単眼リアクティブMAV制御のための転移可能なポリシー学習
Learning Transferable Policies for Monocular Reactive MAV Control
関連するソースドメインの訓練データを活用し、目標ドメインで使える運動ポリシーを学習する汎用フレームワークを提案。単眼リアクティブ制御によるMAV飛行で、屋外の障害物環境での実機実験により有効性を示した。
著者: Shreyansh Daftry, J. Andrew Bagnell, Martial Hebert
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
The ability to transfer knowledge gained in previous tasks into new contexts is one of the most important mechanisms of human learning. Despite this, adapting autonomous behavior to be reused in partially similar settings is still an open problem in current robotics research. In this paper, we take a small step in this direction and propose a generic framework for learning transferable motion policies. Our goal is to solve a learning problem in a target domain by utilizing the training data in a different but related source domain. We present this in the context of an autonomous MAV flight using monocular reactive control, and demonstrate the efficacy of our proposed approach through extensive real-world flight experiments in outdoor cluttered environments.
