Imperial College London
Portrait Picture

Dr Ad Spiers

Faculty of Engineering, Department of Electrical and Electronic Engineering

Lecturer in Robotics and Machine Learning
 
 
 
//

Contact

 

a.spiers

 
 
//

Location

 

Electrical EngineeringSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Spiers:2020:10.1109/toh.2019.2958669,
author = {Spiers, AJ and Morgan, AS and Srinivasan, K and Calli, B and Dollar, AM},
doi = {10.1109/toh.2019.2958669},
journal = {IEEE Transactions on Haptics},
pages = {600--610},
title = {Using a variable-friction robot hand to determine proprioceptive features for object classification during within-hand-manipulation},
url = {http://dx.doi.org/10.1109/toh.2019.2958669},
volume = {13},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - 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%.
AU  - Spiers,AJ
AU  - Morgan,AS
AU  - Srinivasan,K
AU  - Calli,B
AU  - Dollar,AM
DO  - 10.1109/toh.2019.2958669
EP  - 610
PY  - 2020///
SN  - 1939-1412
SP  - 600
TI  - Using a variable-friction robot hand to determine proprioceptive features for object classification during within-hand-manipulation
T2  - IEEE Transactions on Haptics
UR  - http://dx.doi.org/10.1109/toh.2019.2958669
UR  - https://ieeexplore.ieee.org/document/8930085
UR  - http://hdl.handle.net/10044/1/83115
VL  - 13
ER  -
Download