Drone mapping preprint reports lower memory use in field deployments

Researchers report that FLAVOR, a mapping framework for autonomous drone exploration, reduced map memory footprint by 92.67% in a forest and 62.42% at a construction site relative to an explicit point-cloud ikd-tree. The preprint describes keeping detailed geometry in a local map while retaining compact records of observations, unfinished exploration tasks and routes. In three simulated scenes, FLAVOR achieved 31.98-41.88% shorter exploration time and a 94-99% smaller map memory footprint than the best baseline that completed all three scenes. Detailed-map capacity stays fixed as exploration expands, but compact observation and task records still grow.