Gait Phase Estimation and Foot Trajectory Prediction During Dynamic Walking Using Gated Recurrent Units

Simple item page
dc.contributor.authorWisman, Hayleyen
dc.contributor.committeechairJones, Creed Farrisen
dc.contributor.committeechairAsbeck, Alan Thomasen
dc.contributor.committeememberBaumann, William T.en
dc.contributor.departmentElectrical and Computer Engineeringen
dc.date.accessioned2025-03-22T08:00:17Zen
dc.date.available2025-03-22T08:00:17Zen
dc.date.issued2025-03-21en
dc.description.abstractIn the field of assistive robotics and exoskeletons, foot trajectory prediction has the potential to play a pivotal role in improving the functionality and user experience of worn devices. Rather than operating as a reactive system which only responds to user movement, a de vice which predicts future foot position can anticipate an action before it occurs, reducing latency and moving with the wearer for a more natural, uninhibited motion. While previous studies have focused on predicting continuous motion, they often overlook critical transitions between walking and standing, which are essential for natural locomotion. We propose in this study a foot trajectory prediction approach which leverages a recurrent deep learning architecture to make predictions based on sequential walking data. The first of the two ma chine learning models predicts the gait phase as a value between 0 and 1, while the second model leverages the gait phase prediction output to predict foot position in three dimensions. The models were trained and evaluated on IMU sensor data collected from three subjects instructed to walk on a treadmill at speeds varying from 0.5 mph to 1.5 mph. The result ing mean absolute error on gait phase percentage across subjects and velocity was 1.92%. For foot trajectory prediction, the cross-subject trained model achieved mean distance er ror of 2.85±2.89 cm, 3.29±2.82 cm, 4.15±4.12 cm, 5.33±5.46 cm, and 6.92±6.56 cm with prediction horizons of 0.1s, 0.25s, 0.5s, 1s, and 2s, respectively.en
dc.description.abstractgeneralFoot trajectory prediction, which is the process of estimating the movement path of a person's foot during a walking sequence, can be used in the advancement of assistive robotics such as exoskeletons. Knowing where the next step will end and the path it will take to get there can help align the device with the user's intended movements and make the experience more natural. Previous work has often been limited to predicting foot placement during periods of constant walking, but not across sequences of both walking and standing. These transitions are important to capture in order to effectively emulate the human walking pattern and make assistive walking devices more practical and comfortable for everyday use. The approach to this problem proposed in this paper uses two machine learning models trained on walking data gathered from IMUs placed near the feet of the user. The results indicate that this method could be effective for predicting foot trajectory during the use of a walking exoskeleton across walking and standing transitions.en
dc.description.degreeMaster of Scienceen
dc.format.mediumETDen
dc.identifier.othervt_gsexam:42584en
dc.identifier.urihttps://hdl.handle.net/10919/125064en
dc.language.isoenen
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subjectDeep learningen
dc.subjectexoskeletonsen
dc.subjectassistive roboticsen
dc.subjectgated recurrent uniten
dc.subjectgait phaseen
dc.subjectfoot trajectoryen
dc.titleGait Phase Estimation and Foot Trajectory Prediction During Dynamic Walking Using Gated Recurrent Unitsen
dc.typeThesisen
thesis.degree.disciplineComputer Engineeringen
thesis.degree.grantorVirginia Polytechnic Institute and State Universityen
thesis.degree.levelmastersen
thesis.degree.nameMaster of Scienceen

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Wisman_H_T_2025.pdf
Size:
4.09 MB
Format:
Adobe Portable Document Format
Download

Collections

Masters Theses