Related Experiment Video
Updated: Oct 6, 2025
08:04
Using a Split-belt Treadmill to Evaluate Generalization of Human Locomotor Adaptation
Published on: August 23, 2017
8.4K
A Survey of Human Gait-Based Artificial Intelligence Applications
Elsa J Harris1, I-Hung Khoo2,3, Emel Demircan1,3
1Human Performance and Robotics Laboratory, Department of Mechanical and Aerospace Engineering, California State University Long Beach, Long Beach, CA, United States.
Frontiers in Robotics and AI
|January 20, 2022
Summary
Machine learning enhances human gait analysis across six key areas, from health monitoring and biometrics to animation. This survey explores current techniques and future growth opportunities in gait studies.
Area of Science:
- Biomechanics and Human Motion Analysis
- Artificial Intelligence and Machine Learning
Background:
- Human gait analysis is a critical area of study with diverse applications.
- Machine learning (ML) techniques have increasingly been applied to gait data.
- A comprehensive survey of ML applications in gait analysis is needed.
Purpose of the Study:
- To provide a broad-based survey of machine learning applications in human gait studies.
- To identify key applications and future research directions.
- To discuss ML techniques, their tasks, challenges, and trade-offs.
Main Methods:
- Conducted an electronic database search of published works from 2012 to mid-2021.
- Focused on studies applying machine learning techniques to human gait data.
- Identified and categorized six key application areas.
Main Results:
- Six key applications of ML in gait analysis were identified: improved gait analysis, health and wellness monitoring, human pose tracking, gait-based biometrics, smart gait systems, and animation.
- Various ML techniques are employed to address specific challenges in each application area.
- The study highlights the growing integration of ML in understanding and utilizing human gait.
Conclusions:
- Machine learning offers significant advancements across multiple domains of human gait analysis.
- Future research should explore novel ML approaches and expand applications in areas like personalized health and advanced human-computer interaction.
- Continued development in ML for gait analysis promises enhanced capabilities in various scientific and technological fields.
