Toward Enabling Automated Cognition and Decision-Making in Complex Cyber-Physical Systems
Paul Bogdan, Massoud Pedram · 2018
This article presents a framework for empowering automated cognition and decision making in complex cyber-physical systems (CPS). The key idea is for each cyber-physical component in the system to be able to construct from observations and actions a reduced model of its behavior and respond to external stimuli in the form of a (timed) probabilistic automaton such as a semi-Markov decision process. The reduced order behavioral models of various cyber-physical components can then be integrated into an optimization and decision-making module to determine the best actions for the components under different operating scenarios and cost/payoff functions by solving a bounded-rationality global decision-making problem.