3D Shape Perception from Monocular Vision, Touch, and Shape Priors

2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)(2018)

引用 99|浏览196
暂无评分
摘要
Perceiving accurate 3D object shape is important for robots to interact with the physical world. Current research along this direction has been primarily relying on visual observations. Vision, however useful, has inherent limitations due to occlusions and the 2D-3D ambiguities, especially for perception with a monocular camera. In contrast, touch gets precise local shape information, though its efficiency for reconstructing the entire shape could be low. In this paper, we propose a novel paradigm that efficiently perceives accurate 3D object shape by incorporating visual and tactile observations, as well as prior knowledge of common object shapes learned from large-scale shape repositories. We use vision first, applying neural networks with learned shape priors to predict an object's 3D shape from a single-view color image. We then use tactile sensing to refine the shape; the robot actively touches the object regions where the visual prediction has high uncertainty. Our method efficiently builds the 3D shape of common objects from a color image and a small number of tactile explorations (around 10). Our setup is easy to apply and has potentials to help robots better perform grasping or manipulation tasks on real-world objects.
更多
查看译文
关键词
3D object shape,precise local shape information,monocular camera,visual observations,physical world,perceiving accurate 3D object shape,touch,monocular vision,real-world objects,visual prediction,object regions,learned shape priors,large-scale shape repositories,common object shapes,tactile observations
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要