Robust View Based Navigation through View Classification
Title: Robust View Based Navigation through View Classification
Authors: Amany Azevedo Amin (University of Sussex); Efstathios Kagioulis (University of Sussex); Norbert Domcsek (University of Sussex); Paul Graham (University of Sussex); Thomas Nowotny (University of Sussex); Andrew Philippides (University of Sussex);
Year: 2022
Citation: Azevedo Amin, A., Kagioulis, E., Domcsek, N., Graham, P., Nowotny, T., Philippides, A., (2022). Robust View Based Navigation through View Classification. UKRAS22 Conference “Robotics for Unconstrained Environments” Proceedings, 76-77. doi: 10.31256/Xq3Eo4F
Abstract:
Abstract—Current implementations of view-based navigation on robots have shown success, but are limited to routes of <10m [1] [2]. This is in part because current strategies do not take into account whether a view has been correctly recognised, moving in the most familiar direction given by the rotational familiarity function (RFF) regardless of prediction confidence. We demonstrate that it is possible to use the shape of the
RFF to classify if the current view is from a known position, and thus likely to provide valid navigational information, or from a position which is unknown, aliased or occluded and therefore likely to result in erroneous movement. Our model could classify these four view types with accuracies of 1.00, 0.91, 0.97 and 0.87 respectively. We hope to use these results to extend online view-based navigation and prevent robot loss
in complex environments.