Using a Variable-Friction Robot Hand to Determine Proprioceptive Features for Object Classification During Within-Hand-Manipulation
Interactions with an object during within-hand manipulation (WIHM) constitutes an assortment of gripping, sliding, and pivoting actions. In addition to manipulation benefits, the re-orientation and motion of the objects within-the-hand also provides a rich array of additional haptic information via the interactions to the sensory organs of the hand. In this article, we utilize variable friction (VF) robotic fingers to execute a rolling WIHM on a variety of objects, while recording "proprioceptive" actuator data, which is then used for object classification (i.e., without tactile sensors). Rather than hand-picking a select group of features for this task, our approach begins with 66 general features, which are computed from actuator position and load profiles for each object-rolling manipulation, based on gradient changes. An Extra Trees classifier performs object classification while also ranking each feature's importance. Using only the six most-important "Key Features" from the general set, a classification accuracy of 86% was achieved for distinguishing the six geometric objects included in our data set. Comparatively, when all 66 features are used, the accuracy is 89.8%.
| Author(s): | Adam J. Spiers and Andrew S. Morgan and Krishnan Srinivasan and Berk Calli and Aaron M. Dollar |
| Journal: | IEEE Transactions on Haptics |
| Volume: | 13 |
| Number (issue): | 3 |
| Pages: | 600--610 |
| Year: | 2020 |
| Month: | July |
| BibTeX Type: | Article (article) |
| DOI: | 10.1109/TOH.2019.2958669 |
| State: | Published |
| Electronic Archiving: | grant_archive |
BibTeX
@article{Spiers20-TH-Variable,
title = {Using a Variable-Friction Robot Hand to Determine Proprioceptive Features for Object Classification During Within-Hand-Manipulation},
journal = {IEEE Transactions on Haptics},
abstract = {Interactions with an object during within-hand manipulation (WIHM) constitutes an assortment of gripping, sliding, and pivoting actions. In addition to manipulation benefits, the re-orientation and motion of the objects within-the-hand also provides a rich array of additional haptic information via the interactions to the sensory organs of the hand. In this article, we utilize variable friction (VF) robotic fingers to execute a rolling WIHM on a variety of objects, while recording "proprioceptive" actuator data, which is then used for object classification (i.e., without tactile sensors). Rather than hand-picking a select group of features for this task, our approach begins with 66 general features, which are computed from actuator position and load profiles for each object-rolling manipulation, based on gradient changes. An Extra Trees classifier performs object classification while also ranking each feature's importance. Using only the six most-important "Key Features" from the general set, a classification accuracy of 86% was achieved for distinguishing the six geometric objects included in our data set. Comparatively, when all 66 features are used, the accuracy is 89.8%.},
volume = {13},
number = {3},
pages = {600--610},
month = jul,
year = {2020},
author = {Spiers, Adam J. and Morgan, Andrew S. and Srinivasan, Krishnan and Calli, Berk and Dollar, Aaron M.},
doi = {10.1109/TOH.2019.2958669},
month_numeric = {7}
}