Broad learning system-based fixed-time control for a robot with input saturation and output constraint

Purpose This paper presents an adaptive neural network-based fixed-time controller aimed at addressing the challenges of input saturation and output constraints in robotic systems. The purpose of this paper is to enhance the transient response and overall stability of the robot under these conditions. Design/methodology/approach An adaptive fixed-time control strategy is proposed, using barrier Lyapunov functions (BLFs) to handle output constraints. The control law symmetrically converts the asymmetric saturation function through a hyperbolic tangent transformation. In addition, the broad learning system (BLS) is integrated into the adaptive neural network framework to improve robustness and manage system uncertainties. The stability of the proposed controller is analyzed using Lyapunov stability theory, ensuring fixed-time stability with convergence independent of initial conditions. Findings This paper presents an adaptive fixed-time control method for robotic systems with input saturation and time-varying output constraints. By using BLFs and an improved radial basis function neural network based on the BLS architecture, the proposed method ensures fixed-time stability, independent of the robot’s initial state. The approach effectively transforms asymmetric input saturation into a symmetric form, enhancing control performance. Simulations and experiments demonstrate that the controller maintains tracking accuracy within output constraints while mitigating the effects of input saturation, ensuring robust performance in complex environments. Research limitations/implications Although the proposed approach addresses the primary constraints of the system, further research is needed to explore its application in more complex multi-robot environments and under varying real-world disturbances. Practical implications The proposed controller can be implemented in robotic systems facing strict input and output limitations, providing a reliable solution for improving stability and response time in constrained environments. Social implications The findings of this study have broad implications for the development of advanced robotic systems capable of operating safely and efficiently in real-world environments. The proposed control method enhances the adaptability and reliability of robots in industrial, medical and service sectors by ensuring precise operation under complex constraints. This technology can improve productivity, reduce accidents due to operational limits and optimize the performance of robots in time-sensitive tasks. The method’s computational efficiency also opens possibilities for wider applications in areas such as autonomous systems, manufacturing and health care, where safe, reliable robotic assistance is increasingly essential. Originality/value The proposed method tackles both time-varying output constraints and asymmetric input saturation, making it effective for most robotic systems that face these constraints. This paper integrates BLS with trajectory tracking control of robots. The system is proven to achieve fixed-time stability.