Sparse Calibration-Based Personalization of Kernel-Based Gait Phase and Speed Estimation Using Wearable IMUs

Myeongju Cha; Pilwon Hur

cs.ROOct 2, 2026

Sparse Calibration-Based Personalization of Kernel-Based Gait Phase and Speed Estimation Using Wearable IMUs

Authors: Myeongju Cha, Pilwon Hur

Organizations: Department of Mechanical and Robotics Engineering, GIST, Gwangju, Korea

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.

Figures & tables

Setting	Speeds (m/s)	Baseline construction
Offline	0.90, 1.15, 1.35	Equal average; speeds selected by baseline reconstruction RMSE
Online	0.75, 1.00, 1.25	Weighted average for available treadmill speeds

Table 1: Calibration settings for offline and online analyses.

Figure 1: Online setup with four thigh/shank IMUs, heel FSRs, and a Jetson Nano for 100-Hz acquisition and matching.

oX[c]X[c]X[c]Method	Phase RMSE	Speed RMSE
A	$0.0161\pm 0.0040$	$0.1104\pm 0.0625$
B	$0.0161\pm 0.0039$	$0.1103\pm 0.0637$
C	$0.0178\pm 0.0045$	$0.1118\pm 0.0581$

Table 2: Offline validation results, reported as subject-level mean

\pm

standard deviation.

Figure 2: Stride-level online speed estimation RMSE (within-subject mean $\pm$ SD).

Figure 3: Stride-level online phase estimation RMSE (within-subject mean $\pm$ SD).

Method	Total time ( $\mu$ s)	Per kernel ( $\mu$ s)
A	$48.49\pm 0.77$	1.73
B	$49.03\pm 0.84$	1.75
C	$48.89\pm 0.95$	1.75
A+B+C	$146.41\pm 2.51$	–

Table 3: Online matching latency.

Gait Analysis

Gait analysis uses movement and biomechanical signals to characterize walking, recognize people, assess health, and guide rehabilitation or locomotion.

See all 75 papers

Tread: A Visuo-Inertial Framework for Terrain and Locomotion Context-Aware Gait-Phase and Speed Estimation in Wearable Robotics
Oct 13, 2026Debadrata Sarkar, Akash Bachhar, Aman AroraTerrain-Aware Robot Locomotion Gait Analysis
Human Centred Robotics and Cybernetics Group, CSIR-Central Mechanical Engineering Research Institute, Durgapur 713209, India
Two-Stage Personalized Gait Phase Estimation in Stroke Survivors During Exoskeleton-Assisted Walking: An Offline Feasibility Study
Sep 14, 2026Hyungseok Ryu, Pilwon HurGait Analysis Assistive Robotics
Department of Mechanical and Robotics Engineering, Gwangju Institute of Science and Technology (GIST), Gwangju 61005, Republic of Korea
Generating Personalized Lower-Limb Kinematics Across Walking Speeds Using Subject-Conditioned Diffusion
Jul 8, 2026Diya Dinesh, Adrian Krieger, Changseob Song +3Gait Analysis Human Motion Generation
School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, 15213 USA · Department of Mechanical Engineering, Carnegie Mellon University, USA · Woodruff School of Mechanical Engineering and the Institute for Robotics and Intelligent Machines, Georgia Institute of Technology, Atlanta, GA 30332 USA

Oct 13, 2026J/K move · Enter open · S save

Tread: A Visuo-Inertial Framework for Terrain and Locomotion Context-Aware Gait-Phase and Speed Estimation in Wearable Robotics

Debadrata Sarkar, Akash Bachhar, Aman Arora

Human Centred Robotics and Cybernetics Group, CSIR-Central Mechanical Engineering Research Institute, Durgapur 713209, India

Terrain-Aware Robot Locomotion Gait Analysis Wearable Sensing

Open paper AskPDF arXiv

A wearable assistive robot must continuously estimate terrain, locomotion mode, gait phase, and walking speed. These quantities are commonly addressed by separate, terrain-specific models, with datasets rarely collected under a common protocol. This paper presents a visuo-inertial framework that connects these estimates through a causal pipeline using a chest-mounted camera and four lower-limb inertial measurement units (IMUs). Anticipatory Terrain Perception (ATP) classifies incoming terrain with 96.3% accuracy and anticipates terrain transitions by 1.46 s on average. Terrain-Aware Locomotion Mode Identification (TALMI) achieves 93.7% and 98.8% accuracy for its level-ground and stairs experts respectively, with mean transition latencies being below 200 ms. The relevant TALMI posterior is retained as a Probabilistic Locomotion Context (PLC) vector and provided to a shared Gait Kinematic Encoder (GKE), which supports 50-Hz bilateral gait-phase estimation and 2-Hz walking-speed estimation. Leave-one-subject-out evaluation yields gait-phase RMSEs of 1.75%, 2.97%, and 4.55% for level walking, stair ascent, and stair descent respectively while estimating speed over 3.5-5.5 km/h with a RMSE of 0.218 km/h. All inertial sensing based models use sensor-fused Euler angles as input rather than raw accelerometer and gyroscope signals, reducing dependence on sensor mounting variation.

Abstract

Gait Analysis

Explore similar work

Tread: A Visuo-Inertial Framework for Terrain and Locomotion Context-Aware Gait-Phase and Speed Estimation in Wearable Robotics

Two-Stage Personalized Gait Phase Estimation in Stroke Survivors During Exoskeleton-Assisted Walking: An Offline Feasibility Study

Generating Personalized Lower-Limb Kinematics Across Walking Speeds Using Subject-Conditioned Diffusion