ROSA: ロボット状態を活用した視覚言語と行動のアライメント
ROSA: Harnessing Robot States for Vision-Language and Action Alignment
ロボットの状態推定データを自動取得してVLAモデルの訓練に組み込み、視覚言語空間と行動空間のずれを埋めることで、少ないデータでも高性能・高汎化を実現する手法を提案。
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: Yuqing Wen, Kefan Gu, Haoxuan Liu, Yucheng Zhao, Tiancai Wang, Haoqiang Fan, Xiaoyan Sun
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
Vision-Language-Action (VLA) models have recently made significant advance in multi-task, end-to-end robotic control, due to the strong generalization capabilities of Vision-Language Models (VLMs). A fundamental challenge in developing such models is effectively aligning the vision-language space with the robotic action space. Existing approaches typically rely on directly fine-tuning VLMs using expert demonstrations. However, this strategy suffers from a spatio-temporal gap, resulting in considerable data inefficiency and heavy reliance on human labor. Spatially, VLMs operate within a high-level semantic space, whereas robotic actions are grounded in low-level 3D physical space; temporally, VLMs primarily interpret the present, while VLA models anticipate future actions. To overcome these challenges, we propose a novel training paradigm, ROSA, which leverages robot state estimation to improve alignment between vision-language and action spaces. By integrating robot state estimation data obtained via an automated process, ROSA enables the VLA model to gain enhanced spatial understanding and self-awareness, thereby boosting performance and generalization. Extensive experiments in both simulated and real-world environments demonstrate the effectiveness of ROSA, particularly in low-data regimes.
