Inspection of coal-fired power plants is frequently dangerous, includes difficult places to reach and can turn expensive due to the downtimes and cost of inspection crew. Remotely controlled drones have shown capabilities to address some of those issues. However, the current technology is inoperable in areas where GPS is not available and that are beyond the line of view. In this project, students will develop algorithms and technology to provide drones with capabilities to navigate in the reduced areas of a power plant autonomously without the need of a GPS signal. The aerial inspecting platform will include a local planning layer based on a 3D model of the power plant and an online reacting layer that will be capable of detecting and avoiding obstacles in real time based on measurements of vision sensors. Those features will also enable closer inspection than that achievable with the current technology. Students working in this project will obtain inspection on-line and off-line inspection paths based on the 3D model of the power plant, and will develop and program algorithms for the drone to follow the desired trajectory autonomously in a representative component of a coal-fired power plant.