High traffic congestion in cities can lead to difficulties in delivering appropriate aid to people in need of emergency services. Developing an autonomous aerial medical evacuation system with the required size to facilitate the need can allow for the mitigation of the constraint. The aerial system must be capable of vertical takeoff and landing to reach highly conjected areas and areas where traditional aircraft cannot access. In general, the most challenging limitation within any proposed solution is the landing sequence. There have been several techniques developed over the years to land aircraft autonomously; however, very little attention has been scoped to operate strictly within highly congested urban-type environments. The goal of this research is to develop a possible solution to achieve autonomous landing based on computer vision-capture systems. For example, by utilizing modern computer vision approaches involving depth estimation through binocular stereo computer vision, a depth map can be developed. If the vision system is mounted to the bottom of an autonomous aerial system, it can represent the area below the aircraft and determine a possible landing zone. In this work, neural networks are used to isolate the ground via the computer vision height map. Then out of the entire visible ground area, a potential landing position can be estimated. An optimization routine is then developed to identify the most optimal landing position within the visible area. The optimization routine identifies the largest identifiable open area near the desired landing location. Web cameras were utilized and processed on a desktop to form a basis for the computer vision system. The algorithms were tested and verified using a simulation effort proving the feasibility of the approach. In addition, the system was tested on a scaled down city scene and was able to determine an optimal landing zone.
Mechanical Engineering (MS)
Department, Program, or Center
Mechanical Engineering (KGCOE)
Quattrociocchi, Nicholas, "A Depth-Based Computer Vision Approach to Unmanned Aircraft System Landing with Optimal Positioning" (2022). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus