State Tracking of Uncertain Hybrid Concurrent Systems

In this paper we propose a component-based hybrid formalism, that represents physical phenomena by combining concurrent automata with continuous uncertain dynamic models. The formalism eases the modeling of complex physical systems, and adds concurrency to the supervision of hybrid systems. Uncertainties in the model are integrated as probabilities at the discrete level and intervals at the continuous level. Our modeling framework is rather generic while focusing on the construction of intelligent autonomous supervisors by integrating a continuous/discrete interface able to reason on-line in any region of the physical system state-space, for behavior simulation, diagnosis and system tracking.