Coordination of scout drones (UAVs) in smart-city to serve autonomous vehicles

Abstract

The subject of Unmanned Aerial Vehicles (UAVs) has become a promising study field in both research and industry. Due to their autonomy and efficiency in flight, UAVs are considerably used in various applications for different tasks. Actually, the autonomy of the UAV is a challenging issue that can impact both its performance and safety during the mission. During the flight, the autonomous UAVs are required to investigate the area and determine efficiently their trajectory by preserving their resources (energy related to both altitude and path length) and satisfying some constraints (obstacles and axe rotations). This problem is defined as the UAV path planning problem that requires efficient algorithms to be solved, often Artificial Intelligence algorithms. In this thesis, we present two novel approaches for solving the UAV path planning problem. The first approach is an improved algorithm based on African Vultures Optimization Algorithm (AVOA), called CCO-AVOA algorithms, which integrates the Chaotic map, Cauchy mutation, and Elite Opposition-based learning strategies. These three strategies improve the performance of the original AVOA algorithm in terms of the diversity of solutions and the exploration/exploitation search balance. A second approach is a hybrid-based approach, called CAOSA, based on the hybridization of Chaotic Aquila Optimization with Simulated Annealing algorithms. The introduction of the haotic map enhances the diversity of the Aquila Optimization (AO), while the Simulated Annealing (SA) algorithm is applied as a local search algorithm to improve the exploitation search of the traditional AO algorithm. Finally, the autonomy and efficiency of the UAV are tackled in another important application, which is the UAV placement problem. The issue of the UAV placement relays on finding the optimal UAV placement that satisfies both the network coverage and connectivity while considering the UAV’s limitation from energy and load. In this context, we proposed an efficient hybrid called IMRFO-TS, based on the combination of Improved Manta Ray Foraging Optimization, which integrates a tangential control strategy and Tabu Search algorithms