ユーザー近接飛行におけるクアッドロータの視覚制御：媒介学習とエンドツーエンド学習の比較
Vision-based Control of a Quadrotor in User Proximity: Mediated vs End-to-End Learning Approaches
搭載カメラの映像から自由に動くユーザーの前にホバリングするクアッドロータ制御を対象に、高レベル状態を介する学習とエンドツーエンド学習を比較し、性能が同等であることを示した。
著者: Dario Mantegazza, Jérôme Guzzi, Luca M. Gambardella, Alessandro Giusti
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
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.
