Multisensor remote robot localization and manipulation in low-visibility conditions

Indoor sensor localization is a complex task. In normal circumstances, laser meters, ultrasonic meters or even image processing may be used to estimate the position of a given node at a particular moment. Indoor localization in low-visibility conditions due to smoke is one of the EU GUARDIANS (GUARDIANS (2010)) project goals. When smoke density grows, optical sensors are not efficient anymore. In these scenarios other sensors must be studied, such as sonar, radar or radio-frequency signals. The developed multisensor method aims to position a robot in front of doors, fire extinguishers and other points of interest with enough accuracy to, know the doorknob position, grasp it and open the door. In the coarse grain localization, ZigBee and WiFi signals are used to calculate the localization of the robot inside a building and guide it near enough to the point of interest to glimpse a programmable high intensity LED panel. Then, smoke detection and visual fine grained localization are used to position the robot with precision.