Graph-Based Robot Localization in Tunnels Using RF Fadings

Robot localization inside tunnels is a challenging task due to the hostile conditions of the environment. The GPS-denied nature of the scenario together with the low visibility, slippery surfaces, and the lack of distinguishable features, make traditional robotics methods based on cameras or laser unreliable. In this paper, we address the robot localization problem with an alternative graph-based localization approach, taking advantage of the periodic nature of the RF signal fadings that appears inside tunnels under certain transmitter-receiver settings. Experimental results in a real scenario demonstrate the validity of the proposed method for inspection applications.