Safety control with preview automaton: poster abstract

Abstract

In this work we consider control problems for discrete-time dynamical systems with safety constraints. As opposed to the existing work on similar problems, we assume that the system at run-time can preview some of the future uncontrolled inputs (e.g., disturbances). In order to develop a control synthesis technique that can leverage such preview information, we introduce a mathematical construct called Preview Automaton that incorporates system dynamics with the prior knowledge on the structure of the preview. We propose an algorithm to find the maximum controlled invariant set for the Preview Automaton. Although Preview Automaton can be equivalently represented by a Finite Transition System, for which existing control synthesis methods can be applied, we show that exploiting the structure of the Preview Automaton results in more efficient solution algorithms. These ideas are demonstrated with a lane-keeping problem, where we show that existence of the preview information allows the vehicle to safely navigate roads with larger curvature, whereas the problem becomes infeasible when no preview information is available.