Multimodal reasoning for automatic model construction

摘要

This paper describes a program called Pret that au-tomates system identication, the process of nding a dynamical model of a black-box system. Pret per-forms both structural identication and parameter es-timation by integrating several reasoning modes: quali-tative reasoning, qualitative simulation, numerical sim-ulation, geometric reasoning, constraint reasoning, res-olution, reasoning with abstraction levels, declarative meta-level control, and a simple form of truth mainte-nance. Unlike other modeling programs that map structural or functional descriptions to model fragments, Pret com-bines hypotheses about the mathematics involved into candidate models that are intelligently tested against observations about the target system. We give two examples of system identication tasks that this automated modeling tool has successfully per-formed. The rst, a simple linear system, was cho-sen because it facilitates a brief and clear presentation of Pret’s features and reasoning techniques. In the second example, a dicult real-world modeling task, we show how Pret models a radio-controlled car used in the University of British Columbia’s soccer-playing robot project.