Personalized Gait Monitoring and Latency Qualified Cueing in a Wearable Balance Assistance System
Authors
Polina Trotsenko
Share
Annotation
A wearable balance assistance system must identify an atypical movement state and deliver a corrective cue while sufficient response time remains. An integrated architecture combines lumbar inertial sensing, plantar pressure, a personal gait reference, and directional belt feedback with an audible pacing instruction. A retrospective component analysis uses 427 calibration repetitions and 405 held out repetitions from ten participants in a public perturbation dataset. The participant weighted mean baseline trial root mean square error decreases from 42.97 mm with a constant personal reference to 32.69 mm with a phase dependent reference, a 23.9% reduction. The paired mean difference is −10.28 mm, with a participant bootstrap 95% confidence interval of −13.05 to −7.64 mm. Improvement occurs in all ten participants. Baseline flag occupancy is 2.63% and 3.19%, respectively. An analytical support boundary model additionally coordinates the anomaly threshold with the response latency. Across 972 deterministic parameter combinations, the exact horizon gate preserves all 636 timely commands of the comparator gates while excluding late outputs. Under bounded state error, uncertain pendulum height and an additional 50 ms of latency, the conservative gate issues 1710 commands across 2916 stress scenarios; every issued command satisfies the full response budget. The remaining scenarios are classified by the command admissibility conditions. The results establish improved personal reference accuracy and a configurable timing basis for the larger wearable development, supporting its intended application in ambulatory balance assistance and individualized gait rehabilitation.
Keywords
Authors
Polina Trotsenko
Share
References:
Berkelmans, S., Afschrift, M., & Bruijn, S. (2025). Deviations in whole body angular momentum are largely corrected before foot placement (Version v1) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.17962789
Berkelmans, S., Bruijn, S., & Afschrift, M. (2026). Deviations in whole body angular momentum are largely corrected before foot placement. Journal of Biomechanics, 202, Article 113312. https://doi.org/10.1016/j.jbiomech.2026.113312
Bowman, T., Pergolini, A., Carrozza, M. C., Lencioni, T., Marzegan, A., Meloni, M., Vitiello, N., Crea, S., & Cattaneo, D. (2024). Wearable biofeedback device to assess gait features and improve gait pattern in people with Parkinson’s disease: A case series. Journal of NeuroEngineering and Rehabilitation, 21, Article 110. https://doi.org/10.1186/s12984-024-01403-z
Curtze, C., Buurke, T. J. W., & McCrum, C. (2024). Notes on the margin of stability. Journal of Biomechanics, 166, Article 112045. https://doi.org/10.1016/j.jbiomech.2024.112045
Hof, A. L., Gazendam, M. G. J., & Sinke, W. E. (2005). The condition for dynamic stability. Journal of Biomechanics, 38(1), 1-8. https://doi.org/10.1016/j.jbiomech.2004.03.025
Kim, H., Kim, H., & Shin, W.-S. (2022). Effects of vibrotactile biofeedback providing real-time pressure information on static balance ability and weight distribution symmetry index in patients with chronic stroke. Brain Sciences, 12(3), Article 358. https://doi.org/10.3390/brainsci12030358
Lorenzini, M., Gandarias, J. M., Fortini, L., Kim, W., & Ajoudani, A. (2022). ErgoTac-Belt: Anticipatory vibrotactile feedback to lead centre of pressure during walking. In 2022 9th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob) (pp. 1–6). IEEE. https://doi.org/10.1109/BioRob52689.2022.9925563
Pratt, J., Carff, J., Drakunov, S., & Goswami, A. (2006). Capture point: A step toward humanoid push recovery. In 2006 6th IEEE-RAS International Conference on Humanoid Robots (pp. 200-207). IEEE. https://doi.org/10.1109/ICHR.2006.321385
Reimann, H., & Bruijn, S. M. (2024). The condition for dynamic stability in humans walking with feedback control. PLOS Computational Biology, 20(3), Article e1011861. https://doi.org/10.1371/journal.pcbi.1011861
Vlutters, M., van Asseldonk, E. H. F., & van der Kooij, H. (2016). Center of mass velocity-based predictions in balance recovery following pelvis perturbations during human walking. The Journal of Experimental Biology, 219(10), 1514-1523. https://doi.org/10.1242/jeb.129338
Other articles of the issue
