Authors: Mantegazza, D. ; Guzzi, J.; Gambardella, L. M.; Giusti, A.
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 a 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.
- Published in: 2019 International Conference on Robotics and Automation (ICRA), Montreal, QC, Canada, 2019, pp. 6489-6495
- DOI: doi: 10.1109/ICRA.2019.8794377
- Read paper
- Date: 2019