UAV-navigation-using-Q-learning-and-pid

This repository contains the source code for implementing Q learning and pid based autonomous navigation of quadrotor, maneuvering towards the goal point, along the uniform grid distribution in indoor environments.

Parameters:

• State: Discrete
• Action: Discrete
• Action space: 5x5 grid space.

Dependencies & Packages:

• Ubuntu 16.04
• ROS Kinetic
• Gazebo 7
• ArDrone Autonomy ROS Package
• gym: 0.9.3
• TensorFLow 1.1.0 (preferrable with GPU support)
• Python: 2.7