視覚運動制御のための3Dニューラルシーン表現
3D Neural Scene Representations for Visuomotor Control
NeRFと時間コントラスト学習を組み合わせ、2D画像から視点不変な3Dシーン表現を学習し、剛体や流体の操作タスクにおける視覚運動制御を実現した研究。
著者: Yunzhu Li, Shuang Li, Vincent Sitzmann, Pulkit Agrawal, Antonio Torralba
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
Humans have a strong intuitive understanding of the 3D environment around us. The mental model of the physics in our brain applies to objects of different materials and enables us to perform a wide range of manipulation tasks that are far beyond the reach of current robots. In this work, we desire to learn models for dynamic 3D scenes purely from 2D visual observations. Our model combines Neural Radiance Fields (NeRF) and time contrastive learning with an autoencoding framework, which learns viewpoint-invariant 3D-aware scene representations. We show that a dynamics model, constructed over the learned representation space, enables visuomotor control for challenging manipulation tasks involving both rigid bodies and fluids, where the target is specified in a viewpoint different from what the robot operates on. When coupled with an auto-decoding framework, it can even support goal specification from camera viewpoints that are outside the training distribution. We further demonstrate the richness of the learned 3D dynamics model by performing future prediction and novel view synthesis. Finally, we provide detailed ablation studies regarding different system designs and qualitative analysis of the learned representations.
