cVLA: 効率的なカメラ空間VLAに向けて
cVLA: Towards Efficient Camera-Space VLAs
視覚言語モデルを活用し、画像座標でエンドエフェクタの軌道ウェイポイントを直接予測する軽量なVLAを提案。シミュレーションで訓練し実機への転移性能を示した。
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: Max Argus, Jelena Bratulic, Houman Masnavi, Maxim Velikanov, Nick Heppert, Abhinav Valada, Thomas Brox
分類: cs.RO, cs.LG
原文アブストラクト
Vision-Language-Action (VLA) models offer a compelling framework for tackling complex robotic manipulation tasks, but they are often expensive to train. In this paper, we propose a novel VLA approach that leverages the competitive performance of Vision Language Models (VLMs) on 2D images to directly infer robot end-effector poses in image frame coordinates. Unlike prior VLA models that output low-level controls, our model predicts trajectory waypoints, making it both more efficient to train and robot embodiment agnostic. Despite its lightweight design, our next-token prediction architecture effectively learns meaningful and executable robot trajectories. We further explore the underutilized potential of incorporating depth images, inference-time techniques such as decoding strategies, and demonstration-conditioned action generation. Our model is trained on a simulated dataset and exhibits strong sim-to-real transfer capabilities. We evaluate our approach using a combination of simulated and real data, demonstrating its effectiveness on a real robotic system.
