Inverse kinematics of a 6 DoF human upper limb using ANFIS and ANN for anticipatory actuation in ADL-based physical Neurorehabilitation

详细信息	查看全文 | 推荐本文 |

• 作者：Rodrigo Pé ; rez-Rodrí ; guez^a ; ^b ; ^{rperez@gbt.tfo.upm.es} ; Alexis Marcano-Cedeñ ; o^a ; ^b ; Ú ; rsula Costa^c ; Javier Solana^a ; ^b ; Cé ; sar Cá ; ceres^a ; ^b ; Eloy Opisso^c ; Josep M. Tormos^c ; Josep Medina^c ; Enrique J. Gó ; mez^a ; ^b
• 关键词：Inverse kinematics ; Upper limb ; Neurorehabilitation ; Activities of the daily living ; Biomechanical model ; Motion prediction
• 刊名：Expert Systems with Applications
• 出版年：2012
• 期刊代码：62_09574174
• 类别：et
• 出版时间：August, 2012
• 卷：39
• 期：10
• 页码：9612-9622
• 文件大小：1828 K

摘要

Objective

This research is focused in the creation and validation of a solution to the inverse kinematics problem for a 6 degrees of freedom human upper limb. This system is intended to work within a real-time dysfunctional motion prediction system that allows anticipatory actuation in physical Neurorehabilitation under the assisted-as-needed paradigm. For this purpose, a multilayer perceptron-based and an ANFIS-based solution to the inverse kinematics problem are evaluated.

Materials and methods

Both the multilayer perceptron-based and the ANFIS-based inverse kinematics methods have been trained with three-dimensional Cartesian positions corresponding to the end-effector of healthy human upper limbs that execute two different activities of the daily life: 鈥榮erving water from a jar鈥?and 鈥榩icking up a bottle鈥? Validation of the proposed methodologies has been performed by a 10 fold cross-validation procedure.

Results

Once trained, the systems are able to map 3D positions of the end-effector to the corresponding healthy biomechanical configurations. A high mean correlation coefficient and a low root mean squared error have been found for both the multilayer perceptron and ANFIS-based methods.

Conclusions

The obtained results indicate that both systems effectively solve the inverse kinematics problem, but, due to its low computational load, crucial in real-time applications, along with its high performance, a multilayer perceptron-based solution, consisting in 3 input neurons, 1 hidden layer with 3 neurons and 6 output neurons has been considered the most appropriated for the target application.