Reinforcement Learning for Autonomous Aircraft Control and Aerial Maneuvering in Simulated Environments

Abstract

This thesis explores reinforcement learning for autonomous airplane navigation in a Unity-based simulation. Using Proximal Policy Optimization (PPO), the agent learns to fly, avoid obstacles, and reach targets through continuous control. A combination of environment design and reward shaping was essential for achieving stable learning. Results show that performance improves significantly with training and proper reward design. Experiments across different difficulty levels highlight the impact of environment complexity on learning.