概念ゲート型視覚蒸留による視覚言語行動モデルの雑然環境耐性の向上
Overcoming Visual Clutter in Vision Language Action Models via Concept-Gated Visual Distillation
視覚言語行動モデルが雑然環境で失敗する原因を、背景による特徴希釈と特定し、それを抑える訓練不要の推論時フレームワークCGVDを提案した。
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: Sangmim Song, Sarath Kodagoda, Marc Carmichael, Karthick Thiyagarajan
分類: cs.CV, cs.AI, cs.RO, cs.SY, eess.SY
原文アブストラクト
Vision-Language-Action (VLA) models demonstrate impressive zero-shot generalization but frequently suffer from a "Precision-Reasoning Gap" in cluttered environments. This failure is driven by background-induced feature dilution, where high-frequency semantic noise corrupts the geometric grounding required for precise manipulation. To bridge this gap, we propose Concept-Gated Visual Distillation (CGVD), a training-free, model-agnostic inference framework that stabilizes VLA policies. CGVD operates by parsing instructions into safe and distractor sets, utilizing a two-layer target refinement process--combining cross-validation and spatial disambiguation--to explicitly penalize false positives and isolate genuine manipulation targets. We then process the scene via Fourier-based inpainting, generating a clean observation that actively suppresses semantic distractors while preserving critical spatial geometry and visual proprioception. Extensive evaluations in highly cluttered manipulation tasks demonstrate that CGVD prevents performance collapse. In environments with dense semantic distractors, our method significantly outperforms state-of-the-art baselines, achieving a 77.5% success rate compared to the baseline's 43.0%. By enforcing strict attribute adherence, CGVD establishes inference-time visual distillation as a critical prerequisite for robust robotic manipulation in the clutter.
関連論文
- AnySlot: ゼロショットのスロット配置のための目標条件付き視覚言語行動ポリシーVLA/マニピュレーション
- DAM-VLA: 動的行動モデルに基づくロボット操作のための視覚言語行動フレームワークVLA/マニピュレーション
