Skip to main content
SpringerLink
Log in

Real-time recognition of human lower-limb locomotion based on exponential coordinates of relative rotations

  • Article
  • Published:
Science China Technological Sciences Aims and scope Submit manuscript

Abstract

This paper proposes a data-driven method using a parametric representation of relative rotations to classify human lower-limb locomotion, which is designed for wearable robots. Three Inertial measurement units (IMUs) are mounted on the subject’s waist, left knee, and right knee, respectively. Features for classification comprise relative rotations, angular velocities, and waist acceleration. Those relative rotations are represented by the exponential coordinates. The rotation matrices are normalized by Karcher mean and then the Support Vector Machine (SVM) method is used to train the data. Experiments are conducted with a time-window size of less than 40 ms. Three SVM classifiers telling 3, 5 and 6 rough lower-limb locomotion types respectively are trained, and the average accuracies are all over 98%. With the combination of those rough SVM classifiers, an easy SVM-based ensembled-system is proposed to classify 16 fine locomotion types, achieving the average accuracy of 98.22%, and its latency is 18 ms when deployed to an onboard computer.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Sanz-Merodio D, Cestari M, Arevalo J C, et al. A lower-limb exoskeleton for gait assistance in quadriplegia. In: 2012 IEEE International Conference on Robotics and Biomimetics (ROBIO). Guangzhou, China, 2012. 122–127

  2. Chen D, Ning M, Zhang B, et al. An improvement to the reciprocating gait orthosis for aiding paraplegic patients in walking. Sci China Tech Sci, 2015, 58: 727–737

    Article  Google Scholar 

  3. Mooney L M, Rouse E J, Herr H M. Autonomous exoskeleton reduces metabolic cost of human walking during load carriage. J Neuroeng Rehabil, 2014, 11: 80

    Article  Google Scholar 

  4. Jatsun S, Malchikov A, Yatsun A. Automatization of manual labor by using an industrial exoskeleton. In: 2020 International Russian Automation Conference. Sochi, 2020. 470–475

  5. Sanchez-Villamañan M D C, Gonzalez-Vargas J, Torricelli D, et al. Compliant lower limb exoskeletons: A comprehensive review on mechanical design principles. J Neuroeng Rehabil, 2019, 16: 55

    Article  Google Scholar 

  6. Zhou Z, Liu X, Jiang Y, et al. Real-time onboard SVM-based human locomotion recognition for a bionic knee exoskeleton on different terrains. In: 2019 Wearable Robotics Association Conference (Wear- RAcon). Scottsdale, 2019. 34–39

  7. Zheng E, Wang Q, Qiao H. Locomotion mode recognition with robotic transtibial prosthesis in inter-session and inter-day applications. IEEE Trans Neural Syst Rehabil Eng, 2019, 27: 1836–1845

    Article  Google Scholar 

  8. Huo W, Mohammed S, Amirat Y, et al. Fast gait mode detection and assistive torque control of an exoskeletal robotic orthosis for walking assistance. IEEE Trans Robot, 2018, 34: 1–18

    Article  Google Scholar 

  9. Ding S, Ouyang X, Liu T, et al. Gait event detection of a lower extremity exoskeleton robot by an intelligent imu. IEEE Sens J, 2018, 18: 9728–9735

    Article  Google Scholar 

  10. Han Y L, Wang X S. The biomechanical study of lower limb during human walking. Sci China Tech Sci, 2011, 54: 983–991

    Article  Google Scholar 

  11. Hu B, Rouse E, Hargrove L. Fusion of bilateral lower-limb neuromechanical signals improves prediction of locomotor activities. Front Robot AI, 2018, 5: 78, doi: https://doi.org/10.3389/frobt.2018.00078

    Article  Google Scholar 

  12. Zhou Y, Liu J, Zeng J, et al. Bio-signal based elbow angle and torque simultaneous prediction during isokinetic contraction. Sci China Tech Sci, 2018, 62: 21–30

    Article  Google Scholar 

  13. Simao M, Mendes N, Gibaru O, et al. A review on electromyography decoding and pattern recognition for human-machine interaction. IEEE Access, 2019, 7: 39564–39582

    Article  Google Scholar 

  14. Fang C, He B, Wang Y, et al. EMG-centered multisensory based technologies for pattern recognition in rehabilitation: State of the art and challenges. Biosensors, 2020, 10: 85

    Article  Google Scholar 

  15. Preece S J, Goulermas J Y, Kenney L P J, et al. A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Trans Biomed Eng, 2009, 56: 871–879

    Article  Google Scholar 

  16. Mascret Q, Bielmann M, Fall C, et al. Real-time human physical activity recognition with low latency prediction feedback using raw IMU data. In: 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Honolulu, 2018. 239–242

  17. Liu X, Zhou Z, Wang Q. Real-time onboard human motion recognition based on inertial measurement units. In: 2018 IEEE 8th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER). Tianjin, China, 2018. 724–728

  18. Vemulapalli R, Rama C. Rolling rotations for recognizing human actions from 3D skeletal data. In: 2016 Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016. 4471–4479

  19. Huang Z, Wan C, Probst T, et al. Deep learning on lie groups for skeleton-based action recognition. Honolulu, 2017. 1243–1252

  20. Rhif M, Wannous H, Farah I R. Action recognition from 3D skeleton sequences using deep networks on lie group features. In: 2018 24th International Conference on Pattern Recognition (ICPR). Beijing, China, 2018. 3427–3432

  21. Li M, Zhao L. The classification of human lower limb motion based on acceleration sensor. In: 2016 IEEE Chinese Guidance, Navigation and Control Conference. Nanjing, China, 2016. 2210–2214

  22. Li H, Derrode S, Pieczynski W. An adaptive and on-line imu-based locomotion activity classification method using a triplet markov model. Neurocomputing, 2019, 362: 94–105

    Article  Google Scholar 

  23. Wan W, Liu H, Shi G, et al. Real-time recognition of multi-category human motion using µIMU data. In: International Conference on Mechatronics and Automation. Harbin, China, 2007. 1845–1850

  24. Murray R M, Li Z, Shankara S S. A Mathematical Introduction to Robot Manipulation. Boca Raton: CRC Press, 1994. 69–76

    Google Scholar 

  25. Lynch K M, Park F C. Modern Robotics. Cambridge: Cambridge Univeristy Press, 2017. 80–88

    Google Scholar 

  26. Huynh D Q. Metrics for 3D rotations: Comparison and analysis. J Math Imag Vis, 2009, 35: 155–164

    Article  MathSciNet  Google Scholar 

  27. Selig J M. Geometric Fundamentals of Robotics. New York: Springer Science & Business Media, 2005

    MATH  Google Scholar 

  28. Calinon S. Gaussians on riemannian manifolds: Applications for robot learning and adaptive control. IEEE Robot Automat Mag, 2020, 27: 33–45

    Article  Google Scholar 

  29. Taylor M J D, Dabnichki P, Strike S C. A three-dimensional biomechanical comparison between turning strategies during the stance phase of walking. Human Movement Sci, 2005, 24: 558–573

    Article  Google Scholar 

  30. Hsu Y L, Yang S C, Chang H C, et al. Human daily and sport activity recognition using a wearable inertial sensor network. IEEE Access, 2018, 6: 31715–31728

    Article  Google Scholar 

  31. Martinez-Hernandez U, Dehghani-Sanij A A. Adaptive bayesian inference system for recognition of walking activities and prediction of gait events using wearable sensors. Neural Networks, 2018, 102: 107–119

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

    Sen Xu & Ye Ding

Authors
  1. Sen Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ye Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ye Ding.

Additional information

This work was supported by the National Natural Science Foundation of China (Grant No. 91948302).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, S., Ding, Y. Real-time recognition of human lower-limb locomotion based on exponential coordinates of relative rotations. Sci. China Technol. Sci. 64, 1423–1435 (2021). https://doi.org/10.1007/s11431-020-1802-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11431-020-1802-2

Keywords

Search

Navigation