Using a Variable-Friction Robot Hand to Determine Proprioceptive Features for Object Classification During Within-Hand-Manipulation

Using a Variable-Friction Robot Hand to Determine Proprioceptive Features for Object Classification During Within-Hand-Manipulation
复制标题

使用可变摩擦机器人手确定手内操作过程中物体分类的本体感觉特征

DOI:
10.1109/toh.2019.2958669
复制
发表时间:
2020
影响因子:
2.9
通讯作者:
Dollar, Aaron M.
Dollar, Aaron M.
中科院分区:
计算机科学3区
文献类型:
--
作者:
Spiers, Adam J.;Morgan, Andrew S.;Srinivasan, Krishnan;Calli, Berk;Dollar, Aaron M.

文献摘要

参考文献

被引文献

相似文献

手内操作(WIHM)过程中与对象的交互包括抓握、滑动和旋转动作。除了操纵益处之外,对象在手中的重新定向和运动还经由与手的感觉器官的交互提供了丰富的附加触觉信息阵列。在这篇文章中,我们利用可变摩擦(VF)机器人手指在各种物体上执行滚动WIHM,同时记录“本体感受”致动器数据,然后用于物体分类(即,没有触觉传感器)。而不是手工挑选一组选择的功能,这项任务,我们的方法开始与66个一般功能,这是计算从致动器的位置和负载配置文件为每个对象滚动操作,基于梯度变化。Extra Trees分类器执行对象分类,同时还对每个特征的重要性进行排名。只使用六个最重要的“关键特征”从一般的集合,实现了86%的分类精度区分六个几何对象包括在我们的数据集。相比之下,当使用所有66个特征时,准确率为89.8%。
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%.
使用滑动运动通过三指手处理物体
DOI: --
发表时间: 1992
期刊: IEEE/RJS International Conference on Intelligent RObots and Systems
影响因子: --
作者:
T. Yoshikawa;Y. Yokokohji;A. Nagayama
通讯作者: A. Nagayama
使用带有高速触觉传感器的高速多指手进行动态笔旋转
DOI: --
发表时间: 2006
期刊:
影响因子: --
作者:
Tatsuya Ishihara;Akio Namiki;Masatoshi Ishikawa;and Makoto Shimojo
通讯作者: and Makoto Shimojo
DOI: --
发表时间: 1992
期刊: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems
影响因子: --
作者:
P. Dario;P. Ferrante;G. Giacalone;L. Livaldi;B. Allotta;G. Buttazzo;A. Sabatini
通讯作者: A. Sabatini
通过协调扭矩/速度控制的手指进行全臂物体操纵的迭代学习控制
DOI: --
发表时间: 2015
期刊: IEEE/RJS International Conference on Intelligent RObots and Systems
影响因子: --
作者:
M. Yashima;T. Yamawaki
通讯作者: T. Yamawaki
使用行为探索和多模态感知来学习关系对象类别
DOI: 10.1109/icra.2014.6907696
发表时间: 2014
期刊: 2014 IEEE International Conference on Robotics and Automation (ICRA)
影响因子: --
作者:
Jivko Sinapov;Connor Schenck;Alexander Stoytchev
通讯作者: Alexander Stoytchev