実現可能な行動近傍事前分布による視覚言語行動モデルのファインチューニング強化
Boosting Vision-Language-Action Finetuning with Feasible Action Neighborhood Prior
ロボット操作では各状態にほぼ等価な行動の近傍が存在するが、既存のVLA訓練はこれを無視する。本研究では、この近傍構造をガウス事前分布でモデル化する正則化を導入し、サンプル効率と成功率を向上させた。
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: Haochen Niu, Kanyu Zhang, Shuyu Yin, Qinghai Guo, Peilin Liu, Fei Wen
分類: cs.RO
原文アブストラクト
In real-world robotic manipulation, states typically admit a neighborhood of near-equivalent actions. That is, for each state, there exist a feasible action neighborhood (FAN) rather than a single correct action, within which motions yield indistinguishable progress. However, prevalent VLA training methodologies are directly inherited from linguistic settings and do not exploit the FAN property, thus leading to poor generalization and low sample efficiency. To address this limitation, we introduce a FAN-guided regularizer that shapes the model's output distribution to align with the geometry of FAN. Concretely, we introduce a Gaussian prior that promotes locally smooth and unimodal predictions around the preferred direction and magnitude. In extensive experiments across both reinforced finetuning (RFT) and supervised finetuning (SFT), our method achieves significant improvement in sample efficiency, and success rate in both in-distribution and out-of-distribution (OOD) scenarios. By aligning with the intrinsic action tolerance of physical manipulation, FAN-guided regularization provides a principled and practical method for sample-efficient, and generalizable VLA adaptation.
