{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:00:57Z","timestamp":1786122057253,"version":"build-2736575974"},"reference-count":54,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003710","name":"Ministry of Health and Welfare, Republic of Korea","doi-asserted-by":"publisher","award":["RS-2022-KH129263"],"award-info":[{"award-number":["RS-2022-KH129263"]}],"id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Hip assistance robots have become a practical solution as daily-life walking support. However, providing reliable and timely assistance during overground walking remains challenging because gait varies across users and walking conditions. This study presents HealBot-H, a newly developed 2-kg modular hip exoskeleton with a gait-phase-aware admittance control framework driven by a deep learning-based gait phase estimator. The robot features two active hip joints in the sagittal plane and uses a magnetic quick-release modular structure, enabling either unilateral or bilateral configuration depending on the application. The control framework combines a classical admittance law with a bidirectional long short-term memory network that estimates locomotion mode and the continuous gait phase from lower-limb inertial measurement units. The trained model was deployed on a Raspberry Pi 5 for real-time operation. Based on the estimated gait phase, the admittance parameters are scheduled across seven subphases of the gait cycle. To avoid abrupt torque changes at the subphase boundaries, a two-stage update rule comprising linear interpolation and exponential smoothing is applied. The robot was validated with ten healthy adults during overground walking. Surface electromyography (EMG) was recorded from five lower-limb muscles and compared between walking with and without the robot. The mean EMG reductions ranged from 19.0\u201323.9% over the gait cycle after false discovery rate correction (all pFDR&lt;0.01). These results demonstrate that gait-phase-aware admittance control on a lightweight wearable platform can provide effective and well-timed walking assistance, while establishing a foundation for future personalized assistance.<\/jats:p>","DOI":"10.3390\/s26165008","type":"journal-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T08:01:36Z","timestamp":1786089696000},"page":"5008","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Embedded Adaptive Admittance Control for a Modular Hip Exoskeleton Using Deep Learning-Based Gait-Phase Estimation"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0623-3514","authenticated-orcid":false,"given":"Tuan Anh","family":"Nguyen","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Korea University College of Medicine, Seoul 02841, Republic of Korea"},{"name":"T-Robotics Co., Ltd., Osan-si 18102, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6703-5759","authenticated-orcid":false,"given":"Cong Phat","family":"Vo","sequence":"additional","affiliation":[{"name":"T-Robotics Co., Ltd., Osan-si 18102, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8817-4448","authenticated-orcid":false,"given":"Yekwang","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Korea University College of Medicine, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youngbo","family":"Shim","sequence":"additional","affiliation":[{"name":"T-Robotics Co., Ltd., Osan-si 18102, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9609-1116","authenticated-orcid":false,"given":"Seung-Jong","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Korea University College of Medicine, Seoul 02841, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Tu, X., Si, J., Lewek, M.D., and Huang, H. (2023, January 1\u20135). A Robotic Assistance Personalization Control Approach of Hip Exoskeletons for Gait Symmetry Improvement. Proceedings of the 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA.","DOI":"10.1109\/IROS55552.2023.10341440"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1038\/s42256-024-00894-8","article-title":"Soft robotic shorts improve outdoor walking efficiency in older adults","volume":"6","author":"Tricomi","year":"2024","journal-title":"Nat. Mach. Intell."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2560","DOI":"10.1109\/TNSRE.2023.3281409","article-title":"A Cable-Driven Exoskeleton with Personalized Assistance Improves the Gait Metrics of People in Subacute Stroke","volume":"31","author":"Zhong","year":"2023","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"10850","DOI":"10.1038\/s41598-025-95599-2","article-title":"Ultra-lightweight robotic hip exoskeleton with anti-phase torque symmetry for enhanced walking efficiency","volume":"15","author":"Lim","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1098\/rsif.2011.0182","article-title":"The mechanics and energetics of human walking and running: A joint level perspective","volume":"9","author":"Farris","year":"2012","journal-title":"J. R. Soc. Interface"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1186\/s12984-020-00777-0","article-title":"Wearable hip-assist robot modulates cortical activation during gait in stroke patients: A functional near-infrared spectroscopy study","volume":"17","author":"Lee","year":"2020","journal-title":"J. Neuroeng. Rehabil."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chang, Y., Kang, J., Jeong, B., Kim, G., Lim, B., Choi, B., and Lee, Y. (2023). Verification of Industrial Worker Walking Efficiency with Wearable Hip Exoskeleton. Appl. Sci., 13.","DOI":"10.3390\/app132312609"},{"key":"ref_8","unstructured":"(2026, May 15). Available online: https:\/\/www.angel-robotics.com\/en\/products\/angel-suit\/h10."},{"key":"ref_9","unstructured":"(2026, May 15). Available online: https:\/\/hypershell.tech."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1152\/japplphysiol.01133.2014","article-title":"An experimental comparison of the relative benefits of work and torque assistance in ankle exoskeletons","volume":"119","author":"Jackson","year":"2015","journal-title":"J. Appl. Physiol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3571","DOI":"10.1109\/LRA.2022.3147565","article-title":"Deep Learning Enables Exoboot Control to Augment Variable-Speed Walking","volume":"7","author":"Shepherd","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Malcolm, P., Derave, W., Galle, S., and De Clercq, D. (2013). A Simple Exoskeleton That Assists Plantarflexion Can Reduce the Metabolic Cost of Human Walking. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0056137"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1109\/LRA.2019.2890896","article-title":"The Effect of Hip Assistance Levels on Human Energetic Cost Using Robotic Hip Exoskeletons","volume":"4","author":"Kang","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2494","DOI":"10.1109\/TNSRE.2022.3196665","article-title":"The Effects of Incline Level on Optimized Lower-Limb Exoskeleton Assistance: A Case Series","volume":"30","author":"Franks","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1055","DOI":"10.1109\/TRO.2019.2913318","article-title":"Delayed Output Feedback Control for Gait Assistance with a Robotic Hip Exoskeleton","volume":"35","author":"Lim","year":"2019","journal-title":"IEEE Trans. Robot."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Qiu, S., Guo, W., Zha, F., Deng, J., and Wang, X. (2021). Exoskeleton Active Walking Assistance Control Framework Based on Frequency Adaptive Dynamics Movement Primitives. Front. Neurorobot., 15.","DOI":"10.3389\/fnbot.2021.672582"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1016\/j.robot.2015.09.015","article-title":"Integral admittance shaping: A unified framework for active exoskeleton control","volume":"75","author":"Nagarajan","year":"2016","journal-title":"Robot. Auton. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Thieffry, M., Vermeiren, L., and Dequidt, A. (2025, January 6\u201310). Impedance Control of Hip-Exoskeletons based on T-S Unknown Input Observer with Model Uncertainties. Proceedings of the 2025 IEEE International Conference on Fuzzy Systems (FUZZ), Reims, France.","DOI":"10.1109\/FUZZ62266.2025.11152036"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1186\/s10033-024-01113-6","article-title":"Variable admittance control of high compatibility exoskeleton based on human\u2013robotic interaction force","volume":"37","author":"Cao","year":"2024","journal-title":"Chin. J. Mech. Eng."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kim, H., and Yang, W. (2021). Variable admittance control based on human\u2013robot collaboration observer using frequency analysis for sensitive and safe interaction. Sensors, 21.","DOI":"10.3390\/s21051899"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Liang, C., and Hsiao, T. (2020). Walking Strategies and Performance Evaluation for Human-Exoskeleton Systems under Admittance Control. Sensors, 20.","DOI":"10.3390\/s20154346"},{"key":"ref_22","unstructured":"You, Z., and Zhou, X. (2026). Exoskeleton Control through Learning to Reduce Biological Joint Moments in Simulations. arXiv."},{"key":"ref_23","unstructured":"Wang, L., Wang, S., van Asseldonk, E.H.F., and van der Kooij, H. (2013, January 3\u20137). Actively controlled lateral gait assistance in a lower limb exoskeleton. Proceedings of the 2013 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Tokyo, Japan."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Walsh, C.J., Pasch, K., and Herr, H. (2006, January 9\u201315). An autonomous, underactuated exoskeleton for load-carrying augmentation. Proceedings of the 2006 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Beijing, China.","DOI":"10.1109\/IROS.2006.281932"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"938","DOI":"10.1109\/TNSRE.2013.2248749","article-title":"Powered hip exoskeletons can reduce the user\u2019s hip and ankle muscle activations during walking","volume":"21","author":"Lenzi","year":"2013","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kang, I., Hsu, H., and Young, A.J. (October, January 30). Design and Validation of a Torque Controllable Hip Exoskeleton for Walking Assistance. Proceedings of the ASME 2018 Dynamic Systems and Control Conference, Atlanta, GA, USA.","DOI":"10.1115\/DSCC2018-9198"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"103514","DOI":"10.1016\/j.robot.2020.103514","article-title":"A robust phase oscillator design for wearable robotic systems","volume":"128","author":"Subramanian","year":"2020","journal-title":"Robot. Auton. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1109\/TBME.2010.2089629","article-title":"Human\u2013Robot Synchrony: Flexible Assistance Using Adaptive Oscillators","volume":"58","author":"Ronsse","year":"2011","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"3318","DOI":"10.1109\/LRA.2019.2926678","article-title":"Adaptive Oscillator-Based Robust Control for Flexible Hip Assistive Exoskeleton","volume":"4","author":"Xue","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2170","DOI":"10.1109\/TRO.2023.3235584","article-title":"Real-Time Gait Phase and Task Estimation for Controlling a Powered Ankle Exoskeleton on Extremely Uneven Terrain","volume":"39","author":"Medrano","year":"2023","journal-title":"IEEE Trans. Robot."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"6439","DOI":"10.1109\/LRA.2022.3173426","article-title":"Predictive Locomotion Mode Recognition and Accurate Gait Phase Estimation for Hip Exoskeleton on Various Terrains","volume":"7","author":"Qian","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3491","DOI":"10.1109\/LRA.2021.3062562","article-title":"Real-Time Gait Phase Estimation for Robotic Hip Exoskeleton Control During Multimodal Locomotion","volume":"6","author":"Kang","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Mohammadzadeh Gonabadi, A., Pipinos, I.I., Myers, S.A., and Fallahtafti, F. (2025). Optimizing hip exoskeleton assistance pattern based on machine learning and simulation algorithms: A personalized approach to metabolic cost reduction. Front. Robot. AI, 12.","DOI":"10.3389\/frobt.2025.1669600"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"5435","DOI":"10.1038\/s41598-025-89764-w","article-title":"A soft exoskeleton for hip extension and flexion assistance based on reinforcement learning control","volume":"15","author":"Sun","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"eadq0288","DOI":"10.1126\/sciadv.adq0288","article-title":"AI-driven universal lower-limb exoskeleton system for community ambulation","volume":"10","author":"Lee","year":"2024","journal-title":"Sci. Adv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2550","DOI":"10.1109\/LRA.2023.3256135","article-title":"Environment-Based Assistance Modulation for a Hip Exosuit via Computer Vision","volume":"8","author":"Tricomi","year":"2023","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1109\/TMRB.2019.2961749","article-title":"Real-Time Neural Network-Based Gait Phase Estimation Using a Robotic Hip Exoskeleton","volume":"2","author":"Kang","year":"2020","journal-title":"IEEE Trans. Med. Robot. Bionics"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1804","DOI":"10.1007\/s42235-025-00723-7","article-title":"Deep Learning-Based Recognition of Locomotion Mode, Phase, and Phase Progression Using Inertial Measurement Units","volume":"22","author":"Kim","year":"2025","journal-title":"J. Bionic Eng."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Perry, J., Burnfield, J.M., and Cabico, L.M. (2024). Gait Analysis: Normal and Pathological Function, CRC Press. [2nd ed.].","DOI":"10.1201\/9781003525592"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"96515","DOI":"10.1109\/ACCESS.2020.2994374","article-title":"A novel force sensorless reflecting control for bilateral haptic teleoperation system","volume":"8","author":"Vo","year":"2020","journal-title":"IEEE Access"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Sorrentino, I., Romualdi, G., Bergonti, F., L\u2019Erario, G., Traversaro, S., and Pucci, D. (2024, January 22\u201324). Physics-Informed Learning for the Friction Modeling of High-Ratio Harmonic Drives. Proceedings of the 2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids), Nancy, France.","DOI":"10.1109\/Humanoids58906.2024.10769966"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Gao, X., Zhang, P., Peng, X., Zhao, J., Liu, K., Miao, M., Zhao, P., Luo, D., and Li, Y. (2023). Autonomous motion and control of lower limb exoskeleton rehabilitation robot. Front. Bioeng. Biotechnol., 11.","DOI":"10.3389\/fbioe.2023.1223831"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"352","DOI":"10.1109\/TNSRE.2015.2511448","article-title":"LOPES II-Design and Evaluation of an Admittance Controlled Gait Training Robot with Shadow-Leg Approach","volume":"24","author":"Meuleman","year":"2016","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"3419","DOI":"10.1017\/S0263574725102300","article-title":"Human\u2013machine coupling dynamics modeling and adaptive admittance control of lower limb rehabilitation robot","volume":"43","author":"Gao","year":"2025","journal-title":"Robotica"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Brasiliano, P., Mascia, G., Di Feo, P., Di Stanislao, E., Alvini, M., Vannozzi, G., and Camomilla, V. (2023). Impact of Gait Events Identification through Wearable Inertial Sensors on Clinical Gait Analysis of Children with Idiopathic Toe Walking. Micromachines, 14.","DOI":"10.3390\/mi14020277"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1049\/el.2020.0090","article-title":"Practical method for predicting intended gait speed via soleus surface EMG signals","volume":"56","author":"Kim","year":"2020","journal-title":"Electron. Lett."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"848","DOI":"10.1109\/TBME.2003.813539","article-title":"A robust, real-time control scheme for multifunction myoelectric control","volume":"50","author":"Englehart","year":"2003","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1002\/mus.880131008","article-title":"Measurement of the amplitude of the EMG envelope","volume":"13","author":"Nandedkar","year":"1990","journal-title":"Muscle Nerve"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1016\/j.jelekin.2011.04.004","article-title":"A fast implementation for EMG signal linear envelope computation","volume":"21","author":"Barzilay","year":"2011","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Stat. Soc."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1007\/BF00236201","article-title":"Excitability of the soleus H-reflex arc during walking and stepping in man","volume":"66","author":"Crenna","year":"1987","journal-title":"Exp. Brain Res."},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Cao, W., Zhang, Z., Chen, C., He, Y., Wang, D., and Wu, X. (2021). Biomechanical and Physiological Evaluation of a Multi-Joint Exoskeleton with Active-Passive Assistance for Walking. Biosensors, 11.","DOI":"10.3390\/bios11100393"},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Xu, L., Liu, X., Chen, Y., Yu, L., Yan, Z., Yang, C., Zhou, C., and Yang, W. (2023). Reducing the muscle activity of walking using a portable hip exoskeleton based on human-in-the-loop optimization. Front. Bioeng. Biotechnol., 11.","DOI":"10.3389\/fbioe.2023.1006326"},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"11004","DOI":"10.1038\/s41598-022-14784-9","article-title":"Reducing the energy cost of walking with low assistance levels through optimized hip flexion assistance from a soft exosuit","volume":"12","author":"Kim","year":"2022","journal-title":"Sci. Rep."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5008\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T08:06:50Z","timestamp":1786090010000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,7]]},"references-count":54,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165008"],"URL":"https:\/\/doi.org\/10.3390\/s26165008","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,7]]}}}