EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Motion Intention Recognition Method for Lower-Limb Exoskeleton Assistance in Ultra-High-Voltage Transmission Tower Climbing

Haoyuan Chen, Yalun Liu, Ming Li, Zhan Yang, Hongwei Hu, Xingqi Wu, Xingchao Wang, Hanhong Shi, Zhao Guo iD

Sensors · 10.04.2026 · 26 (8) · 2346

DOI: 10.3390/s26082346 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 10.04.2026. Verfasst von Haoyuan Chen und 8 weiteren Autor:innen. Beteiligte Einrichtung: State Grid Hubei Electric Power Co., Ltd., Exta High Voltage Company, Wuhan 430050, China. Hauptthemen laut MEDLINE: Exoskeleton Device, Lower Extremity. Die Arbeit nennt 25 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Science and Technology Project of State Grid Hubei Electric Power Co., Ltd., The Key Research and Development Program of Hubei Province, Science and Technology Project of State Grid Hubei Electric Power Co., Ltd..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Transmission tower climbing is a critical specialized operation in ultra-high-voltage power maintenance and communication infrastructure servicing. However, existing lower-limb exoskeletons used for tower climbing still suffer from insufficient motion intention recognition accuracy under complex operational environments. To address this issue, this study proposes an inertial measurement unit (IMU)-based bidirectional temporal deep learning method for motion intention recognition. First, a one-dimensional convolutional neural network (1D-CNN) is employed to extract local temporal features from multi-channel IMU signals. Subsequently, a bidirectional long short-term memory network (Bi-LSTM) is introduced to model the forward and backward temporal dependencies of motion sequences. Furthermore, a temporal attention mechanism is incorporated to emphasize discriminative features at critical movement phases, enabling the precise recognition of short-duration and transitional motions. Experimental results demonstrate that the proposed method outperforms traditional machine learning approaches and unidirectional temporal models in terms of accuracy, F1-score, and other evaluation metrics. In particular, this method demonstrates significant advantages in identifying the flexion/extension phases and transitional states. This study provides an offline method for analyzing movement intentions in lower-limb exoskeleton control for power transmission tower climbing scenarios and offers a reference for developing assistive control strategies for assisted climbing tasks in this specific context.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Exoskeleton DeviceLower ExtremityHumansLong Short Term MemoryMovementConvolutional Neural NetworksMotionAlgorithmsIntentionMachine Learning

Stichwörter der Autor:innen

bidirectional long short-term memory (Bi-LSTM)lower-limb exoskeletonmotion intention recognitiontemporal attention mechanismtransmission tower climbing

Autor:innen und Institutionen

  • State Grid Hubei Electric Power Co., Ltd., Exta High Voltage Company, Wuhan 430050, China.
  • School of Robotics, Wuhan University, Wuhan 430072, China.

ORCID-Profile: Zhao Guo

Förderung

  • The Science and Technology Project of State Grid Hubei Electric Power Co., Ltd.
  • The Key Research and Development Program of Hubei Province
  • Science and Technology Project of State Grid Hubei Electric Power Co., Ltd.
  • Key Research and Development Program of Hubei Province

Zitieren

APA

Chen, H., Liu, Y., Li, M., Yang, Z., Hu, H., Wu, X., Wang, X., Shi, H., & Guo, Z. (2026). A Motion Intention Recognition Method for Lower-Limb Exoskeleton Assistance in Ultra-High-Voltage Transmission Tower Climbing. Sensors, 26(8), 2346. https://doi.org/10.3390/s26082346

Vancouver

Chen H, Liu Y, Li M, Yang Z, Hu H, Wu X, et al. A Motion Intention Recognition Method for Lower-Limb Exoskeleton Assistance in Ultra-High-Voltage Transmission Tower Climbing. Sensors. 2026;26(8):2346. doi:10.3390/s26082346

BibTeX
@article{Chen2026,
  author = {Chen, Haoyuan and Liu, Yalun and Li, Ming and Yang, Zhan and Hu, Hongwei and Wu, Xingqi and Wang, Xingchao and Shi, Hanhong and Guo, Zhao},
  title = {A Motion Intention Recognition Method for Lower-Limb Exoskeleton Assistance in Ultra-High-Voltage Transmission Tower Climbing},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {8},
  pages = {2346},
  doi = {10.3390/s26082346}
}
Kostenlos starten →