Adaptive dynamic programming-based feature tracking control of visual servoing manipulators with unknown dynamics

Abstract This paper investigates a feature tracking control method for visual servoing (VS) manipulators adaptive dynamic programming (ADP)-based the unknown dynamics. The major superiority of ADP-based optimal lies in that problem is converted to error with cost function. Moreover, an neural network observer developed approximate entire uncertainties, which are utilized construct improved By establishing critic network, Hamilton–Jacobi–Bellman (HJB) equation solved, and policy derived. closed-loop VS manipulator system verified be ultimately uniformly bounded strategy according Lyapunov theory. Finally, simulation results under various situations demonstrate proposed achieves higher accuracy than other methods, as well satisfies energy requirements.