Extreme learning control of surface vehicles with unknown dynamics and disturbances

In this paper, an extreme learning control (ELC) scheme using the single-hidden layer feedforward network (SLFN) for tracking surface vehicles with unknown dynamics and external disturbances is proposed. A sliding surface is defined by incorporating tracking errors and first derivatives, and unknown dynamics including system uncertainties and external disturbances are capsulated into a lumped nonlinearity which is further identified online by the SLFN approximator with random hidden nodes generated by the ELM technique. As a consequence, the SLFN approximator does not require a priori any information on unknown dynamics, and avoids the curse of dimensionality in predefining hidden nodes of high dimension. Not only tracking accuracy but also approximation ability are enhanced by an adaptive compensator for approximation errors in addition to adaptive output weights of the SLFN, which are derived from the Lyapunov synthesis and contribute to global asymptotic stability in terms of tracking errors and first derivatives of the entire closed-loop system. Simulation results and comparative studies demonstrate that the ELC scheme achieves high accuracy of both tracking and approximation.