Hostname: page-component-7dd5485656-frp75 Total loading time: 0 Render date: 2025-10-30T12:09:49.326Z Has data issue: false hasContentIssue false
  • English
  • Français

Prediction of walking direction based on foot rotation angle features

Published online by Cambridge University Press:  30 October 2025

Dianchun Bai ,
Jinli Dai Open the ORCID record for Jinli Dai [Opens in a new window] ,
Zhuo Liu ,
Ruiji Li ,
Fenghao Gong ,
Zhongpeng Lin ,
Yinlai Jiang Open the ORCID record for Yinlai Jiang [Opens in a new window]  and
Hiroshi Yokoi
Dianchun Bai*
Affiliation:
School of Electrical Engineering, Shenyang University of Technology , Shenyang, Liaoning, 110870, China Center for Neuroscience and Biomedical Engineering, University of Electro-Communications, Tokyo, 182-8585, Japan
Jinli Dai
Affiliation:
School of Electrical Engineering, Shenyang University of Technology , Shenyang, Liaoning, 110870, China
Zhuo Liu
Affiliation:
School of Electrical Engineering, Shenyang University of Technology , Shenyang, Liaoning, 110870, China
Ruiji Li
Affiliation:
School of Electrical Engineering, Shenyang University of Technology , Shenyang, Liaoning, 110870, China
Fenghao Gong
Affiliation:
School of Electrical Engineering, Shenyang University of Technology , Shenyang, Liaoning, 110870, China
Zhongpeng Lin
Affiliation:
School of Electrical Engineering, Shenyang University of Technology , Shenyang, Liaoning, 110870, China
Yinlai Jiang
Affiliation:
Center for Neuroscience and Biomedical Engineering, University of Electro-Communications, Tokyo, 182-8585, Japan
Hiroshi Yokoi
Affiliation:
Center for Neuroscience and Biomedical Engineering, University of Electro-Communications, Tokyo, 182-8585, Japan
*
Corresponding author: Dianchun Bai; Email: baidianchun@sut.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

In the context of an aging population and declining birth rates, the advantages of robotic-assisted training are becoming increasingly prominent. However, improving the adaptability and safety of assistive walking robots remains a critical challenge. Accurately identifying a user’s turning intent is essential for preventing dangerous situations such as falls or slips. As one of the core parameters of lower limb motion, foot rotation angles not only reflect the stability and coordination of gait but are also crucial for accurately predicting walking intentions, such as straight walking and turning. This study proposes a gated recurrent unit-based model for predicting foot rotation angles, driven by 3D visual data. By constructing a lower limb linkage model that includes foot joints and incorporating 3D foot rotation angle features, we develop a real-time algorithm for gait state prediction. This model enables accurate prediction of walking intentions, such as straight walking or turning, during walking and is experimentally validated using a robotic walker. The experimental results demonstrate the effectiveness of the proposed predictive model.

Keywords

electronic walkermachine visiondepth learningbehavior prediction

Information

Type
Research Article
Information
Robotica , First View , pp. 1 - 16
Copyright
© The Author(s), 2025. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Linder, T., Vaskevicius, N., Schirmer, R. and Arras, K. O., “Cross-Modal Analysis of Human Detection for Robotics: An Industrial Case Study,” In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE, 2021) pp. 971–978.Google Scholar
Rokhmanova, N., Kuchenbecker, K. J., Shull, P. B., Ferber, R. and Halilaj, E., “Predicting knee adduction moment response to gait retraining with minimal clinical data,” PLOS Comput. Biol. 18(5), e1009500 (2022).10.1371/journal.pcbi.1009500CrossRefGoogle ScholarPubMed
Faraji, S. and Ijspeert, A. J., “Scalable closed-form trajectories for periodic and non-periodic human-like walking,” In: International Conference on Robotics and Automation (ICRA) (IEEE, 2019) pp. 5295–5301.10.1109/ICRA.2019.8793877CrossRefGoogle Scholar
Brederecke, J., “Freezing of gait prediction from accelerometer data using a simple 1D-convolutional neural network – 8th place solution for Kaggle’s parkinson’s freezing of gait prediction competition,” arxiv preprint arxiv:2307.03475 (2023).Google Scholar
Su, B. and Gutierrez-Farewik, E. M., “Gait trajectory and gait phase prediction based on an LSTM network,” Sensors 20(24), 7127 (2020).10.3390/s20247127CrossRefGoogle Scholar
Kidziński, Ł., Delp, S. and Schwartz, M., “Automatic real-time gait event detection in children using deep neural networks,”  PloS one 14(1), e0211466 (2019).10.1371/journal.pone.0211466CrossRefGoogle ScholarPubMed
Kapsalyamov, A., Hussain, S., Goecke, R., Brown, N. A. and Jamwal, P. K., “Customized stiffness control strategy for a six-bar linkage-based gait rehabilitation robot,” Robotica 42(10), 3398–3415 (2024).10.1017/S0263574724001425CrossRefGoogle Scholar
Liu, T., Bai, D., Yi, H. and Yokoi, H., “Prediction of abnormal gait behavior of lower limbs based on depth vision,” Robotica 43(1), 47–68 (2025).10.1017/S0263574724000948CrossRefGoogle Scholar
Malin-Mayor, C., Adeli, V., Sabo, A., Noritsyn, S., Gorodetsky, C., Fasano, A., Iaboni, A. and Taati, B., “Pose2Gait: Extracting Gait Features From Monocular Video of Individuals with Dementia,” In: International Workshop On PRedictive Intelligence In MEdicine 2023, (Springer, 2023) pp. 265–276.Google Scholar
Fang, H.-S., Li, J., Tang, H., Xu, C., Zhu, H., Xiu, Y., Li, Y.-L. and Lu, C., “Alphapose: Whole-body regional multi-person pose estimation and tracking in real-time,” IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7157–7173 (2023).10.1109/TPAMI.2022.3222784CrossRefGoogle ScholarPubMed
Molinaro, D. D., Kang, I., Camargo, J., Gombolay, M. C. and Young, A. J., “Subject-independent, biological hip moment estimation during multimodal overground ambulation using deep learning,” IEEE Trans. Med. Robot. 4(1), 219–229 (2022).10.1109/TMRB.2022.3144025CrossRefGoogle Scholar
Zang, C., Pei, M. and Kong, Y., “Few-shot Human Motion Prediction Via Learning Novel Motion Dynamics,” In: Proceedings of the Twenty-Ninth International Conference on International Joint Conferences on Artificial Intelligence 2021 (IJCAI, 2021) pp. 846–852.Google Scholar
Yu, S., Nakata, Y., Nakamura, Y. and Ishiguro, H., “Joint angle synergy-based humanoid robot motion generation with fascia-inspired nonlinear constraints,” Robotica 42(8), 2566–2588 (2024).10.1017/S0263574724000961CrossRefGoogle Scholar
Mani, N., Haridoss, P. and George, B., “A wearable ultrasonic-based ankle angle and toe clearance sensing system for gait analysis,” IEEE Sens. J. 21(6), 8593–8603 (2021).10.1109/JSEN.2020.3047900CrossRefGoogle Scholar
Yang, G., Heo, J. and Kang, B. B., “Adaptive vision-based gait environment classification for soft ankle exoskeleton,” In Actuators, 13(11), 428 MDPI (2024).Google Scholar
Standardization Technical Committee for Ergonomics of China (SAC/TC7), “Gb/t 10000-2023: Anthropometric dimensions for adults in China,” (Beijing, Standards Press of China, 2023).Google Scholar
Yadav, M. and Alam, M. A., “Dynamic time warping (DTW) algorithm in speech: A review,” IJRECE 6(1), 524–528 (2018).Google Scholar