Model Predictive Neural Control for Aggressive Helicopter Maneuvers

this paper we consider general multi-input-multi-output (MIMO) nonlinear systems with tracking error costs of the form L k ## k ; # k ### k ## k # # k ## k ### k (10.2) where # k # # k # # k , with corresponding to a desired reference state trajectory. The last term assesses a penalty for exceeding control saturation level # , where each element (j # #;:::;m) of the vector k is defined as u k j # # # #,if #u k j ##u j u k j # u j sign#u k j #, otherwise