Parametrization of completeness in symbolic abstraction of bounded input linear systems

Abstract

A good state-time quantized symbolic abstraction of an already input quantized control system would satisfy three conditions: proximity, soundness and completeness. Extant approaches for symbolic abstraction of unstable systems limit to satisfying proximity and soundness but not completeness. Instability of systems is an impediment to constructing fully complete state-time quantized symbolic models for bounded and quantized input unstable systems, even using supervisory feedback. Therefore, in this paper we come up with a way of parametrization of completeness of the symbolic model through the quintessential notion of Trimmed-Input Approximate Bisimulation which is introduced in the paper. The amount of completeness is specified by a parameter called trimming of the set of input trajectories. We subsequently discuss a procedure of constructing state-time quantized symbolic models which are near-complete in addition to being sound and proximate with respect to the time quantized models.