Adaptive neural network fixed‐time control for an uncertain robot with input nonlinearity

Abstract

The article introduces an innovative adaptive fixed‐time control strategy designed for a robot system grappling with challenges like actuator saturation and model uncertainty. Two strategies are explored: model‐based control and neural networks control. In instances of model uncertainty, neural networks are leveraged to contend with the unknown dynamics of the robot system. These networks undergo training to approximate the elusive model parameters. Through this neural network approach, we establish adaptive laws grounded in fixed‐time convergence, ensuring that system tracking errors converge to a confined range near zero within a predetermined time frame. To tackle the issue of actuator saturation, an enhanced auxiliary system is introduced. This auxiliary system is tailored to counterbalance the adverse impacts of actuator saturation, thereby augmenting the tracking performance of the robot system. The proposed control policy is rigorously analyzed using Lyapunov theory, demonstrating that the system's tracking errors converge within a fixed time frame. To validate the efficacy of the proposed methodology, both numerical simulations and practical experiments are conducted, affirming the effectiveness of the approach.