Q-Learning for autonomous navigation of UAVs in indoor environments
Advanced Flight Simulation Laboratory, Aerospace Engineering Division, IISc.
Indoor Path Planning and Navigation of an ArDrone based on simple PID control+Q-Learning. The quadrotor learns to manoeuvres towards the goal point, along the uniform grid distribution(5X5) in the simulation environment based on a reward of -1 while not ending up in the goal state and a reward of +100 for reaching the goal.
Reference: Pham, Huy X., et al. "Autonomous uav navigation using reinforcement learning." arXiv preprint arXiv:1801.05086 (2018).[arxiv]