✨ This project involves developing and training a reinforcement learning model for UAVs to perform tasks autonomously, including navigation, obstacle avoidance, and object detection. The UAV model was integrated with ROS (Robot Operating System) and simulated using Gazebo. During the development, two reinforcement learning algorithms—Q-Learning and TEXPLORE—were explored and tested for efficiency in various UAV operations. The project also covered hardware integration to ensure real-time performance and control in physical environments.
