Task-Based LSTM Kinematic Modeling for a Tendon-Driven Flexible Surgical Robot

Tendon-driven flexible surgical robots are normally suffering from the inaccurate modeling and imprecise motion control problems due to the nonlinearities of tendon transmission. Learning-based approaches are experimental data-driven with uncertainties modeled empirically, which can be adopted to im...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical robotics and bionics 2022-05, Vol.4 (2), p.339-342
Main Authors: Bai, Weibang, Cursi, Francesco, Guo, Xiaotong, Huang, Baoru, Lo, Benny, Yang, Guang-Zhong, Yeatman, Eric M.
Format: Article
Language:English
Subjects:
Data models
Elbow
Kinematics
learning modeling
LSTM (long short-term memory) network
Modelling
Motion control
Robot control
Robot sensing systems
Robots
surgical robot
Task analysis
tendon-driven
Tendons
Trajectory planning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Tendon-driven flexible surgical robots are normally suffering from the inaccurate modeling and imprecise motion control problems due to the nonlinearities of tendon transmission. Learning-based approaches are experimental data-driven with uncertainties modeled empirically, which can be adopted to improve the inevitable issues. This work proposes a LSTM-based kinematic modeling approach with task-based data for a flexible tendon-driven surgical robot to improve the control accuracy. Real experiments demonstrated the effectiveness and superiority of the proposed learned model when completing path following tasks, especially compared to the traditional modeling.
ISSN:2576-3202
2576-3202
DOI:10.1109/TMRB.2021.3127366