摘要

In this paper, an adaptive NN (neural network) control scheme is proposed for uncertain robot systems to achieve fixed-time convergence. With the proposed fixed-time NN controller, the system uncertainty can be handled during the operation and the system can achieve semiglobal stability within fixed-time regardless of the initial conditions. In addition, the boundedness of the NNs weight estimation can be proved theoretically in our work, rather than being assumed as in some recent fixed-time NN control design. Finally, the superior control performance of the proposed scheme is demonstrated based on simulation and experiment study using a Baxter robot.