Indoor autonomous navigation of low-cost MAVs using landmarks and 3D perception

We present an implementation of autonomous navigation for Micro Air Vehicles which is well-suited for very inexpensive models: It relies on a bottom and a front camera, and few additional on-board sensors to solve the challenges of flight planning and collision avoidance. Artificial landmarks may be used in specific places (lines in narrow corridors) and in places with an ambiguous further flight path, such as corridor crossings or junctions. For the latter case, they thus provide topological localization, which enables our system to perform tasks like way point following. Even without any 3D sensor, our system is also able to reconstruct metric distances from its monocular camera via two complementary methods: An oscillating motion pattern is superimposed to regular flight to reliably estimate up-to-date 3D positions of sparse image features. As an alternative, a specific flight maneuver can virtually create a vertical stereo camera to provide depth information densely across most pixels at single points in time.