Ricerc@Sapienza

Efficient robotic behaviors require robustness and adaptation to dynamic changes of the environment, whose characteristics rapidly vary during robot operation. To generate effective robot action policies, planning and learning techniques have shown the most promising results. However, if considered individually, they present different limitations. Planning techniques lack generalization among similar states and require experts to define behavioral routines at different levels of abstraction.

We address the problem of devising an optimized energy aware flight plan for multiple Unmanned Aerial Vehicles (UAVs) mounted Base Stations (BS) within heterogeneous networks. The chosen approach makes use of Q-learning algorithms, through the definition of a reward related to relevant quality and battery consumption metrics, providing also service overlapping avoidance between UAVs, that is two or more UAVs serving the same cluster area.

This paper deals with the adoption of Unmanned Aerial Vehicles (UAVs) as mobile Base Stations providing video streaming services within a cellular macro area. We devise a Q-learning based UAV flight planning algorithm aimed at improving the Quality of Experience (QoE) of video users. Specifically, the proposed algorithm, herein denoted as Q-SQUARE, leverages the well-established Q-learning algorithm by introducing a reward related to a key QoE metric that is the video segment delay.