GeoAlign: セマンティクスを超えた状態誘導による空間的位置合わせをVLAモデルに導入
GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models
VLAモデルにロボットの状態情報を利用した幾何学的特徴の位置合わせ機構を導入し、操作タスクの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: Yizhi Chen, Zhanxiang Cao, Xinyi Peng, Yixiao Zheng, Xiaxi Si, Yiheng Li, Liyun Yan, Keqi Zhu, Xueyun Chen, Shengcheng Fu, Tianyue Zhan, Yufei Jia, Jinming Yao, Yan Xie, Kun Wang, Cewu Lu, Yue Gao
分類: cs.RO
原文アブストラクト
Current Vision--Language--Action (VLA) models often optimize for semantic grounding, whereas executable manipulation requires geometry-aware spatial alignment and dynamic affordance selection. We introduce GeoAlign, a state-guided spatial alignment architecture for VLA policy learning. GeoAlign post-trains an RGB geometry branch with robot-domain RGB-D supervision, yielding RGB-derived Geometry-Enhanced Post-Trained (GEP) features for policy rollout. The robot's proprioceptive state queries the GEP feature grid, producing compact, phase-dependent geometry tokens for action prediction. GeoAlign achieves 99.0% on LIBERO, 85.3% across three SimplerEnv-Fractal tasks, and 78.8% on eight geometry-critical real-world ALOHA tasks, with ablations confirming the value of geometry post-training and proprioceptive-state-guided querying.
