closed-loop control system. The stability of the robot control system and the convergence of tracking errors to zeros are guaranteed by a Lyapunov stability theory. Unlike some existing tracking control approaches for mobile robots whose control velocities have velocity jumps, the proposed neurodynamics-based approach is capable of generating smooth continuous robot control signals with zero initial velocities. Moreover, the issue of large tracking error is resolved by the proposed fuzzy logic and biologically inspired neural network method. The effectiveness, robustness, and efficiency of the proposed neurodynamics-based fuzzy tracking control of mobile robots are demonstrated by simulation and comparison studies. The simulation studies are performed on the ROS environment. The effectiveness of the proposed control scheme have been validated by both simulations and experiments.