Small scale unmanned aerial system (UAS) for railway culvert and tunnel inspection

This project aims to develop a small-scale multi-rotor unmanned aerial system (UAS) as a railway culvert inspection tool. In the current study, the UAS is deployed at the entrance to a culvert and it then traverses through the culvert in a semi-autonomous fashion. The UAS is able to measure the cross sectional shape of the culvert in real time using the on-board light detection and ranging (LiDAR) scanner, that is also used to autonomously align the UAS with the centroid of this cross section. With extra sensors to measure the distance of the UAS from entrance of the culvert, the cross sectional data collected from the LiDAR can then be further processed to obtain three-dimensional point clouds of the culvert’s structure. This system enables the railway entities to safely and efficiently conduct regular inspections and collect necessary measurements without needing to enter confined spaces or rail corridor. Navigating the UAS through confined spaces does present a number of challenges. Novel research is required to deal with the stability of a UAS in a confined space, where the interaction between the vehicle rotor downwash and the walls of the culvert leads to unstable flight.