Sparse Calibration for Personalized Gait Estimation with Wearable IMUs
Sparse Calibration-Based Personalization of Kernel-Based Gait Phase and Speed Estimation Using Wearable IMUs
This study personalizes gait phase and speed estimation using sparse calibration and wearable IMUs. Personalized kernels reduced phase error but showed no significant speed improvement in real-time testing.
Source: arXiv Robotics — research abstracts · Read original article ↗
Article text · Original source · English
arXiv:2610.03931v1 Announce Type: new Abstract: This paper presents sparse calibration-based personalization for kernel-based gait phase and walking speed co-estimation from wearable inertial measurement units (IMUs). A 28-speed reference library was constructed from bilateral thigh and shank trajectories in a 20-subject locomotion dataset. Rather than directly applying population-average kernels, the method combines a user-specific baseline estimated from three calibration speeds with a principal-component (PC) model of baseline-centered kinematic deviations. Offline validation showed that personalized kernels reduced phase error relative to the population kernel. In a single-participant online pilot evaluation, the personalized kernels produced numerically lower mean phase and speed errors and ran in real time on embedded hardware. However, the speed effect was not significant, and pairwise phase differences did not remain significant after multiple-comparison correction. The pilot evaluation establishes wearable implementation feasibility while indicating reference-to-online dataset mismatch and the need for larger-cohort validation.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
speed
28
View original evidence
A 28-speed reference library was constructed from bilateral thigh and shank trajectories in a 20-subject locomotion dataset.
Open source S2subjects
20
View original evidence
A 28-speed reference library was constructed from bilateral thigh and shank trajectories in a 20-subject locomotion dataset.
Open source S2
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2610.03931v1 Announce Type: new Abstract: This paper presents sparse calibration-based personalization for kernel-based gait phase and walking speed co-estimation from wearable inertial measurement units (IMUs). A 28-speed reference library was constructed from bilateral thigh and shank trajectories in a 20-subject locomotion dataset. Rather than directly applying population-average kernels, the method combines
Open source S2
a user-specific baseline estimated from three calibration speeds with a principal-component (PC) model of baseline-centered kinematic deviations. Offline validation showed that personalized kernels reduced phase error relative to the population kernel. In a single-participant online pilot evaluation, the personalized kernels produced numerically lower mean phase and speed errors and ran in real time on embedded hard
Open source S3
ware. However, the speed effect was not significant, and pairwise phase differences did not remain significant after multiple-comparison correction. The pilot evaluation establishes wearable implementation feasibility while indicating reference-to-online dataset mismatch and the need for larger-cohort validation.
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org