Target set reachability criteria for dynamical systems described by inaccurate models

S is taken to be a dynamical system (described by Banach space operators) whose outputy we wish to regulate. The structural complexity ofS (nonlinearities, distributed parameters, etc.) forces us to design a controller forS using an approximate modelM ofS. A convex error bound ? describes the accuracy of the approximation ofS byM. For a prescribed target setY _t , we considered the problem of driving the output ofS toY _t subject to worst possible error excursions betweenM andS. The notion of areconstructed support function is instrumental to the derivation of the main result, Theorem 6.1, which we can paraphrase as follows. IfM is linear (S need not be), then we can describe a finite-dimensional convex programming Problem (P), whose solution tells us whether or notY _t is reachable. Theorem 6.1 is then specialized to differential systems approximated in the norm. The computation of numerical solutions is also discussed.