A³-VLA: 操作プロセスから自動生成した知覚ガイドで注意を整列させるロボットマニピュレーション手法
$A^3$-VLA: Automatic Perception-Guided Attention Alignment for Robot Manipulation
操作中の視覚変化から対象物・ロボット領域を自動抽出し、注意配分損失と対照学習でVLAの注意をタスク重要領域へ誘導するフレームワーク。複数のVLAバックボーンで成功率を6.5〜25.2%向上させた。
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: Shengzhe Zhang, Qi Zhang, Dazhong Shen, Chao Wang, Shaopeng Zhai, Hui Xiong
分類: cs.RO
原文アブストラクト
Vision-Language-Action Models (VLAs) enable robots to perform manipulation tasks by leveraging Vision-Language Models (VLMs) to process visual observations and language instructions. However, the action prediction objective itself lacks fine-grained task-specific perceptual supervision, making it prone to relying on task-irrelevant visual shortcuts, leading attention away from target objects and key interaction areas, thereby limiting its operational performance and generalization ability. To address this, we propose Automatic Perception-Guided Attention Alignment for Robot Manipulation ($A^3$-VLA), a framework that derives task-specific visual guidance from the manipulation process itself. Specifically, $A^3$-VLA first generates heuristic candidate regions for target objects and the robot from interaction-induced visual changes, and refines them with a visual segmentation model offline. These regions serve as explicit perceptual guidance through two complementary objectives: an attention allocation loss that encourages sufficient focus on task-critical regions when language or robot state tokens query the visual input, and a contrastive learning loss that aligns the representations of candidate target regions with language instructions while separating them from task-irrelevant regions. Extensive experiments on simulated and real-world manipulation tasks demonstrate that $A^3$-VLA consistently improves multiple VLA backbones, with an average success rate gain of 6.5% - 25.2% across benchmarks.