Gait Analysis

Follow this topic Ask about this topic

Gait analysis studies how people and legged robots walk, using motion, forces, and timing to describe identity, impairment, function, and stability. Methods range from marker-based motion capture and force plates to camera-based pose estimation and wearable inertial sensors, paired with biomechanical models and sequence-learning methods to estimate gait events, joint motion, forces, or diagnostic patterns. Applications include assessment and monitoring of Parkinson’s disease, stroke, frailty, falls, and freezing of gait, as well as gait recognition, assistive-device control, and robot locomotion; evaluations use subject-held-out and cross-site tests alongside recognition benchmarks such as CASIA-B. Models can perform well in constrained tests, but robustness across people, clinics, sensors, and pathological gait remains unresolved, and markerless estimates—especially of forces—still need validation against instrumented measurements before clinical reliance.

Latest papers

75 papers9 papers in the last four weeks, down 44% on the four weeks before. 0.1% of all new papers.

Recurrent Temporal Restricted Boltzmann Machines as Unsupervised Encoders for Biomechanical Movement Sequences
Oct 17, 2026Wafi Sharif, Nicholas LaHayeMotion Representation Learning Time Series Representation Learning
Queens High School for the Sciences · Jet Propulsion Laboratory, California Institute of Technology
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
When Participant Disjoint Validation Is Not Enough to Establish Generalization in Parkinson's Gait Classification
Oct 12, 2026Md. Sifat, Sania Akter, Akif Islam +1Parkinson's Disease Classification Cross-Domain Generalization
Department of Computer Science and Engineering, University of Rajshahi, Motihar, Rajshahi, 6205, Bangladesh
Adaptive Gait Biofeedback With Participant-Held-Out Modeling and Participant-Specific Updating in Chronic Ankle Instability
Oct 5, 2026Jaeyoon Kim, Veronika Lebisova, Jeniya Sultana +2Gait Analysis
Department of Civil, Environmental, and Construction Engineering, The University of Texas at El Paso, El Paso, TX 79968, USA · Department of Kinesiology, The University of Texas at El Paso, El Paso, TX 79968, USA · Department of Aerospace and Mechanical Engineering, The University of Texas at El Paso, El Paso, TX 79968, USA
Monocular markerless biomechanics for clinically interpretable gait assessment in spinal cord injury
Oct 4, 2026Shreyasvi Natraj, Mathieu Ruepp, Yanke Li +3Markerless Motion Capture Gait Analysis
Spinal Cord Artificial Intelligence (SCAI) Lab, ETH Zürich, Zürich, Switzerland · Swiss Paraplegic Research, Swiss Paraplegic Centre, Nottwil, Switzerland · University Hospital Balgrist, Zurich, Switzerland +4
Terrain-Dependent Intra-Cycle Leg Timing for Effective Locomotion on Granular Slopes
Oct 2, 2026Long Zhao, Xingjue Liao, Feifei QianGranular Terrain Locomotion Robot Locomotion
Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA.
Sparse Calibration-Based Personalization of Kernel-Based Gait Phase and Speed Estimation Using Wearable IMUs
Oct 2, 2026Myeongju Cha, Pilwon HurGait Analysis Wearable Sensing
Department of Mechanical and Robotics Engineering, GIST, Gwangju, Korea
The Effect of Gait Stability Based on Two Types of Impact Strategies for Two-Link Walking and Brachiating Robots
Oct 1, 2026Alan Estrada Flores, Nelson RosaDynamical Systems Gait Analysis
Illinois Institute of Technology, Chicago IL 60616, USA
PhaseSync-Exo: Human Clock Anchored Reference Adaptation for Dynamic Gait Tracking
Sep 30, 2026Kaijie Qi, Yuehan Wang, Kaiming Xu +2Gait Analysis Motion Retargeting
Tsinghua University
DrGait: Biomechanically Grounded Visual Reasoning for Interpretable Clinical Gait Analysis
Sep 23, 2026Xiangyu Yin, Shiqi Wang, Abrar Alamri +4Vision-Language Models Gait Analysis
University of Pittsburgh
DiaSeg: Diagonal Segment Extraction from DTW Paths for Interpretable Gait Analysis
Sep 21, 2026Tresor Y. Koffi, Amel Hidouri, Corentin Legrand +1Dynamic Time Warping Gait Analysis
Université Bourgogne Europe, CIAD UR 7533, Dijon, 21000, France.
A Compact Stance-Indexed Anterior-Posterior COP Representation for Parkinson's Disease Classification from Plantar VGRF
Sep 19, 2026Md. Sifat, Sania Akter, Akif Islam +1Parkinson's Disease Classification Gait Analysis
Department of Computer Science and Engineering, University of Rajshahi, Rajshahi, Bangladesh
GaitVista: Reliability-Aware AI Measurement toward Accessible Longitudinal Gait Assessment
Sep 18, 2026Nethmi Jayasinghe, Mihir Parashar, Amit Ranjan TrivediGait Analysis Multimodal Sensor Fusion
Department of Electrical and Computer Engineering, University of Illinois Chicago, Chicago, IL, USA. · Illinois Mathematics and Science Academy, Aurora, IL, USA.
Duty Factor Predicts Robust Constrained Quadrupedal Locomotion Across Gait Types
Sep 18, 2026James Zhu, David Ologan, George Ortiz +5Compliant Legged Locomotion Quadruped Locomotion
Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL, USA · Department of Mechanical Engineering, 3 Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA
Video-Based Markerless Motion Capture for Clinical and Rehabilitation Biomechanics: A PRISMA-ScR Scoping Review of Validated Architectures, Clinical Readiness, and Emerging Methods
Sep 16, 2026Florian Delaplace, Elodie Piche, Frédéric Chorin +1Markerless Motion Capture Gait Analysis
LAMHESS, CHU · LAMHESS, Université Côte d'Azur, Nice, France · LAMHESS +3
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
3D Gait-Based Autism Classification Using Attention-Enhanced Deep Learning with Cross-Fold Statistical Stability Analysis
Sep 12, 2026Md Nadim Mahamood, Md Arif Shahriar, Md Parvej Sikder +4Autism Spectrum Disorder Gait Analysis
Department of Computer Science and Engineering Begum Rokeya University Rangpur, Bangladesh · Department of Computer Science Texas State University San Marcos, Texas, USA · Department of Information and Communication Technologies Asian Institute of Technology Pathum Thani, Thailand +1
3D Digital Twin Visualization of Multiclass GRF-Based Gait Disorder Classification
Sep 11, 2026Nayoung Son, Minwoo ShinGait Analysis
Department of Software, Yonsei University, Wonju, 26493, Republic of Korea
Hybrid Physics-AI Framework of Body Center of Mass Dynamics from Wrist-Worn Sensors
Sep 11, 2026Shuhao Que, Valentina Breschi, Ying WangGait Analysis Wearable Sensing
Electrical Engineering, University of Twente, Drienerlolaan 5, Enschede, 7522 NB, Netherlands. · Electrical Engineering, Eindhoven University of Technology, Groene Loper 19, Eindhoven, 5612 AP, Netherlands.
3rd Place Solution to Human Motion Challenges in Real-World and Clinical Settings (MoCha) @ECCV2026: Language-Aligned Motion Representations for Domain-Generalizable UPDRS-Gait Severity Estimation
Sep 9, 2026Soojie Kim, Muhammad Munsif, Minkyung Kim +1Representation Learning Medical Diagnosis
UNIST, South Korea
Freezing of Gait Prediction Under Spatial Occlusion: An IMU-Supervised Cross-Modal Distillation Approach
Sep 9, 2026Chandan Biswas, Aryan Singh, Anabik PalCross-Modal Knowledge Distillation Gait Analysis
NeuroAI Fusion Labs Kolkata, India · Indian Institute of Science Education and Research Berhampur, Odisha
Recovering Biomechanical Signals from Missing Keypoints Using Temporal Interpolation in Monocular Gait Analysis
Sep 9, 2026Shubham JariwalaTime Series Imputation Gait Analysis
Information Systems Technology and Design, Singapore University of Technology and Design, 8 Somapah Road, Singapore 487372, Singapore
Supervised Cross-Modal Feature Alignment for Zero-Wearable Freezing of Gait Detection in Parkinsonism
Sep 8, 2026Aryan Singh, Chandan BiswasCross-Modal Knowledge Distillation Cross-Modal Alignment
NeuroAI Fusion Labs Kolkata, India
SynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation
Sep 8, 2026Soroush Mehraban, Xin Lei Lin, Vida Adeli +5Synthetic-to-Real Domain Adaptation Physical Consistency in Video Generation
1KITE Research Institute · University of Toronto · 3Vector Institute +2
Mudskippers use tail thrusting to help crutching to move on mud of various wetness
Sep 1, 2026Divya Ramesh, Gargi Sadalgekar, Jiangqi Tan +1Gait Analysis
Department of Mechanical Engineering, Johns Hopkins University
More Motion Is Not Always Better Motion: Corpus Composition Governs Whether Augmentation Helps SMPL-Based Parkinsonian Gait Severity Estimation
Aug 24, 2026Michael Caiola, Andrew C. WeitzSynthetic Data Augmentation Gait Analysis
Credence, McLean VA, USA
Kinematic Knowledge Maps for Pattern Alignment: Structured Latent Representational Learning in Multimodal Gait Analysis
Aug 21, 2026Chen Dong, He Zonglin, Cheung Kenneth M. CGait Analysis Representation Learning
Department of Orthopaedics & Traumatology, University of Hong Kong, Hong Kong, China · University of Hong Kong - Shenzhen hospital, Shenzhen, China
Aggregate, Don't Adapt: Subject-Level Posterior Aggregation and Transductive Calibration for Cross-Site Parkinsonian Gait Severity
Aug 20, 2026Junlong ShenGait Analysis Parkinson's Disease
University of Alberta, Edmonton, Canada
VideoRun2D Demo: Markerless Body Tracking for Biomechanical Analysis of Running
Aug 19, 2026Luis F. Gomez, Julian Fierrez, Roberto Daza +5Human Pose Estimation Gait Analysis
BiometricsAI, Universidad Autonoma de Madrid (UAM), Spain
Towards Context-Aware Clinical Motion Understanding in Daily Living at Home: Freezing of Gait Detection with Egocentric Vision
Aug 13, 2026Vayalet Stefanova, Diwas Lamsal, Margot Genbrugge +5Gait Analysis Parkinson's Disease
Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium · Neurorehabilitation Research Group (eNRGy), Department of Rehabilitation Sciences, KU Leuven, Leuven, Belgium · Institute of Interdisciplinary Exercise Science and Sports Medicine, Medical School Hamburg, Hamburg, Germany +2

Oct 17, 2026J/K move · Enter open · S save

Recurrent Temporal Restricted Boltzmann Machines as Unsupervised Encoders for Biomechanical Movement Sequences

Wafi Sharif, Nicholas LaHaye

Queens High School for the Sciences · Jet Propulsion Laboratory, California Institute of Technology

Motion Representation Learning Time Series Representation Learning Restricted Boltzmann Machines Gait Analysis

Open paper AskPDF arXiv

Biomechanical movement recordings are continuous, high-dimensional time series, and analyzing them without manually labeling them requires representations that capture how movements evolve over time. Most unsupervised representation-learning pipelines, however, treat each observation frame independently and discard this temporal structure, while energy-based models that could capture it have not extensively been adapted to biomechanical signals. So, this paper implements the Recurrent Temporal Restricted Boltzmann Machine (RTRBM), a recurrent energy-based model, into an unsupervised encoder that maps windows of movement data to fixed-length embeddings, and tests what its recurrent structure contributes. We adapt the model to continuous-valued signals, stack it into a deep architecture, and integrate it into the SIT-FUSE segmentation pipeline. We evaluate the embeddings on simulated musculoskeletal reaching and on two real gait datasets, using clustering, reconstruction, and walking-speed classification of unseen subjects, and compare them against non-recurrent and non-probabilistic baselines, including a control that removes the recurrent connection. Clustering the embeddings recovers movement structure tied to progress toward the target without any labels, which also transfers to unseen episodes. On gait data, the embeddings outperform PCA and autoencoder baselines under a nonlinear probe. However, removing the recurrent connection does not yield a measurable loss on the reaching task, and simple per-channel summary statistics classify walking speed at least as well as the embeddings. The model is therefore a working, verified encoder for SIT-FUSE, while the evidence for a benefit of recurrence is mixed, and the learned embeddings did not outperform simple summary statistics on gait.