Trajectory optimization for autonomous underwater vehicles in IoUT-enabled ocean exploration / Abderrahmane Nebeg

Public ISBD Titre : Trajectory optimization for autonomous underwater vehicles in IoUT-enabled ocean exploration Type de document : document multimédia Auteurs : Abderrahmane Nebeg, Auteur ; Mohamed Azeddine Nebeg, Auteur ; Abdelmadjid Ben Arfa, Directeur de thèse Editeur : Laghouat : Université Amar Telidji - Département d'informatique Année de publication : 2026 Importance : 125 p. Accompagnement : 1 disque optique numérique (CD-ROM) Note générale : Option : Networks, systems and distributed applications Langues : Anglais (eng) Mots-clés : Autonomous underwater vehicles  Trajectory optimization  A∗  Q-Learning  Model predictive control  IoUT Résumé : Autonomous Underwater Vehicles (AUVs) play a crucial role in ocean exploration, scientific research, and environmental monitoring. However, efficient trajectory optimization in dynamic underwater environments remains a significant challenge due to factors such as ocean currents, obstacles, and limited energy resources. In this work, we propose a hybrid framework for trajectory optimization of AUVs in an Internet of Underwater Things (IoUT)-enabled environment. The proposed approach combines the A∗ algorithm for global path planning, Q-Learning for adaptive decision-making, and an MPC-based trajectory refinement layer strategy to ensure smooth and feasible trajectories under system constraints. The A∗ algorithm is used to generate an initial feasible path, while the Q-Learning module refines local navigation decisions by interacting with the dynamic environment. The MPC controller is then applied to enhance trajectory smoothness and enforce physical and operational constraints. In addition, an interactive interface is developed to visualize, analyze, and monitor the trajectory optimization process, providing better understanding and control of the system behavior. The proposed framework is evaluated through simulation in order to analyze its performance in terms of trajectory efficiency, energy consumption, and navigation safety. note de thèses : Mémoire de master en informatique Trajectory optimization for autonomous underwater vehicles in IoUT-enabled ocean exploration [document multimédia] / Abderrahmane Nebeg, Auteur ; Mohamed Azeddine Nebeg, Auteur ; Abdelmadjid Ben Arfa, Directeur de thèse . - Laghouat : Université Amar Telidji - Département d'informatique, 2026 . - 125 p. + 1 disque optique numérique (CD-ROM). Option : Networks, systems and distributed applications Langues : Anglais (eng) Mots-clés : Autonomous underwater vehicles  Trajectory optimization  A∗  Q-Learning  Model predictive control  IoUT Résumé : Autonomous Underwater Vehicles (AUVs) play a crucial role in ocean exploration, scientific research, and environmental monitoring. However, efficient trajectory optimization in dynamic underwater environments remains a significant challenge due to factors such as ocean currents, obstacles, and limited energy resources. In this work, we propose a hybrid framework for trajectory optimization of AUVs in an Internet of Underwater Things (IoUT)-enabled environment. The proposed approach combines the A∗ algorithm for global path planning, Q-Learning for adaptive decision-making, and an MPC-based trajectory refinement layer strategy to ensure smooth and feasible trajectories under system constraints. The A∗ algorithm is used to generate an initial feasible path, while the Q-Learning module refines local navigation decisions by interacting with the dynamic environment. The MPC controller is then applied to enhance trajectory smoothness and enforce physical and operational constraints. In addition, an interactive interface is developed to visualize, analyze, and monitor the trajectory optimization process, providing better understanding and control of the system behavior. The proposed framework is evaluated through simulation in order to analyze its performance in terms of trajectory efficiency, energy consumption, and navigation safety. note de thèses : Mémoire de master en informatique

---

1 (1 - 1 / 1) Par page : 25 50 100 200