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...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |