UAV Path Planning for Wireless Data Harvesting: A Deep Reinforcement Learning Approach
This work addresses efficient and adaptive trajectory planning for UAVs in communication networks, offering a solution that avoids expensive recomputations when parameters change, though it is incremental as it builds on existing RL methods.
The paper tackles UAV path planning for wireless data harvesting in urban IoT networks by proposing a deep reinforcement learning approach using a DDQN with combined experience replay and a multi-layer map, resulting in a policy that generalizes across changing scenario parameters like sensor positions and flying time, with demonstrated learning efficiency improvements.
Autonomous deployment of unmanned aerial vehicles (UAVs) supporting next-generation communication networks requires efficient trajectory planning methods. We propose a new end-to-end reinforcement learning (RL) approach to UAV-enabled data collection from Internet of Things (IoT) devices in an urban environment. An autonomous drone is tasked with gathering data from distributed sensor nodes subject to limited flying time and obstacle avoidance. While previous approaches, learning and non-learning based, must perform expensive recomputations or relearn a behavior when important scenario parameters such as the number of sensors, sensor positions, or maximum flying time, change, we train a double deep Q-network (DDQN) with combined experience replay to learn a UAV control policy that generalizes over changing scenario parameters. By exploiting a multi-layer map of the environment fed through convolutional network layers to the agent, we show that our proposed network architecture enables the agent to make movement decisions for a variety of scenario parameters that balance the data collection goal with flight time efficiency and safety constraints. Considerable advantages in learning efficiency from using a map centered on the UAV's position over a non-centered map are also illustrated.