Grasping Force Prediction for Underactuated Multi-Fingered Hand by Using Artificial Neural Network
Abstract
In this paper, the feedforward neural network with Levenberg-Marquardt backpropagation training algorithm is used to predict the grasping forces according to the multisensory signals as training samples for specific design of underactuated multifingered hand to avoid the complexity of calculating the inverse kinematics which is appeared through the dynamic modeling of the robotic hand and preparing this network to be used as part of a control system.
Keywords: Grasping force, underactuated, prediction, Neural network
![Download the IISTE publication guideline!](https://www.iiste.org/sub/iiste_footer_journal.jpg)
To list your conference here. Please contact the administrator of this platform.
Paper submission email: CTI@iiste.org
ISSN (Paper)2224-5774 ISSN (Online)2225-0492
Please add our address "contact@iiste.org" into your email contact list.
This journal follows ISO 9001 management standard and licensed under a Creative Commons Attribution 3.0 License.
Copyright © www.iiste.org