Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evaluating Gait Symmetry with a Smart Robotic Walker: A Novel Approach to Mobility Assessment

Mahdi Chalaki, Abed Soleymani, Xingyu Li, Vivian Mushahwar, Mahdi Tavakoli

TL;DR

The paper tackles gait asymmetry in populations affected by aging, stroke, or limb differences by deploying a Smart Walker that records interaction-torque signals and applies a seasonal-trend decomposition to extract stride-level patterns and a symmetry index. It introduces an MSTL-based framework to estimate stride durations and define the symmetry index, with the SA index given by $SA = (45° - arctan(X_{left}/X_{right})) * (100%/90°)$, and demonstrates an 84.9% accuracy in identifying asymmetric gait in controlled experiments. It further shows clustering of gait patterns via PCA and Gaussian Mixture Models, illustrating potential rehabilitation pathways through a simulated improvement trajectory. Overall, the approach enables real-world, continuous gait monitoring and supports targeted, personalized interventions using assistive robotics data.

Abstract

Gait asymmetry, a consequence of various neurological or physical conditions such as aging and stroke, detrimentally impacts bipedal locomotion, causing biomechanical alterations, increasing the risk of falls and reducing quality of life. Addressing this critical issue, this paper introduces a novel diagnostic method for gait symmetry analysis through the use of an assistive robotic Smart Walker equipped with an innovative asymmetry detection scheme. This method analyzes sensor measurements capturing the interaction torque between user and walker. By applying a seasonal-trend decomposition tool, we isolate gait-specific patterns within these data, allowing for the estimation of stride durations and calculation of a symmetry index. Through experiments involving 5 experimenters, we demonstrate the Smart Walker's capability in detecting and quantifying gait asymmetry by achieving an accuracy of 84.9% in identifying asymmetric cases in a controlled testing environment. Further analysis explores the classification of these asymmetries based on their underlying causes, providing valuable insights for gait assessment. The results underscore the potential of the device as a precise, ready-to-use monitoring tool for personalized rehabilitation, facilitating targeted interventions for enhanced patient outcomes.

Evaluating Gait Symmetry with a Smart Robotic Walker: A Novel Approach to Mobility Assessment

TL;DR

The paper tackles gait asymmetry in populations affected by aging, stroke, or limb differences by deploying a Smart Walker that records interaction-torque signals and applies a seasonal-trend decomposition to extract stride-level patterns and a symmetry index. It introduces an MSTL-based framework to estimate stride durations and define the symmetry index, with the SA index given by , and demonstrates an 84.9% accuracy in identifying asymmetric gait in controlled experiments. It further shows clustering of gait patterns via PCA and Gaussian Mixture Models, illustrating potential rehabilitation pathways through a simulated improvement trajectory. Overall, the approach enables real-world, continuous gait monitoring and supports targeted, personalized interventions using assistive robotics data.

Abstract

Gait asymmetry, a consequence of various neurological or physical conditions such as aging and stroke, detrimentally impacts bipedal locomotion, causing biomechanical alterations, increasing the risk of falls and reducing quality of life. Addressing this critical issue, this paper introduces a novel diagnostic method for gait symmetry analysis through the use of an assistive robotic Smart Walker equipped with an innovative asymmetry detection scheme. This method analyzes sensor measurements capturing the interaction torque between user and walker. By applying a seasonal-trend decomposition tool, we isolate gait-specific patterns within these data, allowing for the estimation of stride durations and calculation of a symmetry index. Through experiments involving 5 experimenters, we demonstrate the Smart Walker's capability in detecting and quantifying gait asymmetry by achieving an accuracy of 84.9% in identifying asymmetric cases in a controlled testing environment. Further analysis explores the classification of these asymmetries based on their underlying causes, providing valuable insights for gait assessment. The results underscore the potential of the device as a precise, ready-to-use monitoring tool for personalized rehabilitation, facilitating targeted interventions for enhanced patient outcomes.
Paper Structure (17 sections, 3 equations, 5 figures, 2 tables)

This paper contains 17 sections, 3 equations, 5 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. Background
  3. Challenges in Gait Assessment: A Need for Innovation
  4. Instrumented rollators: A Promising Solution
  5. Research Objectives and Significance
  6. Methodology
  7. Seasonal-Trend Decomposition of Interaction Force
  8. Experimental Setup
  9. Data Collection
  10. Data Analysis
  11. EXPERIMENTS AND RESULTS
  12. Experiment 1: Simulating Gait Disorders for Symmetry Assessment
  13. Evaluation of the Smart Walker's Discriminatory Capacity
  14. Assessment of Anomaly Detection Accuracy in Gait Symmetry
  15. Experiment 2: Monitoring Gait Asymmetry Progression
  16. ...and 2 more sections

Figures (5)

  • Figure 1: (left) Illustration of mobility assistance with the Smart Walker, knee immobilizer induces hemiplegic gait on the right leg - (middle) Coordinate reference frame on the force/torque sensor - (right) Demonstration of simulating leg length discrepancy to mimic short-leg gait.
  • Figure 2: Distribution of symmetry angles among experimenters across five gait classes.
  • Figure 3: The differences in symmetry angles among experimenters across two levels of LLD.
  • Figure 4: GMM clustering in PCA-reduced space for the investigated five gait patterns.
  • Figure 5: Stages of gait improvement from an initially asymmetrical stride towards a symmetrical gait pattern.