Deep learning for human locomotion analysis in lower-limb exoskeletons: a comparative study

IntroductionWearable robotics for lower-limb assistance is increasingly investigated to enhance mobility in individuals with physical impairments and to augment performance in able-bodied users. A major challenge in this domain is the development of accurate and adaptive control systems that ensure...

Full description

Saved in:
Bibliographic Details
Main Authors: Omar Coser, Christian Tamantini, Matteo Tortora, Leonardo Furia, Rosa Sicilia, Loredana Zollo, Paolo Soda
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Computer Science
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fcomp.2025.1597143/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849239741181984768
author Omar Coser
Omar Coser
Christian Tamantini
Christian Tamantini
Matteo Tortora
Matteo Tortora
Leonardo Furia
Rosa Sicilia
Loredana Zollo
Paolo Soda
Paolo Soda
author_facet Omar Coser
Omar Coser
Christian Tamantini
Christian Tamantini
Matteo Tortora
Matteo Tortora
Leonardo Furia
Rosa Sicilia
Loredana Zollo
Paolo Soda
Paolo Soda
author_sort Omar Coser
collection DOAJ
description IntroductionWearable robotics for lower-limb assistance is increasingly investigated to enhance mobility in individuals with physical impairments and to augment performance in able-bodied users. A major challenge in this domain is the development of accurate and adaptive control systems that ensure seamless human-robot interaction across diverse terrains. While neural networks have recently shown promise in time-series analysis, no prior work has tackled the combined task of classifying ground conditions into five terrain classes and estimating high-level locomotion parameters such as ramp slope and stair height.MethodsThis study presents an experimental comparison of eight deep neural network architectures for terrain classification and locomotion parameter estimation. The models are trained on the publicly available CAMARGO 2021 dataset using inertial (IMU) and electromyographic (EMG) signals. Particular attention is given to evaluating the performance of IMU-only inputs versus combined IMU+EMG data, with an emphasis on cost-efficiency and sensor minimization. The tested architectures include LSTM, CNN, and hybrid CNN-LSTM models, among others. Model explainability is assessed via SHAP analysis to guide sensor selection.ResultsIMU-only configurations matched or outperformed those using both IMU and EMG, supporting a more efficient setup. The LSTM model, using only three IMU sensors, achieved high terrain classification accuracy (0.94 ± 0.04) and reliably estimated ramp slopes (1.95 ± 0.58°). The CNN-LSTM architecture demonstrated superior performance in stair height estimation, achieving a accuracy of 15.65 ± 7.40 mm. SHAP analysis confirmed that sensor reduction did not compromise model accuracy.DiscussionThe results highlight the feasibility of using lightweight, IMU-only setups for real-time terrain classification and locomotion parameter estimation. The proposed system achieves an inference time of ~2 ms, making it suitable for real-time wearable robotics applications. This study paves the way for more accessible and deployable solutions in assistive and augmentative lower-limb robotic systems. Code and models are publicly available at: [https://github.com/cosbidev/Human-Locomotion-Identification].
format Article
id doaj-art-a40dc12f9d2842db94e3d372e2640ea9
institution Kabale University
issn 2624-9898
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Computer Science
spelling doaj-art-a40dc12f9d2842db94e3d372e2640ea92025-08-20T04:00:50ZengFrontiers Media S.A.Frontiers in Computer Science2624-98982025-08-01710.3389/fcomp.2025.15971431597143Deep learning for human locomotion analysis in lower-limb exoskeletons: a comparative studyOmar Coser0Omar Coser1Christian Tamantini2Christian Tamantini3Matteo Tortora4Matteo Tortora5Leonardo Furia6Rosa Sicilia7Loredana Zollo8Paolo Soda9Paolo Soda10Unit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico di Roma, Rome, ItalyUnit of Advanced Robotics and Human-Centered Technologies, Università Campus Bio-Medico di Roma, Rome, ItalyUnit of Advanced Robotics and Human-Centered Technologies, Università Campus Bio-Medico di Roma, Rome, ItalyInstitute of Cognitive Sciences and Technologies, National Research Council of Italy, Rome, ItalyUnit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico di Roma, Rome, ItalyDipartimento di Ingegneria Navale, Elettrica, Elettronica e delle Telecomunicazioni, Università degli Studi di Genova, Genova, ItalyUnit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico di Roma, Rome, ItalyUnit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico di Roma, Rome, ItalyUnit of Advanced Robotics and Human-Centered Technologies, Università Campus Bio-Medico di Roma, Rome, ItalyUnit of Artificial Intelligence and Computer Systems, Università Campus Bio-Medico di Roma, Rome, ItalyDepartment of Diagnostics and Intervention, Radiation Physics, Biomedical Engineering, Umeå University, Umeå, SwedenIntroductionWearable robotics for lower-limb assistance is increasingly investigated to enhance mobility in individuals with physical impairments and to augment performance in able-bodied users. A major challenge in this domain is the development of accurate and adaptive control systems that ensure seamless human-robot interaction across diverse terrains. While neural networks have recently shown promise in time-series analysis, no prior work has tackled the combined task of classifying ground conditions into five terrain classes and estimating high-level locomotion parameters such as ramp slope and stair height.MethodsThis study presents an experimental comparison of eight deep neural network architectures for terrain classification and locomotion parameter estimation. The models are trained on the publicly available CAMARGO 2021 dataset using inertial (IMU) and electromyographic (EMG) signals. Particular attention is given to evaluating the performance of IMU-only inputs versus combined IMU+EMG data, with an emphasis on cost-efficiency and sensor minimization. The tested architectures include LSTM, CNN, and hybrid CNN-LSTM models, among others. Model explainability is assessed via SHAP analysis to guide sensor selection.ResultsIMU-only configurations matched or outperformed those using both IMU and EMG, supporting a more efficient setup. The LSTM model, using only three IMU sensors, achieved high terrain classification accuracy (0.94 ± 0.04) and reliably estimated ramp slopes (1.95 ± 0.58°). The CNN-LSTM architecture demonstrated superior performance in stair height estimation, achieving a accuracy of 15.65 ± 7.40 mm. SHAP analysis confirmed that sensor reduction did not compromise model accuracy.DiscussionThe results highlight the feasibility of using lightweight, IMU-only setups for real-time terrain classification and locomotion parameter estimation. The proposed system achieves an inference time of ~2 ms, making it suitable for real-time wearable robotics applications. This study paves the way for more accessible and deployable solutions in assistive and augmentative lower-limb robotic systems. Code and models are publicly available at: [https://github.com/cosbidev/Human-Locomotion-Identification].https://www.frontiersin.org/articles/10.3389/fcomp.2025.1597143/fulldeep learningexplainable AIhuman locomotionmultimodal learningneural networks
spellingShingle Omar Coser
Omar Coser
Christian Tamantini
Christian Tamantini
Matteo Tortora
Matteo Tortora
Leonardo Furia
Rosa Sicilia
Loredana Zollo
Paolo Soda
Paolo Soda
Deep learning for human locomotion analysis in lower-limb exoskeletons: a comparative study
Frontiers in Computer Science
deep learning
explainable AI
human locomotion
multimodal learning
neural networks
title Deep learning for human locomotion analysis in lower-limb exoskeletons: a comparative study
title_full Deep learning for human locomotion analysis in lower-limb exoskeletons: a comparative study
title_fullStr Deep learning for human locomotion analysis in lower-limb exoskeletons: a comparative study
title_full_unstemmed Deep learning for human locomotion analysis in lower-limb exoskeletons: a comparative study
title_short Deep learning for human locomotion analysis in lower-limb exoskeletons: a comparative study
title_sort deep learning for human locomotion analysis in lower limb exoskeletons a comparative study
topic deep learning
explainable AI
human locomotion
multimodal learning
neural networks
url https://www.frontiersin.org/articles/10.3389/fcomp.2025.1597143/full
work_keys_str_mv AT omarcoser deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT omarcoser deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT christiantamantini deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT christiantamantini deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT matteotortora deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT matteotortora deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT leonardofuria deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT rosasicilia deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT loredanazollo deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT paolosoda deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy
AT paolosoda deeplearningforhumanlocomotionanalysisinlowerlimbexoskeletonsacomparativestudy