VISTA: 行動履歴条件付けによるスケール認識型視覚ナビゲーション
VISTA: Scale-Aware Visual Navigation via Action History Conditioning
視覚ナビゲーション基盤モデルが正規化された行動予測により物理的スケールを誤解する問題を解決するため、行動履歴を条件付けに加え、DINOv3エンコーダで空間・幾何情報を強化したモデルVISTAを提案。未見環境でのゼロショット実世界展開で高い性能を示した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Maeva Guerrier, Koki Kobayashi, Simon Roy, Jana Pavlasek, Giovanni Beltrame
分類: cs.RO, cs.LG
原文アブストラクト
Vision Navigation Foundation Models (VNMs) promise end-to-end learned navigation policies capable of zero-shot deployment across diverse embodiments and environments. To maintain generality, many vision-based navigation models predict normalized actions. However, this normalization introduces a critical deployment vulnerability: applying different scaling factors to the same normalized trajectory alters its physical geometry, which degrades navigation performance and increases collision risks. We address this vulnerability by conditioning the model on normalized action histories alongside image observations, providing explicit context on the relationship between the model's predictions and the robot's actual physical displacement. Furthermore, current VNMs often struggle in visually repetitive environments that lack distinct features. To resolve this issue, we integrate a DINOv3 encoder, whose richer representations enable our model to capture both spatial and geometric dimensions between observations. VISTA generalizes robustly to out-of-distribution environments, achieving 100% goal prediction accuracy in zero-shot, real-world deployment in Outdoor, Forest and Office settings, and an average of 95% checkpoints crossed, demonstrating consistent path following in unseen environments.
