ロボット操作のための3D動的シーン表現の学習
Learning 3D Dynamic Scene Representations for Robot Manipulation
物体の永続性・非可視形状の完全性・時空間連続性を捉える3Dボリューム表現DSRと、複数回の観測を統合してこれを構築・更新するDSR-Netを提案し、モデル予測制御と組み合わせて押し操作などの計画精度を向上させた。
著者: Zhenjia Xu, Zhanpeng He, Jiajun Wu, Shuran Song
分類: cs.RO, cs.CV
原文アブストラクト
3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completeness -- objects have 3D occupancy, even if only partial observations are available; spatiotemporal continuity -- the movement of each object is continuous over space and time. In this paper, we introduce 3D Dynamic Scene Representation (DSR), a 3D volumetric scene representation that simultaneously discovers, tracks, reconstructs objects, and predicts their dynamics while capturing all three properties. We further propose DSR-Net, which learns to aggregate visual observations over multiple interactions to gradually build and refine DSR. Our model achieves state-of-the-art performance in modeling 3D scene dynamics with DSR on both simulated and real data. Combined with model predictive control, DSR-Net enables accurate planning in downstream robotic manipulation tasks such as planar pushing. Video is available at https://youtu.be/GQjYG3nQJ80.
