MULTI-ROBOT SURVEILLANCE SYSTEM FOR INDOORS FIRE DETECTION: A CASE OF STUDY

AbstractIn this paper we present the application of a framework that gives the bases to model necessary behaviors and functions of robotic agents for surveillance, that can be used in the implementation of a Robotic surveillance system. The framework includes a formal definition of Surveillance, a hierarchy of alarm events, a model of the surveillance environment using a 2 dimension space tessellation, a definition of sensors and surveillance agents, a model of the interactions among the agents, and formal definitions of different kinds of surveillance patrolling. The framework is applied to a case of study for a surveillance system for Indoors Fire Detection, using a heterogeneous sensor platform. The relevant surveillance events are identified and formally defined as discrete events for the experimental case. The definition is mapped to a Petri Net that manages the events to detect possible alarm states. Experimental setup, implementation and conclusions about the case of study are shown.