Generating synthetic gait patterns based on benchmark datasets for controlling prosthetic legs.
Generating synthetic gait patterns based on benchmark datasets for controlling prosthetic legs.
复制标题
DOI：
10.1186/s12984-023-01232-6
复制
发表时间：
2023-09-04
影响因子：
5.1
通讯作者：
Hargrove, Levi J.
中科院分区：
文献类型：
--
作者：
Kim, Minjae;Hargrove, Levi J.
Prosthetic legs help individuals with an amputation regain locomotion. Recently, deep neural network (DNN)-based control methods, which take advantage of the end-to-end learning capability of the network, have been proposed. One prominent challenge for these learning-based approaches is obtaining data for the training, particularly for the training of a mid-level controller. In this study, we propose a method for generating synthetic gait patterns (vertical load and lower limb joint angles) using a generative adversarial network (GAN). This approach enables a mid-level controller to execute ambulation modes that are not included in the training datasets. The conditional GAN is trained on benchmark datasets that contain the gait data of individuals without amputation; synthetic gait patterns are generated from the user input. Further, a DNN-based controller for the generation of impedance parameters is trained using the synthetic gait pattern and the corresponding synthetic stiffness and damping coefficients. The trained GAN generated synthetic gait patterns with a coefficient of determination of 0.97 and a structural similarity index of 0.94 relative to benchmark data that were not included in the training datasets. We trained a DNN-based controller using the GAN-generated synthetic gait patterns for level-ground walking, standing-to-sitting motion, and sitting-to-standing motion. Four individuals without amputation participated in bypass testing and demonstrated the ambulation modes. The model successfully generated control parameters for the knee and ankle based on thigh angle and vertical load. This study demonstrates that synthetic gait patterns can be used to train DNN models for impedance control. We believe a conditional GAN trained on benchmark datasets can provide reliable gait data for ambulation modes that are not included in its training datasets. Thus, designing gait data using a conditional GAN could facilitate the efficient and effective training of controllers for prosthetic legs. The online version contains supplementary material available at 10.1186/s12984-023-01232-6.
登录
查看更多内容
影响因子：
4.2
作者：
Hazra D;Byun YC
通讯作者：
Byun YC
影响因子：
5.2
作者：
Kim, Minjae;Hargrove, Levi J.
通讯作者：
Hargrove, Levi J.
DOI：
10.1109/tmrb.2022.3185405
发表时间：
2022-08
期刊：
IEEE TRANSACTIONS ON MEDICAL ROBOTICS AND BIONICS
影响因子：
--
作者：
Cheng, Shihao;Bolivar-Nieto, Edgar;Welker, Cara Gonzalez;Gregg, Robert D.
通讯作者：
Gregg, Robert D.
影响因子：
5.2
作者：
Wu, Ruofan;Li, Minhan;Huang, He
通讯作者：
Huang, He
DOI：
10.1109/jtehm.2016.2601613
发表时间：
2016
影响因子：
3.4
作者：
Lee H;Rouse EJ;Krebs HI
通讯作者：
Krebs HI