Environmental Hotspot Identification in Limited Time with a UAV Equipped with a Downward-Facing Camera
This work addresses environmental monitoring for applications like pollution tracking, but it is incremental as it adapts existing methods to a specific UAV-based sensing scenario.
The paper tackles the problem of identifying environmental hotspots using a UAV with a limited time budget by formulating it as a novel multi-fidelity Gaussian Process multi-armed bandit problem, and presents a strategy that is empirically compared to baselines and tested in real and simulated environments.
Our work is motivated by environmental monitoring tasks, where finding the global maxima (i.e., hotspot) of a spatially varying field is crucial. We investigate the problem of identifying the hotspot for fields that can be sensed using an Unmanned Aerial Vehicle (UAV) equipped with a downward-facing camera. The UAV has a limited time budget which it can use for learning the unknown field and identifying the hotspot. Our contribution is to show how this problem can be formulated as a novel multi-fidelity variant of the Gaussian Process (GP) multi-armed bandit problem. The novelty is two-fold: (i) unlike standard multi-armed bandit settings, the rewards of the arms are correlated with each other; and (ii) unlike standard GP regression, the measurements in our problem are images (i.e., vector measurements) whose quality depends on the altitude of the UAV. We present a strategy for finding the sequence of UAV sensing locations and empirically compare it with several baselines. Experimental results using images gathered onboard a UAV are also presented and the scalability of the proposed methodology is assessed in a large-scale simulated environment in Gazebo.