Research on human gait prediction and recognition algorithm of lower limb-assisted exoskeleton robot


Wearable lower limb-assisted exoskeleton robot can improve a human's ability to walk long distances under heavy load. Accurate perception and recognition of human lower limb motion and real-time input of exoskeleton control system parameters have always been the key technologies of wearing lower limb assist exoskeleton robot. To solve the problem of poor real-time and stability of the lower extremity exoskeleton system caused by time delay in transmitting gait information from the lower extremity assisted exoskeleton robot perception system to the control system, we proposed a new human gait prediction and recognition algorithm. Based on the gait sample data of human lower limbs, we proposed a prediction algorithm concerning least-squares support vector regression (LS-SVR) to predict the gait data at the next moment of human lower limbs movement. We proposed a human gait phase recognition algorithm using fuzzy theory to identify the gait phase at the next moment of human lower limb movement. The proposed algorithm can identify the heel landing phase, the load-supporting phase, the pre-swing phase, and the swing phase of human lower limbs. Experimental results demonstrate that gait prediction accuracy is 99.83% and the gait phase recognition rate based on the predicted gait data of 120 complete gait cycles is 99.93%. It comes up to a feasible method for wearable lower limb-assisted exoskeleton robot intelligent perception technology. New algorithms improve the recognition rate of gait phase prediction and effectively improve the real-time, stability, and robustness of the lower extremity exoskeleton robot system. The proposed gait prediction and recognition model can help gait recognition tasks to overcome the difficulties in real application scenarios and provide a feasible method for a lower extremity assisted exoskeleton robot perception system.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12


  1. 1.

    Mcgrath RL, Ziegler ML, Piresfernandes M et al (2019) The effect of stride length on lower extremity joint kinetics at various gait speeds. PLOS ONE 14(2):e0200862

    Article  Google Scholar 

  2. 2.

    Ding S, Ouyang X, Liu T et al (2018) Gait event detection of a lower extremity exoskeleton robot by an intelligent IMU[J]. IEEE Sens J 18(23):9728–9735

    Article  Google Scholar 

  3. 3.

    Chia Bejarano N, Ambrosini E, Pedrocchi A, Ferrigno G, Monticone M, Ferrante S (2015) A novel adaptive, real-time algorithm to detect gait events from wearable sensors. IEEE Trans Neural Syst Rehabilit Eng 23(3):413–422

    Article  Google Scholar 

  4. 4.

    Luo J, Tjahjadi T (2020) Gait recognition and understanding based on hierarchical temporal memory using 3D gait semantic folding. Sensors 20:1646

    Article  Google Scholar 

  5. 5.

    Davarzani S, Saucier D, Peranich P, Carroll W, Turner A, Parker E, Middleton C, Nguyen P, Robertson P, Smith B, Ball J, Burch R, Chander H, Knight A, Prabhu R, Luczak T (2020) Closing the wearable gap-part VI: human gait recognition using deep learning methodologies. Electronics 9:796

    Article  Google Scholar 

  6. 6.

    Lishani AO, Boubchir L, Khalifa E et al (2019) Human gait recognition using GEI-based local multi-scale feature descriptors. Multimed Tools Appl 78:5715–5730

    Article  Google Scholar 

  7. 7.

    Akhil VM, Ashmi M, Rajendrakumar PK et al (2020) Human gait recognition using hip, knee and ankle joint ratios. IRBM 41(3):133–140

    Article  Google Scholar 

  8. 8.

    Leclair J, Pardoel S, Helal A et al (2020) Development of an unpowered ankle exoskeleton for walking assist[J]. Disabil Rehabil Assist Technol 15(1):1–13

    Article  Google Scholar 

  9. 9.

    Madden JD (2007) Mobile robots: motor challenges and materials solutions [J]. Science 318(5853):1094–1097

    Article  Google Scholar 

  10. 10.

    Nolan KJ, Ehrenberg N, Kesten AG, et al. (2018) Robotic exoskeleton gait training for inpatient rehabilitation in a young adult with traumatic brain injury[C]. In: International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 2809–2812

  11. 11.

    Yuan P, Wang T, Ma F, Gong M (2014) Key technologies and prospects of individual combat exoskeleton[M]. In: Sun F, Li T, Li H (eds) Knowledge engineering and management. Springer, Berlin

    Google Scholar 

  12. 12.

    Mohammadpour R, Shaharuddin S, Chang CK, Zakaria NA, Ab Ghani A, Chan NW (2015) Prediction of water quality index in constructed wetlands using support vector machine. Environ Sci Pollut Res 22(8):6208–6219

    Article  Google Scholar 

  13. 13.

    S Zhu, C Xu, J Wang, Y Xiao and F Ma (2017) Research and application of combined kernel SVM in dynamic voiceprint password authentication system. In: 2017 IEEE 9th International Conference on Communication Software and Networks (ICCSN), Guangzhou, China, pp. 1052–1055

  14. 14.

    Yunlong Z, Peng Z (2012) Vibration fault diagnosis method of centrifugal pump based on EMD complexity feature and least square support vector machine[J]. Energy Procedia 17:939–945

    Article  Google Scholar 

  15. 15.

    Almasi ON, Khooban MH, Behzad H (2018) Non-linear MIMO identification of a Phantom Omni using LS-SVR with a hybrid model selection. IET Sci Meas Technol 12(5):678–683

    Article  Google Scholar 

  16. 16.

    Mesquita DPP, Freitas LA, Gomes JPP, Mattos CLC (2020) LS-SVR as a Bayesian RBF network. EEE Trans Neural Netw Learn Syst 31(10):4389–4393

    MathSciNet  Article  Google Scholar 

  17. 17.

    LopezMeyer P, Fulk GD, Sazonov ES (2011) Automatic detection of temporal gait parameters in poststroke individuals. IEEE Trans Inf Technol Biomed 15(4):594–601

    Article  Google Scholar 

  18. 18.

    Liao R, Yu S, An W, Huang Y (2020) A model-based gait recognition method with body pose and human prior knowledge. Pattern Recognit. 98:107069

    Article  Google Scholar 

  19. 19.

    Ben X, Gong C, Zhang P et al (2020) Coupled bilinear discriminant projection for cross-view gait recognition[J]. IEEE Trans Circuits Syst Video Technol 30(3):734–747

    Article  Google Scholar 

  20. 20.

    MS Ivanova, (2019) Fuzzy set theory and fuzzy logic for activities automation in engineering education. In: 2019 IEEE XXVIII International Scientific Conference Electronics (ET), Sozopol, Bulgaria, pp. 1-4

  21. 21.

    Kumar PS (2020) Algorithms for solving the optimization problems using fuzzy and intuitionistic fuzzy set[J]. Int J Syst Assur Eng Manag 11(1):189–222

    Article  Google Scholar 

  22. 22.

    VSR Poli, (2017) A method for generalized fuzzy rough sets and application to fuzzy control systems. In: 2017 International Conference on Fuzzy Theory and Its Applications (iFUZZY), Pingtung, pp.1–6

  23. 23.

    Zhang Y, Ansari N, Su W, et al. (2011) Multi-sensor signal fusion based modulation classification by using wireless sensor networks[C]. International conference on communications, pp. 1–5

  24. 24.

    J Yang, A Bouzerdoum and SLPhung, (2010) A training algorithm for sparse LS-SVM using compressive sampling. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, TX, pp. 2054–2057

Download references


This Research was supported by University of Electronic Science and Technology of China.

Author information



Corresponding author

Correspondence to Tao Qin.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Qin, T., Yang, Y., Wen, B. et al. Research on human gait prediction and recognition algorithm of lower limb-assisted exoskeleton robot. Intel Serv Robotics (2021).

Download citation


  • Exoskeleton robot
  • LS-SVR
  • Fuzzy theory
  • Gait data prediction
  • Gait phase recognition