実行時観察介入で視覚言語行動モデルの視覚的堅牢性を向上
Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust
VLAモデルが苦手とする妨害物体や背景色などのタスク無関係な視覚的詳細に対し、実行時に感度の高い領域を特定し自動画像編集で最小限の修正を加えるBYOVLAを提案。ファインチューニング不要で成功率低下を防ぐ。
著者: Asher J. Hancock, Allen Z. Ren, Anirudha Majumdar
分類: cs.RO, cs.LG
原文アブストラクト
Vision-language-action (VLA) models trained on large-scale internet data and robot demonstrations have the potential to serve as generalist robot policies. However, despite their large-scale training, VLAs are often brittle to task-irrelevant visual details such as distractor objects or background colors. We introduce Bring Your Own VLA (BYOVLA): a run-time intervention scheme that (1) dynamically identifies regions of the input image that the model is sensitive to, and (2) minimally alters task-irrelevant regions to reduce the model's sensitivity using automated image editing tools. Our approach is compatible with any off the shelf VLA without model fine-tuning or access to the model's weights. Hardware experiments on language-instructed manipulation tasks demonstrate that BYOVLA enables state-of-the-art VLA models to nearly retain their nominal performance in the presence of distractor objects and backgrounds, which otherwise degrade task success rates by up to 40%. Website with additional information, videos, and code: https://aasherh.github.io/byovla/ .
