3D shape perception from monocular vision, touch, and shape priors
Name
1808.03247.pdf
Description
Accepted version
Size
8.54 MB
Format
Adobe PDF
Checksum (MD5)
91ad5c1c36b545ac838e9d54b3dc8b20
Author(s)
Wang, Shaoxiong
Wu, Jiajun
Sun, Xingyuan
Yuan, Wenzhen
Freeman, William T.
Tenenbaum, Joshua B.
Adelson, Edward H.
Date Issued
October 2018
Citation
S. Wang et al., "3D shape perception from monocular vision, touch, and shape priors." Digest, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, October 1-5, 2018 (Piscataway, N.J.: IEEE, 2018): p. 1606-13 doi 10.1109/IROS.2018.8593430 ©2018 Author(s)
Version
Author's final manuscript
Abstract
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. ©2018
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/IROS.2018.8593430
