Print Email Facebook Twitter Visual Homing for Micro Aerial Vehicles Using Scene Familiarity Title Visual Homing for Micro Aerial Vehicles Using Scene Familiarity Author van Dalen, G.J.J. McGuire, K.N. (TU Delft Control & Simulation) de Croon, G.C.H.E. (TU Delft Control & Simulation) Date 2018-06-08 Abstract Autonomous navigation is a major challenge in the development of Micro Aerial Vehicles (MAVs). Especially, when an algorithm has to be efficient, insect intelligence can be a source of inspiration. One of the elementary navigation tasks of insects and robots is “homing”, which is the task of returning to an initial starting position. A promising approach uses learned visual familiarity of a route to determine reference headings during homing. In this paper, an existing biological proof-of-concept is transferred to an algorithm for micro drones, using vision-in-the-loop experiments in indoor environments. An artificial neural network determines which control actions to take place. Subject Visual HomingScene familiarityMAV To reference this document use: http://resolver.tudelft.nl/uuid:ca31d3aa-76e4-4677-bae7-2514f696f67d DOI https://doi.org/10.1142/S230138501850005X Embargo date 2019-07-01 ISSN 2301-3850 Source Unmanned Systems, 06 (02), 119-130 Part of collection Institutional Repository Document type journal article Rights © 2018 G.J.J. van Dalen, K.N. McGuire, G.C.H.E. de Croon Files PDF unmanned_systems_visual.pdf 1.21 MB Close viewer /islandora/object/uuid:ca31d3aa-76e4-4677-bae7-2514f696f67d/datastream/OBJ/view