Adaptive RBFNN-Based Fast Fixed-Time Backstepping Control for Robotic Manipulators

This article explores the time-varying trajectory tracking control for robotic manipulators with uncertainties. Initially, we propose a novel fixed-time backstepping control algorithm. This innovation allows the system to achieve fixed-time convergence more rapidly. Considering that the manipulator system are affected by disturbance and model uncertainty, we adopt an adaptive radial basis function neural network (RBFNN) to compensate for the lumped disturbance. The effectiveness of the proposed algorithm is verified by simulation. Compared to existing methods, this approach shows a more rapid convergence rate and superior convergence performance.