GeomVLA: 3D空間でシーン・運動・行動を統合するVLAモデル
GeomVLA: Unifying Scene, Motion, and Action in 3D
深度とカメラキャリブレーションでVLM特徴を3Dシーントークンに持ち上げ、シーン点の将来運動を潜在表現として予測し、それを条件に3Dフロー型行動生成を行うVLAモデルを提案。CALVINなどで高性能を示した。
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: Ziyin Xiong, Nikos Gkanatsios, Moritz Reuss, Katerina Fragkiadaki
分類: cs.RO
原文アブストラクト
We present GeomVLA, a Vision-Language-Action (VLA) model that unifies perception, latent scene motion prediction, and action generation within a shared robot-centric 3D coordinate frame. Our approach lifts pretrained VLM features into spatially grounded 3D scene tokens using depth and camera calibration, while retaining the semantic representations learned during VLM pretraining. We further introduce a 3D Scene Trajectory Denoiser, a task-conditioned module that learns a latent representation of how scene points are expected to move in 3D. Rather than executing the predicted trajectory as an open-loop plan, GeomVLA extracts intermediate motion tokens from the trajectory denoiser and uses them to condition a 3D flow-based action denoiser through geometry-aware attention. GeomVLA achieves state-of-the-art performance on CALVIN, competitive performance on LIBERO and RoboTwin2.0, and outperforms strong baselines in real-world manipulation settings without robot-action pretraining. Extensive ablations show that future-motion reasoning alone is insufficient: the primary gains are associated with maintaining geometric consistency among scene representation, motion prediction, and robot actions throughout the perception-to-action pipeline.