In this video we present results on autonomous subterranean exploration inside an abandoned underground mine using an aerial robot. The aerial robot is utilizing the proposed Graph-based Exploration Path Planner which ensures the efficient exploration of the complex underground environment, while simultaneously avoiding obstacles. The designed planner first operates by engaging its local exploration mode with which guides the robot to explore along a mine corridor. When the system reaches a local dead-end, a mine heading with a machineshop, the global planning layer of the method is engaged and provides plan to guide the robot towards a selected frontier of the explored space. The robot is thus re-positioned to this frontier and upon arrival the local planning mode is enabled again in order to enable the continuation of the exploration mission. Finally, provided a time budget for the mission, the global planner identifies the point that the robot must be commanded to return-to-home and provides an associated reference path. The presented mission is completely autonomous.
