作者: Michel Lopez-Franco , Edgar N. Sanchez , Alma Y. Alanis , Carlos Lopez-Franco , Nancy Arana-Daniel
DOI: 10.1016/J.NEUCOM.2015.06.012
关键词:
摘要: This paper proposes a decentralized control for stabilization of nonlinear multi-agent systems using neural inverse optimal control. approach consists in synthesizing suitable controller each agent; accordingly, local subsystem is approximated by an identifier discrete-time recurrent high order network (RHONN), trained with extended Kalman filter (EKF) algorithm. The scheme used to model uncertain subsystem, and based on this the knowledge Lyapunov function, then synthesized avoid solving Hamilton Jacobi Bellman (HJB) equation.