High-Speed Autonomous Quadrotor Navigation through Image Paths

This paper addresses the problem of autonomous quadrotor navigation within indoor spaces. In particular, we focus on the case where a visual map of the area, represented as a graph of linked images, is constructed offline (from visual and inertial data collected beforehand) and used to determine visual paths for the quadrotor to follow. Moreover, during the actual navigation, the quadrotor employs both the 3+1pt and the 1+1pt RANSAC to efficiently determine its desired motion towards the next reference image, for both cases of sufficient and insufficient baseline (e.g., rotations in place). Lastly, we introduce an adaptive optical-flow algorithm that can accurately estimate the quadrotor’s horizontal velocity under adverse conditions (e.g., when flying over dark, textureless floors) by progressively using information from more parts of the images. The speed and robustness of our algorithms are evaluated experimentally on a commercial quadrotor navigating in the presence of dynamic obstacles (i.e., people walking), along lengthy corridors, and through tight corners, as well as across building floors via poorly-lit staircases.