Page 68 - IJAMD-1-1

International Journal of AI

for Material and Design

ORIGINAL RESEARCH ARTICLE
Joint angle prediction for a cable-driven gripper

with variable joint stiffness through numerical
modeling and machine learning

1
Guo Liang Goh , Xi Huang , William Toh , Zhengchen Li , Samuel Lee , Van Pho
1
1
1
1
1,2
Nguyen , Wai Yee Yeong *, Boon Siew Han , and Teng Yong Ng 1
2
1
1 School of Mechanical and Aerospace Engineering, Nanyang Technological University, Singapore,
Republic of Singapore
2 Schaeffler Hub for Advanced Research, Nanyang Technological University, Singapore, Republic of
Singapore
Abstract
Soft grippers in automation, particularly those with variable joint stiffness, offer
promising possibilities for precise manipulation tasks. However, accurately
predicting finger joint bending angles in this field poses significant challenges
due to the soft and complex nature of the grippers, making modeling and angle
prediction difficult. This paper presents the development of a predictive model for
precisely controlling bending angles in multi-material printed soft grippers with
variable stiffness, which are pivotal for delicate manipulation tasks in automation.
In particular, we explore a cable-driven gripper design made of thermoplastic
polyurethane and conductive polylactic acid materials, featuring integrated resistive
joints for stiffness modulation through controlled Joule heating. A data-driven
*Corresponding author: modeling approach, combining numerical modeling of the gripper and machine
Wai Yee Yeong learning techniques, was employed for the development of the predictive model.
(wyyeong@ntu.edu.sg)
We performed static structural simulations using ANSYS Workbench to measure
Citation: Goh GL, Huang X, bending angles under various conditions for developing datasets for model training.
Toh W, et al. Joint angle prediction
for a cable-driven gripper with In this work, we evaluated several machine learning models such as linear regression,
variable joint stiffness through decision tree, and K-nearest neighbor regression models to predict the correlation
numerical modeling and machine between temperature, pull distance, and bending angle. The K-nearest neighbor
learning. Int J AI Mater Design.
2024;1(1):2328. regression model demonstrated the highest accuracy, with a mean absolute error
https://doi.org/10.36922/ijamd.2328 of approximately 11%. These findings underline the importance of precise angle
prediction models in enhancing the functionality and reliability of soft grippers,
Received: November 28, 2023
Accepted: January 10, 2024 paving the way for their broader application in automation and robotics.
Published Online: January 29, 2024
Copyright: © 2024 Author(s). Keywords: 3D printing; Variable stiffness gripper; Soft robotics; Machine learning;
This is an Open-Access article
distributed under the terms of the Numerical modeling
Creative Commons Attribution
License, permitting distribution,
and reproduction in any medium,
provided the original work is
properly cited. 1. Introduction
Publisher’s Note: AccScience Soft robotic grippers mark a revolutionary step in automation, providing an unmatched
Publishing remains neutral with level of adaptability and delicate manipulation that mirrors biological appendages and
regard to jurisdictional claims in 1
published maps and institutional surpasses the capabilities of traditional rigid grippers. The prior art in this domain
affiliations. is rich with a variety of technologies and actuation mechanisms, including examples

Volume 1 Issue 1 (2024) 62 https://doi.org/10.36922/ijamd.2328