We consider the task of controlling a quadrotor to hover in front of a freely moving user, using input data from an onboard camera. On this specific task we compare two widespread learning paradigms: a mediated approach, which learns an high-level state from the input and then uses it for deriving control signals; and an end-to-end approach, which skips high-level state estimation altogether. We show that despite their fundamental difference, both approaches yield equivalent performance on this task. We finally qualitatively analyze the behavior of a quadrotor implementing such approaches.
@article{arxiv.1809.08881,
title = {Vision-based Control of a Quadrotor in User Proximity: Mediated vs End-to-End Learning Approaches},
author = {Dario Mantegazza and Jérôme Guzzi and Luca M. Gambardella and Alessandro Giusti},
journal= {arXiv preprint arXiv:1809.08881},
year = {2019}
}