Development of a sEMG-Based Joint Torque Estimation Strategy Using Hill-Type Muscle Model and Neural Network

A neural network system is presented for controlling a two-link dynamic arm model where the task is to move the arm from any initial position to any final position in the sagittal plane. The controller produces joint torque-lime profiles that begin and end with equilibrium values at the initial and final positions, respectively. A memory type neural network is trained by supervised learning methods to predict the joint's static equilibrium torque values corresponding to joint angles. A reinforcement learning network is used to determine the parameters needed for synthesis of the torque-time profiles for each joint. The reinforcement signal is computed based on the distance between the desired end point position and velocity and the states achieved based on the generated torque profiles. The general pattern of the torque-time plots is decided a priori according to the literature. The methods of training and an illustrative example of the algorithm's performance are presented.

Download Full-text

Parallel Wire Driven System for Joint Torque Estimation of Human Leg in Passive Motion

SICE Journal of Control Measurement and System Integration ◽

10.9746/jcmsi.5.70 ◽

2012 ◽

Vol 5 (2) ◽

pp. 70-77 ◽

Cited By ~ 1

Author(s):

Hitoshi KINO ◽

Kenichi SAISHO ◽

Tsutomu MIYAZOE ◽

Sadao KAWAMURA

Keyword(s):

Joint Torque ◽

Parallel Wire ◽

Passive Motion ◽

Torque Estimation ◽

Driven System

Download Full-text

A Power Assist Device Based on Joint Equilibrium Point Estimation from EMG Signals

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2012.p0205 ◽

2012 ◽

Vol 24 (1) ◽

pp. 205-218 ◽

Cited By ~ 15

Author(s):

Toshihiro Kawase ◽

◽

Hiroyuki Kambara ◽

Yasuharu Koike ◽

Keyword(s):

Equilibrium Point ◽

Equilibrium Points ◽

User Equilibrium ◽

Point Estimation ◽

Joint Torque ◽

Stable Operation ◽

Assist Devices ◽

User Intentions ◽

Torque Estimation ◽

Posture Maintenance

In some researches about power assist devices, surface ElectroMyoGraphy (EMG) signals are used to estimate user intentions to move their limbs. These conventional methods mainly focus on estimation of joint torque. However, the devices based on torque estimation are inclined to cause the vibration of users’ posture originating from the waviness of the EMG signals. Focusing on estimation of states related to the joint angle may improve the performance of the power assist devices. This paper proposes a new method that estimates user joint equilibrium point and stiffness separately from the EMG and that amplifies the stiffness while tuning the device joints according to user equilibrium points. To evaluate the method, we constructed a power assist system for the wrist and compared the method with a method based on simple torque estimation during posture maintenance tasks. Our results showed that the proposed method offers a more stable operation at the same assist ratio and proved the effectiveness of the method.

Download Full-text

Multifunctional Electrical Prosthetic Hand -Development of Tendon-driven Mechanism and Controller

Journal of Robotics and Mechatronics ◽

10.20965/jrm.2002.p0557 ◽

2002 ◽

Vol 14 (6) ◽

pp. 557-564 ◽

Cited By ~ 1

Author(s):

Wenwei Yu ◽

◽

Daisuke Nishikawa ◽

Yasuhiro Ishikawa ◽

Hiroshi Yokoi ◽

...

Keyword(s):

Neural Network ◽

Time Delay ◽

Recurrent Neural Network ◽

Network Models ◽

Joint Torque ◽

Prosthetic Hand ◽

Neural Network Models ◽

Nonlinear Properties ◽

The Stability

The purpose of this research was to develop a tendondriven electrical prosthetic hand, which is characterized by its mechanical torque-velocity converter and a mechanism that can assist proximal joint torque by distal actuators. To cope with time-delay and nonlinear properties of the prosthetic hand, a controller based on a Jordan network, recurrent neural network models, is proposed. The results of experiments on the stability of the controller are confirmed when tracking static wire tensions. Finally, the next prototype of prosthetic hand based on these methods is introduced.

Download Full-text