An adaptive terminal sliding mode control of stone-carving robotic manipulators based on radial basis function neural network.

The stone-carving robotic manipulators (SCRM) find a broad range of applications due to their high efficiency, wide range of processing and strong flexibility. In stone carving process, high response speed and high robustness are required to realize the high precision tracking control of SCRM. This paper proposes an adaptive terminal sliding mode control strategy based on radial basis function neural network (RBFNN-based TSM). First, we deduced the dynamic model of SCRM system with the Lagrange method. Then the dynamic model with uncertainties was further considered, the radial basis function neural network (RBFNN) was employed to approximate the manipulator dynamic model. Finally, in order to improve the response speed and tracking accuracy of SCRM, the RBFNN-based TSM control strategy was designed for SCRM, and the high-gain observer was used to estimate the joint velocity information online. The Lyapunov's theory proved the stability of the algorithm, and the experimental results show that the model-free and chattering-free control was achieved. [ABSTRACT FROM AUTHOR]