SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation
Name
2101.11812.pdf
Description
Accepted version
Size
25.2 MB
Format
Adobe PDF
Checksum (MD5)
210ad02755d6e2ccefb8bafa92d45190
Author(s)
Wang, Chen
Wang, Shaoxiong
Romero, Branden
Veiga, Filipe
Adelson, Edward
Date Issued
2020
Journal
IEEE International Conference on Intelligent Robots and Systems
Publisher
Institute of Electrical and Electronics Engineers (IEEE)
Citation
Wang, Chen, Wang, Shaoxiong, Romero, Branden, Veiga, Filipe and Adelson, Edward. 2020. "SwingBot: Learning Physical Features from In-hand Tactile Exploration for Dynamic Swing-up Manipulation." IEEE International Conference on Intelligent Robots and Systems.
Version
Author's final manuscript
Abstract
© 2020 IEEE. Several robot manipulation tasks are extremely sensitive to variations of the physical properties of the manipulated objects. One such task is manipulating objects by using gravity or arm accelerations, increasing the importance of mass, center of mass, and friction information. We present SwingBot, a robot that is able to learn the physical features of an held object through tactile exploration. Two exploration actions (tilting and shaking) provide the tactile information used to create a physical feature embedding space. With this embedding, SwingBot is able to predict the swing angle achieved by a robot performing dynamic swing-up manipulations on a previously unseen object. Using these predictions, it is able to search for the optimal control parameters for a desired swing-up angle. We show that with the learned physical features our end-to-end self-supervised learning pipeline is able to substantially improve the accuracy of swinging up unseen objects. We also show that objects with similar dynamics are closer to each other on the embedding space and that the embedding can be disentangled into values of specific physical properties.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1109/IROS45743.2020.9341006
