Local sampling for indoor flight

A challenging problem in artificial intelligence is to achieve vision-based autonomous indoor flight with Micro Air Vehicles. Approaches to this problem currently do not make use of image appearance features, because these features generally are computationally expensive. In this article, we deliver a proof-ofconcept that appearance features can be extracted computationally efficient enough to be used for autonomous flight. In particular, we present a novel height control algorithm that uses local sampling; it estimates the height at which an image is taken by processing small image patches. We vary the specific number of image patches to directly influence the trade-off between processing time and the accuracy of the height estimation. The algorithm is first tested on image sets and then on videos taken from a real platform. Finally, we test the algorithm on a 15-gram ornithopter in an office room. The experiments show that very few image patches ( 0.56% of all possible patches) are already sufficient for the task of height control.