Autonomous drone flight and mission planning with reinforcement learning: developing strategies to achieve goals and overcome obstacles

The aim of this study is to develop strategies for achieving targets and overcoming obstacles in autonomous drone flight and mission planning by utilizing reinforcement learning methods. This represents a significant area of research aimed at enhancing the efficiency and reliability of drone technology. It is hypothesized that reinforcement learning algorithms can optimize the decision-making processes of autonomous drones, enabling them to adapt to changing environmental conditions and develop effective strategies for target achievement and obstacle avoidance. Within the scope of this study, the performance of reinforcement learning algorithms will be evaluated under different environmental conditions and mission scenarios. The sample has been designed to ensure the collection and analysis of comprehensive data across various scenarios. Reinforcement learning algorithms implemented for autonomous drone systems will be examined in detail using data obtained from simulation environments. The effectiveness of reinforcement learning algorithms in improving the task performance of autonomous drones will be analyzed by demonstrating their progress in achieving targets and overcoming obstacles. This thesis aims to emphasize the strategic importance of reinforcement learning in autonomous drone flight and mission planning, while also assessing the applicability and effectiveness of newly developed algorithms.