Gait Parameter Identification of Lower Limb Exoskeleton based on Neural Network
DOI:
https://doi.org/10.54097/v8msr468Keywords:
Long short-term memory network (LSTM), GNN, recurrent neural network, parameter identification, gait recognition.Abstract
With the continuous development and improvement of related technologies, as well as the increasing aging of the population, the increasing demand for assisted walking equipment for the elderly and other issues, the lower limb exoskeleton will play a more important role in the field of rehabilitation medicine. The physical condition and rehabilitation needs of each patient are unique, and the lower limb exoskeleton based on neural network can automatically adjust the rehabilitation plan according to the specific situation of the patient to achieve personalized treatment. This personalized program can better meet the needs of patients and improve the rehabilitation effect. With the continuous development of artificial intelligence and robotics, lower limb exoskeleton based on neural network is expected to become an important direction of rehabilitation technology in the future, and its research results will bring revolutionary changes to the rehabilitation medical field. Therefore, based on the relevant theoretical knowledge of neural networks, this paper will explore and discuss several different neural network related algorithms, namely GNN, recurrent neural network, long short-term memory network (LSTM) combined with Conformer framework, and explore their specific effects on the parameter identification of lower limb exoskeleton and gait recognition.
Downloads
References
[1] Sun W. Research on parameter identification and control of lower limb exoskeleton based on DeLaN [D]. University of Electronic Science and Technology of China, 2023.
[2] Guo Z, Zhou S, Pan L. Research on lower limb exoskeleton robot design for elderly people based on Ergonomics [J]. Science and Technology Innovation, 2024, 20:205-208.
[3] Sun X, Yu X. A review of gait recognition systems for lower limb exoskeleton robots [J]. Artificial Intelligence,2024, 01:66-80.
[4] Li Y, Huang G, Xie L. Gait trajectory prediction of lower limb rehabilitation exoskeleton based on deep Learning [J]. Robot Technology and Application,2024, 04:28-32.
[5] JIANG Lu. Motion Planning and Adaptive Control of Mobile Manipulator in Man-machine Collaboration [D]. University of Science and Technology of China, 2021.
[6] Chen F, Hou Y, Li S. Inverse Kinematics of Manipulator Based on Improved Gated Recurrent Neural Network [J/OL]. Machine Design & Manufacture, 2024, 1-5.
[7] Zhou H, He Z, Zhou Y. Inverse Kinematics of Manipulator Based on Long Short-term Memory Network [J]. Machinery & Electronics, 2019, 38(06):74-80.
[8] Tay Y, Dehghani M, Bahri D, et al. Efficient transformers: A survey[J]. arXiv preprint arXiv: 2009: 06732,202.
[9] Gulati A, Qin J, Chiu C, et al. Conformer: Convolution-augmented Transformer for Speech Recognition[J]. arXiv preprint arXiv2005.08100,2020. DOI: https://doi.org/10.21437/Interspeech.2020-3015
[10] Zhao Z, Wang T, Bei T, et al. Lower limb exoskeleton gait prediction method based on LSTM and Conformer [J]. Computer Age, 2022, 08:1-5.
[11] Tian Q. Research on lower limb exoskeleton gait teaching based on inertial sensor data [D]. Qingdao University, 2023.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
