NS-VLA:神経記号型視覚言語行動モデル
NS-VLA: Towards Neuro-Symbolic Vision-Language-Action Models
視覚・言語特徴から記号的にプリミティブを抽出し、オンライン強化学習で行動系列を生成する神経記号型VLAフレームワークを提案。少データ・摂動環境で高精度かつゼロショット汎化を示す。
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: Ziyue Zhu, Shangyang Wu, Shuai Zhao, Zhiqiu Zhao, Shengjie Li, Yi Wang, Fang Li, Haoran Luo
分類: cs.RO
原文アブストラクト
Vision-Language-Action (VLA) models are formulated to ground instructions in visual context and generate action sequences for robotic manipulation. Despite recent progress, VLA models still face challenges in learning related and reusable primitives, reducing reliance on large-scale data and complex architectures, and enabling exploration beyond demonstrations. To address these challenges, we propose a novel Neuro-Symbolic Vision-Language-Action (NS-VLA) framework via online reinforcement learning (RL). It introduces a symbolic encoder to embedding vision and language features and extract structured primitives, utilizes a symbolic solver for data-efficient action sequencing, and leverages online RL to optimize generation via expansive exploration. Experiments on robotic manipulation benchmarks demonstrate that NS-VLA outperforms previous methods in both one-shot training and data-perturbed settings, while simultaneously exhibiting superior zero-shot generalizability, high data efficiency and expanded exploration space. Our code is available.
