Autonomous Elevator Inspection with Unmanned Aerial Vehicle

Hong Kong has the highest elevator density in the world, with more than 63,000 elevators. The inspection and maintenance of elevator rope have been carried out directly by human with simple inspection gadgets traditionally. Recently however, the big gap between dramatically increasing demand of elevator inspection and insufficient manpower in the related industry, as well as the safety issues coupled with human inspection have resulted in investigations of the possibility in adopting Unmanned Aerial Vehicle (UAV) for elevator rope inspection. Nevertheless, UAV's control and navigation in a relatively small (comparing to the size of UAV itself) elevator shaft with extremely low luminance and high air turbulence are the biggest challenges in this solution, especially when its bottom camera, which serves as a crucial input for hovering, is nearly unplugged. This project intends to propose and develop an effective methodology of elevator rope inspection with an UAV. Vision-based control and navigation algorithms for facilitating the UAV with autonomous elevator rope detection, tracking, and inspection have been proposed. Simulations and experiments were conducted with a real setup of elevator shaft. Experimental results verified the effectiveness and efficiency of the proposed method. The proposed method can address the above issues confronted by the elevator maintenance service providers.