TY - GEN
T1 - Machine Leaning-Based Method for Kinematics Parameters Identification of Twin-Pivot Cable-Driven Continuum Robots
AU - Yang, Zheshuai
AU - Lan, Yu
AU - Yang, Dong
AU - Yang, Laihao
AU - Sun, Yu
AU - Chen, Xuefeng
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Twin-pivot cable-driven continuum robots have been widely employed in complex and unstructured scenarios, benefiting from their compliant and torsion-resistant properties. However, significant numbers of sections lead to a challenging problem in solving the inverse kinematics/statics. And the conventional Jacobian-based method suffers from complex computation, which is time-consuming. This paper proposed a machine learning-based method to identify kinematics parameters. First and foremost, an accurate static model is established. And then, the multi-layer perceptron (MLP) is employed to learn the inverse statics based on the large numbers of samples generated by the proposed static model. Finally, the verification of the proposed models is performed. The experimental results indicate that the mean absolute percentage error of cable lengths is within 2.2%, and the tip position error is within 1.6%.
AB - Twin-pivot cable-driven continuum robots have been widely employed in complex and unstructured scenarios, benefiting from their compliant and torsion-resistant properties. However, significant numbers of sections lead to a challenging problem in solving the inverse kinematics/statics. And the conventional Jacobian-based method suffers from complex computation, which is time-consuming. This paper proposed a machine learning-based method to identify kinematics parameters. First and foremost, an accurate static model is established. And then, the multi-layer perceptron (MLP) is employed to learn the inverse statics based on the large numbers of samples generated by the proposed static model. Finally, the verification of the proposed models is performed. The experimental results indicate that the mean absolute percentage error of cable lengths is within 2.2%, and the tip position error is within 1.6%.
KW - continuum robot
KW - inverse statics
KW - multi-layer perceptron (MLP)
KW - static model
UR - https://www.scopus.com/pages/publications/85150424298
U2 - 10.1109/ICSMD57530.2022.10058226
DO - 10.1109/ICSMD57530.2022.10058226
M3 - 会议稿件
AN - SCOPUS:85150424298
T3 - 2022 International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022 - Proceedings
BT - 2022 International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 3rd International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022
Y2 - 22 December 2022 through 24 December 2022
ER -