Related Experiment Video
Updated: Apr 19, 2026
06:58
A Structured Rehabilitation Protocol for Improved Multifunctional Prosthetic Control: A Case Study
Published on: November 6, 2015
10.4K
Modulation of grasping force in prosthetic hands using neural network-based predictive control.
Cristian F Pasluosta1, Alan W L Chiu
1Electronics Core-Medical Device Solutions, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA.
Methods in Molecular Biology (Clifton, N.J.)
|December 16, 2014
Summary
This study introduces a neural network controller for prosthetic hands, addressing challenges in precise electromechanical control. Simulations show this approach is feasible for daily living activities.
Area of Science:
- Biomedical Engineering
- Robotics
- Artificial Intelligence
Background:
- Prosthetic hand control faces challenges due to complex electromechanical nonlinearities.
- Existing model-based controllers may struggle with these intricate dynamics.
Purpose of the Study:
- To implement a neural network-based predictive control system for prosthetic hand actuation.
- To model the complex finger dynamics of prosthetic devices using neural networks.
Main Methods:
- Development of a neural network-based predictive control system.
- Utilizing neural network-based modeling to capture finger dynamics.
- Simulation of control system performance in daily living scenarios.
Main Results:
- Demonstrated feasibility of the neural network-based predictive control system.
- Successfully modeled complex electromechanical nonlinearities of the prosthetic hand.
- Simulations indicated effective performance in realistic daily activities.
Conclusions:
- Neural network-based predictive control is a viable solution for precise prosthetic hand operation.
- This technique effectively addresses the nonlinearities inherent in prosthetic devices.
- The proposed system shows promise for enhancing prosthetic hand functionality in daily life.
