Author Type

Graduate Student

Date of Award

Spring 4-13-2026

Document Type

Dissertation

Publication Status

Version of Record

Submission Date

April 2026

Department

Computer and Electrical Engineering and Computer Science

College Granting Degree

College of Engineering and Computer Science

Department Granting Degree

Electrical Engineering and Computer Science

Degree Name

Doctor of Philosophy (PhD)

Thesis/Dissertation Advisor [Chair]

Imadeldin Mahgoub

Abstract

Modern world is being heavily impacted and increasingly being shaped by autonomous systems and connected devices. This necessity to utilize these devices has made it of utmost urgency to develop intelligent, adaptive, and secure drone operations. This dissertation investigates how nature-inspired algorithms (NIAs) can significantly enhance the path and motion planning mechanisms of Unmanned Aerial Vehicles (UAVs), specially in complex, dense, and adversarial environments.

The work in this dissertation is motivated by two critical challenges facing UAV systems. The first one is being the need for efficient and adaptive path planning in static environments. The second one is the motion planning in dynamic and hostile 3D environments for single and multi-UAV.

The methods that are utilized to approach these challenges in UAVs are inspired by biological processes and flock collective behaviors found in nature such as the foraging of ants, flocking of birds, and the leaping of frogs. This research explores how NIAs such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), and Shuffled Frog Leaping Algorithm (SFLA) are capable of providing practical solutions to these issues.

The dissertation is structured into three core contributions. First, we conducted a survey and proposed an expanded taxonomy of NIAs applied in Internet of Vehicles (IoV) environments. In addition, we identified overlooked domains such as clustering and provided a mapping of algorithms to appropriate use cases. Second, we proposed two hybrid algorithms: GBGA-PSO-ACO algorithm and enhanced GA-PSO-ACO algorithm called E-GPA. These two hybrid frameworks improve UAV path planning in static environments for a single UAV. Results of experiments demonstrate enhanced convergence, and shorter paths. Third, we proposed an adaptive SFLA model designed for motion planning in dynamic and adversarial scenarios in 3D environments that minimize detection risk and improve mission success.

By combining NIAs with domain-specific application, this research provides new tools and perspectives for designing resilient, intelligent, and adaptable UAV path and motion planning systems.

Available for download on Thursday, April 15, 2027

Share

COinS