Multi-agent control architecture for RFID cyberphysical robotic systems initial validation of tagged objects detection and identification using Player/Stage

摘要

The objective of this paper is to describe and validate a multi-agent architecture proposed to control RFID Cyber-Physical Robotic Systems. This environment may contain human operators, robots (mobiles, manipulators, mobile manipulators, etc.), places (workrooms, walls, etc.) and other objects (tables, chairs, etc.). The proposed control architecture is composed of two types of agents dispatched on two levels. We find at the Organization level a Supervisory agent to allow operators to configure, manage and interact with the overall control system. At the Control level, we distinguish the Robots agents, to each robot (mobiles, manipulators or mobile manipulators) is assigned a Robot agent to carry out operations. We simulated RFID readers with fiducial finders and RFID tags with fiducials system using Player/Stage. Fiducial tags are attached to all the objects of interest of the environment; fiducial finders are installed on the robots (Robots agents) to be able to detect and identify each tagged object in the robots vicinity. Finally, obtained data are sent to the Supervisory agent to be saved and organized into a centralized database available for all the robots of the system.