Multi-sensor fusion and classification with mobile robots for situation awareness in urban search and rescue using ROS

This paper proposes a specific configuration of sensors assembled in a mobile robot, which can be used as a proof of concept to measure important environmental variables in an urban search and rescue mission, such as toxic gas density, temperature gradient and smoke particles density. This data is processed through a support vector machine classifier with the purpose of detecting relevant contexts in the course of the mission. The outcome is provided by the experimental experiments conducted with TraxBot and Pioneer-3DX robots under the Robot Operating System framework.