Flex: 基盤モデル特徴量によるエンドツーエンドのテキスト指示視覚ナビゲーション
Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features
事前学習済みVLMを凍結したパッチ単位の特徴抽出器として使い、少量のシミュレーションデータで訓練したドローンの視覚ナビゲーション方策が、未知のテキスト指示や実世界の視覚変化に汎化できることを示した。
著者: Makram Chahine, Alex Quach, Alaa Maalouf, Tsun-Hsuan Wang, Daniela Rus
分類: cs.RO, cs.AI
原文アブストラクト
End-to-end learning directly maps sensory inputs to actions, creating highly integrated and efficient policies for complex robotics tasks. However, such models often struggle to generalize beyond their training scenarios, limiting adaptability to new environments, tasks, and concepts. In this work, we investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies under unseen text instructions and visual distribution shifts. Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors, generating spatially aware embeddings that integrate semantic and visual information. We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning on a small simulated dataset successfully generalize to real-world scenes with diverse novel goals and command formulations.
