Multi-Sensor Surveillance of Indoor Environments by an Autonomous Mobile Robot

摘要

In this paper, we present our autonomous mobile robotic system for surveillance of indoor environments. The robot is equipped with a monocular camera, a laser scanner, encoders, and an RFID device, connected to a multi-layer decision and control scheme. Two main functions are implemented: to build a map of the environment, identifying specific areas of interest, marked by RFID tags; to monitor the target zones to detect unexpected changes, such as object addition or removal, based on a vision scene change detector (V-SCD) and a laser scene change detector (L-SCD). Fuzzy logic is used to integrate information provided by the different sensors. Applications of the proposed system include surveillance of wide areas, such as airports and museums, and monitoring of safety equipment. The feasibility of the approach is demonstrated through experimental tests, performed in the ISSIA Mobile Robotics Laboratory of Ban, Italy. The results are promising, proving the method to be effective in detecting either new or removed objects in the surveyed scene, also in presence of relatively small viewpoint changes. It is shown that the proposed robotic surveillance system successfully addresses a number of specific problems related to environment mapping, autonomous navigation, and scene processing, and can be potentially employed in real world surveillance applications.