MoDA: 地図スタイル転送による身体性エージェントの自己教師ありドメイン適応
MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents
シミュレータで学習した視覚ナビゲーションエージェントを、正解ラベルなしでノイズの多い実環境に適応させる手法を提案。地図の空間的規則性を手がかりに、スタイル転送で生成した擬似クリーン地図で自己教師あり学習を行う。
著者: Eun Sun Lee, Junho Kim, SangWon Park, Young Min Kim
分類: cs.RO, cs.CV
原文アブストラクト
We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision. Map-based memory provides important contextual information for visual navigation, and exhibits unique spatial structure mainly composed of flat walls and rectangular obstacles. Our adaptation approach encourages the inherent regularities on the estimated maps to guide the agent to overcome the prevalent domain discrepancy in a novel environment. Specifically, we propose an efficient learning curriculum to handle the visual and dynamics corruptions in an online manner, self-supervised with pseudo clean maps generated by style transfer networks. Because the map-based representation provides spatial knowledge for the agent's policy, our formulation can deploy the pretrained policy networks from simulators in a new setting. We evaluate MoDA in various practical scenarios and show that our proposed method quickly enhances the agent's performance in downstream tasks including localization, mapping, exploration, and point-goal navigation.
