GWM-VLA：視覚言語行動学習のための幾何認識潜在世界モデリング
GWM-VLA: Geometry-Aware Latent World Modeling for Vision-Language-Action Learning
視覚言語行動モデルの堅牢性を向上させるため、多視点の幾何関係を明示的にモデル化する潜在世界モデルを提案し、シミュレーションと実環境で性能を検証した。
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: Yanping Zhao, Hang Yu, Yiwei Wang, Chen Ye, Siyu Tian, Di Zhang, Qingjun Wang, Qian Chen, Junqiao Zhao, Chen Ye, Guang Chen
分類: cs.RO
原文アブストラクト
Vision-Language-Action (VLA) models achieve strong robotic manipulation performance but often degrade under visual and environmental shifts. Latent world modeling offers a promising approach to improving robustness, yet existing methods commonly encode camera views independently and predict holistic scene dynamics without explicitly modeling their geometric relationships. We propose GWM-VLA, a geometry-aware latent world modeling framework for VLA learning. GWM-VLA combines geometry-aware multi-view state encoding, global context-conditioned target-view prediction, and shared latent-action representations grounded by robot-action supervision. Specifically, VGGT-$Ω$ jointly aggregates multi-view observations at each timestep to construct geometry-aware multi-view states. The latent world model predicts the next-step patch tokens of a selected target view using patch and register tokens obtained after multi-view aggregation, thereby retaining multi-view geometric information without predicting the complete multi-view state. We use the wrist view as the target in our experiments, placing greater emphasis on end-effector motion and local gripper-object interactions. Finally, the shared latent-action representations condition both the latent world model and the flow-matching action head, allowing latent-prediction supervision and ground-truth robot-action supervision to jointly shape the same latent-action representations. Experiments across both simulation and real-world environments demonstrate the effectiveness and robustness of GWM-VLA.