Date of Graduation
Eberly College of Arts and Sciences
The main goal of this research is to design and develop a genetic algorithm (GA) for path planning of an Unmanned Aerial Vehicle (UAV) outfitted with a camera to efficiently search for a lost person in an area of interest. The research focuses on scenarios where the lost person is from a vulnerable population, such as someone suffering from Alzheimer or a small child who has wondered off. To solve this problem, a GA for path planning was designed and implemented in Matlab. The area of interest is considered to be a circle that encompasses the distance the person could have walked in the time they have been missing. The area might also have some subareas that could not be excluded from the search for various reasons, such as a river they could not cross, or a fenced area. A grid is imposed on the area of interest, based on the field of view of the camera that the UAV is carrying and the height the UAV is flying. A chromosome is the encoding of the path the UAV will fly and the fitness function of the GA is designed to ensure that the UAV is covering all areas of the grid with the least amount of backtracking. The results show that the GA can find a path that efficiently covers the area. These results can be generalized to use more than one UAV.
Aljandeel, Shuhad, "Genetic Algorithms used for Search and Rescue of Vulnerable People in an Urban Setting" (2020). Graduate Theses, Dissertations, and Problem Reports. 7596.