Skip to main content
Log in

A Data-Driven Approach to Estimate Human Center of Mass State During Perturbed Locomotion Using Simulated Wearable Sensors

  • Original Article
  • Published:
Annals of Biomedical Engineering Aims and scope Submit manuscript

Abstract

Center of mass (COM) state, specifically in a local reference frame (i.e., relative to center of pressure), is an important variable for controlling and quantifying bipedal locomotion. However, this metric is not easily attainable in real time during human locomotion experiments. This information could be valuable when controlling wearable robotic exoskeletons, specifically for stability augmentation where knowledge of COM state could enable step placement planners similar to bipedal robots. Here, we explored the ability of simulated wearable sensor-driven models to rapidly estimate COM state during steady state and perturbed walking, spanning delayed estimates (i.e., estimating past state) to anticipated estimates (i.e., estimating future state). We used various simulated inertial measurement unit (IMU) sensor configurations typically found on lower limb exoskeletons and a temporal convolutional network (TCN) model throughout this analysis. We found comparable COM estimation capabilities across hip, knee, and ankle exoskeleton sensor configurations, where device type did not significantly influence error. We also found that anticipating COM state during perturbations induced a significant increase in error proportional to anticipation time. Delaying COM state estimates significantly increased accuracy for velocity estimates but not position estimates. All tested conditions resulted in models with R2 > 0.85, with a majority resulting in R2 > 0.95, emphasizing the viability of this approach. Broadly, this preliminary work using simulated IMUs supports the efficacy of wearable sensor-driven deep learning approaches to provide real-time COM state estimates for lower limb exoskeleton control or other wearable sensor-based applications, such as mobile data collection or use in real-time biofeedback.

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

Access this article

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

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Pratt, J., J. Carff, S. Drakunov, and A. Goswami. Capture point: a step toward humanoid push recovery. In: 2006 6th IEEE-RAS International Conference on Humanoid Robots. University of Genova, Genova, Italy. IEEE, 2006, pp. 200–207. https://doi.org/10.1109/ICHR.2006.321385.

  2. Hof, A. L. The ‘extrapolated center of mass’ concept suggests a simple control of balance in walking. Hum. Mov. Sci. 27(1):112–125, 2008. https://doi.org/10.1016/j.humov.2007.08.003.

    Article  PubMed  Google Scholar 

  3. Wang, Y., and M. Srinivasan. Stepping in the direction of the fall: the next foot placement can be predicted from current upper body state in steady-state walking. Biol. Lett. 10(9):20140405, 2014. https://doi.org/10.1098/rsbl.2014.0405.

    Article  PubMed  PubMed Central  Google Scholar 

  4. Simonetti, E., E. Bergamini, G. Vannozzi, J. Bascou, and H. Pillet. Estimation of 3D body center of mass acceleration and instantaneous velocity from a wearable inertial sensor network in transfemoral amputee gait: a case study. Sensors. 21(9):Art. no. 9, 2021. https://doi.org/10.3390/s21093129.

    Article  Google Scholar 

  5. Zhang, T., M. Tran, and H. Huang. Design and experimental verification of hip exoskeleton with balance capacities for walking assistance. IEEE/ASME Trans. Mechatron. 23(1):274–285, 2018. https://doi.org/10.1109/TMECH.2018.2790358.

    Article  Google Scholar 

  6. Afschrift, M., et al. Assisting walking balance using a bio-inspired exoskeleton controller. J. Neuroeng. Rehabil. 20:82, 2023. https://doi.org/10.1186/s12984-023-01205-9.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Bayón, C., A. Q. L. Keemink, M. van Mierlo, W. Rampeltshammer, H. van der Kooij, and E. H. F. van Asseldonk. Cooperative ankle-exoskeleton control can reduce effort to recover balance after unexpected disturbances during walking. J. NeuroEng. Rehabil. 19(1):21, 2022. https://doi.org/10.1186/s12984-022-01000-y.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Camargo, J., D. D. Molinaro, and A. J. Young. Predicting biological joint moment during multiple ambulation tasks. J. Biomech. 134:111020, 2022. https://doi.org/10.1016/j.jbiomech.2022.111020.

    Article  PubMed  Google Scholar 

  9. Molinaro, D. D., E. O. Park, and A. J. Young. Anticipation and delayed estimation of human hip moments using deep learning and a robotic hip exoskeleton. IEEE ICRA. 2023.

  10. Hollinger, D., M. Schall, H. Chen, S. Bass, and M. Zabala. The influence of gait phase on predicting lower-limb joint angles. IEEE Trans. Med. Robot. Bionics. 5(2):343–352, 2023. https://doi.org/10.1109/TMRB.2023.3260261.

    Article  Google Scholar 

  11. Lee, S.-W., and A. Asbeck. A deep learning-based approach for foot placement prediction. IEEE Robot. Autom. Lett. 8(8):4959–4966, 2023. https://doi.org/10.1109/LRA.2023.3290521.

    Article  Google Scholar 

  12. Tanghe, K., F. De Groote, D. Lefeber, J. De Schutter, and E. Aertbeliën. Gait trajectory and event prediction from state estimation for exoskeletons during gait. IEEE Trans. Neural Syst. Rehabil. Eng. 28(1):211–220, 2020. https://doi.org/10.1109/TNSRE.2019.2950309.

    Article  PubMed  Google Scholar 

  13. Molinaro, D. D., I. Kang, J. Camargo, M. C. Gombolay, and A. J. Young. Subject-independent, biological hip moment estimation during multimodal overground ambulation using deep learning. IEEE Trans. Med. Robot. Bionics. 4(1):219–229, 2022. https://doi.org/10.1109/TMRB.2022.3144025.

    Article  Google Scholar 

  14. Dorschky, E., M. Nitschke, C. F. Martindale, A. J. van den Bogert, A. D. Koelewijn, and B. M. Eskofier. CNN-based estimation of sagittal plane walking and running biomechanics from measured and simulated inertial sensor data. Front. Bioeng. Biotechnol. 8:604, 2020. https://doi.org/10.3389/fbioe.2020.00604.

    Article  PubMed  PubMed Central  Google Scholar 

  15. Lim, H., B. Kim, and S. Park. Prediction of lower limb kinetics and kinematics during walking by a single IMU on the lower back using machine learning. Sensors. 20(1):130, 2020. https://doi.org/10.3390/s20010130.

    Article  Google Scholar 

  16. Camargo, J., W. Flanagan, N. Csomay-Shanklin, B. Kanwar, and A. Young. A machine learning strategy for locomotion classification and parameter estimation using fusion of wearable sensors. IEEE Trans. Biomed. Eng. 68(5):1569–1578, 2021. https://doi.org/10.1109/TBME.2021.3065809.

    Article  PubMed  Google Scholar 

  17. Leestma, J. K., P. R. Golyski, C. R. Smith, G. S. Sawicki, and A. J. Young. Linking whole-body angular momentum and step placement during perturbed walking. J. Exp. Biol. 226(6):jeb244760, 2023. https://doi.org/10.1242/jeb.244760.

    Article  PubMed  PubMed Central  Google Scholar 

  18. Hnat, S. K., B. J. H. van Basten, and A. J. van den Bogert. Compensation for inertial and gravity effects in a moving force platform. J. Biomech. 75:96–101, 2018. https://doi.org/10.1016/j.jbiomech.2018.05.009.

    Article  PubMed  Google Scholar 

  19. Delp, S. L., et al. OpenSim: open-source software to create and analyze dynamic simulations of movement. IEEE Trans. Biomed. Eng. 54(11):1940–1950, 2007. https://doi.org/10.1109/TBME.2007.901024.

    Article  PubMed  Google Scholar 

  20. Rajagopal, A., C. L. Dembia, M. S. DeMers, D. D. Delp, J. L. Hicks, and S. L. Delp. Full-body musculoskeletal model for muscle-driven simulation of human gait. IEEE Trans. Biomed. Eng. 63(10):2068–2079, 2016. https://doi.org/10.1109/TBME.2016.2586891.

    Article  PubMed  PubMed Central  Google Scholar 

  21. Vlutters, M., E. H. F. Van Asseldonk, and H. Van der Kooij. Center of mass velocity based predictions in balance recovery following pelvis perturbations during human walking. J. Exp. Biol. 219(10):1514–1523, 2016. https://doi.org/10.1242/jeb.129338.

    Article  CAS  PubMed  Google Scholar 

  22. Chiu, V. L., M. Raitor, and S. H. Collins. Design of a hip exoskeleton with actuation in frontal and sagittal planes. IEEE Trans. Med. Robot. Bionics. 3(3):773–782, 2021. https://doi.org/10.1109/TMRB.2021.3088521.

    Article  Google Scholar 

  23. Alili, A., A. Fleming, V. Nalam, M. Liu, J. Dean, and H. Huang. Abduction/adduction assistance from powered hip exoskeleton enables modulation of user step width during walking. IEEE Trans. Biomed. Eng. 71(1):334–342, 2023. https://doi.org/10.1109/TBME.2023.3301444.

    Article  PubMed  Google Scholar 

  24. Liang, W., F. Wang, A. Fan, W. Zhao, W. Yao, and P. Yang. Deep-learning model for the prediction of lower-limb joint moments using single inertial measurement unit during different locomotive activities. Biomed. Signal Process. Control. 86:105372, 2023. https://doi.org/10.1016/j.bspc.2023.105372.

    Article  Google Scholar 

  25. Hossain, M. S. B., Z. Guo, and H. Choi. Estimation of lower extremity joint moments and 3D ground reaction forces using IMU sensors in multiple walking conditions: a deep learning approach. IEEE J. Biomed. Health Inform. 27(6):2829–2840, 2023. https://doi.org/10.1109/JBHI.2023.3262164.

    Article  PubMed  Google Scholar 

  26. Reimann, H., T. D. Fettrow, E. D. Thompson, P. Agada, B. J. McFadyen, and J. J. Jeka. Complementary mechanisms for upright balance during walking. PLoS ONE 12(2):e0172215, 2017. https://doi.org/10.1371/journal.pone.0172215.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgments

The authors would like to thank Z. Centeno Sanz and V. Iyer for their help building the code for COP correction, P. Golyski and D. Espinal for their help with data collection, D. Molinaro for providing guidance on the TCN model, and E. Schonhaut for his assistance running models. This work was supported by National Science Foundation Research Traineeship: Accessibility, Rehabilitation, and Movement Science (NSF NRT ARMS) Program Award #1545287, National Science Foundation Graduate Research Fellowship Program (NSF GRFP) Award #1324585, the Georgia Institute of Technology Petit Institute Pruitt Scholarship, and NIH Director’s New Innovator Award DP2-HD111709.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Jennifer K. Leestma.

Ethics declarations

Competing Interests

The authors have no financial or non-financial interests to disclose.

Additional information

Associate Editor Joel Stitzel oversaw the review of this article.

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Leestma, J.K., Smith, C.R., Sawicki, G.S. et al. A Data-Driven Approach to Estimate Human Center of Mass State During Perturbed Locomotion Using Simulated Wearable Sensors. Ann Biomed Eng (2024). https://doi.org/10.1007/s10439-024-03495-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10439-024-03495-z

Keywords

Navigation