Informative Path Planning for UAV-based Active Sensing
Unmanned aerial vehicles (UAVs) are rapidly gaining popularity in aerial mapping and general monitoring tasks. In many applications, including agriculture, surveillance, post-disaster assessment, and search and rescue, UAVs are replacing conventional methods of data collection at higher levels of precision, safety, and time- and cost-efficiency. However, a key challenge is deciding how an autonomous agent should act to gather the most useful data about an initially unknown, uncertain environment within the set of its resource constraints. To address this, this lecture will discuss the informative path planning problem for active sensing using UAVs in terrain monitoring scenarios. I will introduce recent methods for planning, mapping, and learning that enable efficient data gathering using examples from the agricultural domain and conclude with an outlook towards future work.