Abstract
This paper focuses on adaptive neural control for a class of flexible joint manipulator with unknown dynamics under the output tracking error constraint. To facilitate the design of control law, the constrained tracking error is transformed into unconstrained variable by introducing a performance function, the unknown dynamics of manipulator are accurately approximated by radial basis function(RBF) neural network(NN). Then, a novel adaptive neural control scheme is proposed using the derivative of the filter's output as the input of NN instead of traditional intermediate variables. Due to structure features of the considered flexible joint manipulator, the proposed control scheme not only decreases the dimension of NN inputs, but also reduces the number of NN approximators. Moreover, it can be verified that all the signals in the closed-loop system are uniformly ultimately bounded and the constrained tracking error converges to a small neighborhood around zero with the prescribed performance. Simulation results on a single-link flexible joint manipulator are given to illustrate the effectiveness of the proposed scheme.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call