Accurate trajectory tracking control with adaptive neural networks for omnidirectional mobile robots subject to unmodeled dynamics

Abstract Omnidirectional mobile robots have gained a lot of attention in recent years due to their maneuverability capabilities. However, ensuring accurate trajectory tracking with this class is still challenging control system designers. In work, novel intelligent controller introduced for omnidirectional subject unstructured uncertainties. An adaptive neural network adopted within Lyapunov-based nonlinear scheme deal frictional forces and other unmodeled dynamics or external disturbances that may occur. Online learning, rather than supervised offline training, employed allow the robot learn on its own how compensate uncertainties by interacting environment. The adoption combined error signal as single input significantly reduces computational complexity disturbance compensation enables resulting be implemented embedded hardware robots. boundedness convergence properties proposed are proved means Lyapunov-like stability analysis. effectiveness numerically evaluated experimentally validated using an robot. comparative analyses obtained results show based networks allows reductions more $$95\%$$ 95 % error, thus guaranteeing confirming great superiority strategy.