Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/1989
標題: 階層式類神經力量控制於工業機械臂之應用
Application of Hierarchical Neural Force Control for Industrial Robots
作者: 曾錫璋
Tzeng, Shyi-Jang
關鍵字: neural network;類神經網路;robot;force control;機械手臂;力量控制
出版社: 機械工程學系
摘要: 
在本篇論文中,我們提出一階層式類神經力量控制架構,並結合機
械臂內建之位置控制器、力量/扭矩感測器及個人電腦,實現工業機械臂
在力量控制方面的應用。由於機械臂內建之位置控制器只擁有位置控制的
功能,對於力量控制方面的應用便不敷使用。在本文中,將討論到以階層
式控制法結合力量/扭矩感測器來跨越機械臂內建之位置控制器在力量控
制上的限制。另外,為了改善對環境變化的適應能力,本文提出了一個類
神經力量控制架構以適應環境變化,並且將之應用於單臂及雙臂系統上,
而實驗結果證明其控制效果良好。本論文中亦探討了僅以力量/扭矩感測
器結合工業機械臂應用於插銷裝配的例子,並討論其所產生的問題及實驗
結果。

A hierarchical control framework that integrates the built in
position control-ler of an industrial robot, a BL Force/Torque
sensor, and a personal computeris proposed in this thesis to
complete the application of the MITSUBISHI MELFARV-M1 industrial
robot in force control. Since the industrial robot has builtin
position controller and don't allow direct access to actuator
torques, itcan not be used in the application of force control
directly. A hierarchicalcontrol scheme combined with a
Force/Torque sensor is proposed to overcomethis difficulty.In
order to improve the adaptive ability for the
environmentalvariation, a force control architecture based on
a neural network is used toadapt the change of environment and
has been applied on single arm and dual-arm systems.
Experimental results show that the force controller has
satisfac-tory performance. The discussion of peg-in-hole
insertion solely based on theproposed controller is presented,
and the experiment results are given.
URI: http://hdl.handle.net/11455/1989
Appears in Collections:機械工程學系所

Show full item record
 
TAIR Related Article

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.