Receding-Horizon Control of Constrained Switched Systems with Neural Networks as Parametric Function Approximators

Abstract This work studies receding-horizon control of discrete-time switched linear systems subject to polytopic constraints for the continuous states and inputs. The objective is approximate optimal strategy cases in which online computation intractable due necessity solving mixed-integer quadratic programs each discrete time instant. proposed approach builds upon an approximated finite-horizon law closed-loop form with guaranteed constraint satisfaction. paper derives properties recursive feasibility asymptotic stability approach. A numerical example provided illustration evaluation