[1]陈辉,宋爱国,黄惟一.人手抓取特性与机械手神经网络抓取策略[J].东南大学学报(自然科学版),1999,29(2):18-22.[doi:10.3969/j.issn.1001-0505.1999.02.004]
 Chen Hui,Song Aiguo,Huang Weiyi.Human Grasp Property and Robot Hand Grasp Tactics about Neural Networks[J].Journal of Southeast University (Natural Science Edition),1999,29(2):18-22.[doi:10.3969/j.issn.1001-0505.1999.02.004]
点击复制

人手抓取特性与机械手神经网络抓取策略()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
29
期数:
1999年第2期
页码:
18-22
栏目:
自动化
出版日期:
1999-03-20

文章信息/Info

Title:
Human Grasp Property and Robot Hand Grasp Tactics about Neural Networks
作者:
陈辉 宋爱国 黄惟一
东南大学仪器科学与工程系,南京 210096
Author(s):
Chen Hui Song Aiguo Huang Weiyi
Department of Instrument Science and Technology, Southeast University, Nanjing 210096
关键词:
抓取 姿态 虚拟手指 神经网络
Keywords:
hand grasp posture virtual finger neural networks
分类号:
TP249
DOI:
10.3969/j.issn.1001-0505.1999.02.004
摘要:
分析了人手抓取的各种姿态,提出了3种基本的抓取姿态结构,并举例说明了人手的姿态可分解为3种基本姿态的组合. 基于人手的灵巧性,机械手的抓取可模仿人手的抓取特性,根据姿态、物体、任务之间的关系提出了神经网络规划的抓取方法,并设计了相应的神经网络.
Abstract:
The human hand is very dexterous in the operation. According to demand of task, human can do many complex tasks using different posture. This paper analyses various of postures, puts forward three basic postures, and explains that human hand posture is made of three basic postures. Because of the dexterity of human hand, robot hand can imitate human hand. In the last, we design neural networks according to the relationship of posture, object and task.

参考文献/References:

[1] Iberall T.Human prehension and dexterous robot hands.The Int Journal of Robotics Research,1997,16(3):285~299
[2] Iberall T.The nature of human prehension:three dexterous hands in one.IEEE Int Conf Robotics and Automation,1987,396~401

备注/Memo

备注/Memo:
基金项目:国家高技术航天领域863—2—7资助项目.
更新日期/Last Update: 1999-03-20