Task-agnostic exoskeleton control via biological joint moment estimation
Abstract
Lower-limb exoskeletons have the potential to transform the way we move 1-14, but current state-of-the-art controllers cannot accommodate the rich set of possible human behaviours that range from cyclic and predictable to transitory and unstructured. We introduce a task-agnostic controller that assists the user on the basis of instantaneous estimates of lower-limb biological joint moments from a deep neural network. By estimating both hip and knee moments in-the-loop, our approach provided multi-joint, coordinated assistance through our autonomous, clothing-integrated exoskeleton. When deployed during 28 activities, spanning cyclic locomotion to unstructured tasks (for example, passive meandering and high-speed lateral cutting), the network accurately estimated hip and knee moments with an average R 2 of 0.83 relative to ground truth. Further, our approach significantly outperformed a best-case task classifier-based method constructed from splines and impedance parameters. When tested on ten activities (including level walking, running, lifting a 25 lb (roughly 11 kg) weight and lunging), our controller significantly reduced user energetics (metabolic cost or lower-limb biological joint work depending on the task) relative to the zero torque condition, ranging from 5.3 to 19.7%, without any manual controller modifications among activities. Thus, this task-agnostic controller can enable exoskeletons to aid users across a broad spectrum of human activities, a necessity for real-world viability.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cites
Biomechanics and Motor Control of Human Movement
Winter, D. A. (2009) · Wiley eBooks · doi:10.1002/9780470549148 · Cited by 6,112 · see citing works
OpenSim: Open-Source Software to Create and Analyze Dynamic Simulations of Movement
Delp, S. L., Anderson, F. C., Arnold, A. S., Loan, P., Habib, A., John, C. T., Guendelman, E., & Thelen, D. G. (2007) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2007.901024 · Cited by 4,951 · see citing works
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Bai, S., Kolter, J. Z., & Koltun, V. (2018) · arXiv · doi:10.48550/arxiv.1803.01271 · Cited by 4,655 · see citing works
Seth, A., Hicks, J. L., Uchida, T. K., Habib, A., Dembia, C. L., Dunne, J. J., Ong, C. F., DeMers, M. S., Rajagopal, A., Millard, M., et al. (2018) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1006223 · Cited by 1,338 · see citing works
Reducing the energy cost of human walking using an unpowered exoskeleton
Collins, S. H., Wiggin, M. B., & Sawicki, G. S. (2015) · Nature · doi:10.1038/nature14288 · Cited by 1,027 · see citing works
Human-in-the-loop optimization of exoskeleton assistance during walking
Zhang, J., Fiers, P., Witte, K. A., Jackson, R. W., Poggensee, K. L., Atkeson, C. G., & Collins, S. H. (2017) · Science · doi:10.1126/science.aal5054 · Cited by 1,020 · see citing works
State of the Art and Future Directions for Lower Limb Robotic Exoskeletons
Young, A. J., & Ferris, D. P. (2016) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2016.2521160 · Cited by 909 · see citing works
Self-citationA soft robotic exosuit improves walking in patients after stroke
Awad, L. N., Bae, J., O’Donnell, K., De Rossi, S. M. M., Hendron, K., Sloot, L. H., Kudzia, P., Allen, S., Holt, K. G., Ellis, T. D., et al. (2017) · Science Translational Medicine · doi:10.1126/scitranslmed.aai9084 · Cited by 672 · see citing works
The Effects of Adding Mass to the Legs on the Energetics and Biomechanics of Walking
Browning, R. C., Modica, J. R., Kram, R., & Goswami, A. (2007) · Medicine & Science in Sports & Exercise · doi:10.1249/mss.0b013e31802b3562 · Cited by 607 · see citing works
Golovin, D., Solnik, B., Moitra, S., Kochanski, G., Karro, J. E., & Sculley, D. (2017) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3097983.3098043 · Cited by 585 · see citing works
The mechanics and energetics of human walking and running: a joint level perspective
Farris, D. J., & Sawicki, G. S. (2011) · Journal of The Royal Society Interface · doi:10.1098/rsif.2011.0182 · Cited by 575 · see citing works
Derivation of formulae used to calculate energy expenditure in man.
Jm, B. (1987) · PubMed · Cited by 568 · see citing works
Biomechanical Motor Patterns in Normal Walking
Winter, D. A. (1983) · Journal of Motor Behavior · doi:10.1080/00222895.1983.10735302 · Cited by 533 · see citing works
Reducing the metabolic rate of walking and running with a versatile, portable exosuit
Kim, J., Lee, G., Heimgartner, R., Revi, D. A., Karavas, N. C., Nathanson, D., Galiana, I., Eckert-Erdheim, A. M., Murphy, P., Perry, D., et al. (2019) · Science · doi:10.1126/science.aav7536 · Cited by 491 · see citing works
Autonomous exoskeleton reduces metabolic cost of human walking during load carriage
Mooney, L. M., Rouse, E. J., & Herr, H. (2014) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/1743-0003-11-80 · Cited by 466 · see citing works
A Simple Exoskeleton That Assists Plantarflexion Can Reduce the Metabolic Cost of Human Walking
Malcolm, P., Derave, W., Galle, S., & Clercq, D. D. (2013) · PLoS ONE · doi:10.1371/journal.pone.0056137 · Cited by 428 · see citing works
The exoskeleton expansion: improving walking and running economy
Sawicki, G. S., Beck, O. N., Kang, I., & Young, A. J. (2020) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-020-00663-9 · Cited by 424 · see citing works
Self-citationMeasurement and reduction of noise in kinematics of locomotion
Winter, D. A., Sidwall, H. G., & Hobson, D. (1974) · Journal of Biomechanics · doi:10.1016/0021-9290(74)90056-6 · Cited by 407 · see citing works
Camargo, J., Ramanathan, A., Flanagan, W., & Young, A. J. (2021) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2021.110320 · Cited by 371 · see citing works
Self-citationPersonalizing exoskeleton assistance while walking in the real world
Slade, P., Kochenderfer, M. J., Delp, S. L., & Collins, S. H. (2022) · Nature · doi:10.1038/s41586-022-05191-1 · Cited by 339 · see citing works
How humans walk: Bout duration, steps per bout, and rest duration
Orendurff, M. S. (2008) · The Journal of Rehabilitation Research and Development · doi:10.1682/jrrd.2007.11.0197 · Cited by 306 · see citing works
Opportunities and challenges in the development of exoskeletons for locomotor assistance
Siviy, C., Baker, L. M., Quinlivan, B., Porciuncula, F., Swaminathan, K., Awad, L. N., & Walsh, C. J. (2022) · Nature Biomedical Engineering · doi:10.1038/s41551-022-00984-1 · Cited by 267 · see citing works
Effect of timing of hip extension assistance during loaded walking with a soft exosuit
Ding, Y., Panizzolo, F. A., Siviy, C., Malcolm, P., Galiana, I., Holt, K. G., & Walsh, C. J. (2016) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-016-0196-8 · Cited by 250 · see citing works
Ancillao, A., Tedesco, S. A., Barton, J. J., & O’Flynn, B. (2018) · Sensors · doi:10.3390/s18082564 · Cited by 244 · see citing works
How adaptation, training, and customization contribute to benefits from exoskeleton assistance
Poggensee, K. L., & Collins, S. H. (2021) · Science Robotics · doi:10.1126/scirobotics.abf1078 · Cited by 218 · see citing works
Witte, K. A., Fiers, P., Sheets, A. L., & Collins, S. H. (2020) · Science Robotics · doi:10.1126/scirobotics.aay9108 · Cited by 188 · see citing works
Design and Validation of a Torque-Controllable Knee Exoskeleton for Sit-to-Stand Assistance
Shepherd, M. K., & Rouse, E. J. (2017) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2017.2704521 · Cited by 176 · see citing works
Self-citationReal-Time Gait Phase Estimation for Robotic Hip Exoskeleton Control During Multimodal Locomotion
Kang, I., Molinaro, D. D., Duggal, S., Chen, Y., Kunapuli, P., & Young, A. J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2021.3062562 · Cited by 164 · see citing works
Self-citationThe effect of a passive trunk exoskeleton on metabolic costs during lifting and walking
Baltrusch, S. J., van Dieën, J. H., Bruijn, S. M., Koopman, A. S., van Bennekom, C. A. M., & Houdijk, H. (2019) · Ergonomics · doi:10.1080/00140139.2019.1602288 · Cited by 159 · see citing works
Lim, H., Kim, B. J., & Park, S. (2019) · Sensors · doi:10.3390/s20010130 · Cited by 155 · see citing works
Estimating instantaneous energetic cost during non-steady-state gait
Selinger, J. C., & Donelan, J. M. (2014) · Journal of Applied Physiology · doi:10.1152/japplphysiol.00445.2014 · Cited by 148 · see citing works
Dorschky, E., Nitschke, M., Martindale, C. F., van den Bogert, A. J., Koelewijn, A. D., & Eskofier, B. M. (2020) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2020.00604 · Cited by 137 · see citing works
Estimating human joint moments unifies exoskeleton control, reducing user effort
Molinaro, D. D., Kang, I., & Young, A. J. (2024) · Science Robotics · doi:10.1126/scirobotics.adi8852 · Cited by 128 · see citing works
Self-citationFranks, P. W., Bryan, G. M., Martin, R., Reyes, R., Lakmazaheri, A., & Collins, S. H. (2021) · Wearable Technologies · doi:10.1017/wtc.2021.14 · Cited by 126 · see citing works
Farris, D. J., Hampton, A., Lewek, M. D., & Sawicki, G. S. (2015) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-015-0012-x · Cited by 123 · see citing works
Proportional Joint-Moment Control for Instantaneously Adaptive Ankle Exoskeleton Assistance
Gasparri, G. M., Luque, J., & Lerner, Z. F. (2019) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2019.2905979 · Cited by 116 · see citing works
Delayed Output Feedback Control for Gait Assistance With a Robotic Hip Exoskeleton
Lim, B., Lee, J., Jang, J., Kim, K., Park, Y. J., Seo, K., & Shim, Y. (2019) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2913318 · Cited by 112 · see citing works
Qian, Y., Wang, Y., Chen, C., Xiong, J., Leng, Y., Yu, H., & Fu, C. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3173426 · Cited by 108 · see citing works
Forner‐Cordero, A., Koopman, H. F. J. M., & van der Helm, F. C. T. (2005) · Gait & Posture · doi:10.1016/j.gaitpost.2005.02.002 · Cited by 105 · see citing works
Spine-Inspired Continuum Soft Exoskeleton for Stoop Lifting Assistance
Yang, X., Huang, T.-H., Hu, H., Yu, S., Zhang, S., Zhou, X. A., Carriero, A., Yue, G. H., & Su, H. (2019) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2019.2935351 · Cited by 105 · see citing works
Nuckols, R. W., Takahashi, K. Z., Farris, D. J., Mizrachi, S., Riemer, R., & Sawicki, G. S. (2020) · PLoS ONE · doi:10.1371/journal.pone.0231996 · Cited by 101 · see citing works
Mundt, M., Johnson, W. R., Potthast, W., Markert, B., Mian, A., & Alderson, J. (2021) · Sensors · doi:10.3390/s21134535 · Cited by 95 · see citing works
Linking the mechanics and energetics of hopping with elastic ankle exoskeletons
Farris, D. J., & Sawicki, G. S. (2012) · Journal of Applied Physiology · doi:10.1152/japplphysiol.00802.2012 · Cited by 91 · see citing works
Molinaro, D. D., Kang, I., Camargo, J., Gombolay, M. C., & Young, A. J. (2022) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2022.3144025 · Cited by 90 · see citing works
Self-citationGait mode recognition and control for a portable-powered ankle-foot orthosis
Li, Y. D., & Hsiao‐Wecksler, E. T. (2013) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr.2013.6650373 · Cited by 88 · see citing works
Medrano, R. L., Thomas, G. C., Keais, C. G., Rouse, E. J., & Gregg, R. D. (2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3235584 · Cited by 82 · see citing works
Laschowski, B., McNally, W., Wong, A. K. C., & McPhee, J. (2022) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2021.730965 · Cited by 82 · see citing works
Hossain, M. S. B., Guo, Z., & Choi, H. Y. (2023) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2023.3262164 · Cited by 82 · see citing works
Camargo, J., Flanagan, W., Csomay-Shanklin, N., Kanwar, B., & Young, A. J. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3065809 · Cited by 79 · see citing works
Self-citationImpedance Modulation Control of a Lower-Limb Exoskeleton to Assist Sit-to-Stand Movements
Huo, W., Moon, H., Alouane, M. A., Bonnet, V., Huang, J., Amirat, Y., Vaidyanathan, R., & Mohammed, S. (2021) · IEEE Transactions on Robotics · doi:10.1109/tro.2021.3104244 · Cited by 75 · see citing works
Alexander, N., Strutzenberger, G., Ameshofer, L. M., & Schwameder, H. (2017) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2017.07.001 · Cited by 68 · see citing works
Powered hip exoskeleton improves walking economy in individuals with above-knee amputation
Ishmael, M. K., Archangeli, D., & Lenzi, T. (2021) · Nature Medicine · doi:10.1038/s41591-021-01515-2 · Cited by 67 · see citing works
Adaptive Ankle Exoskeleton Control: Validation Across Diverse Walking Conditions
Bishe, S. S. P. A., Nguyen, T. T., Fang, Y., & Lerner, Z. F. (2021) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2021.3091519 · Cited by 62 · see citing works
Deep Learning Enables Exoboot Control to Augment Variable-Speed Walking
Shepherd, M. K., Molinaro, D. D., Sawicki, G. S., & Young, A. J. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3147565 · Cited by 57 · see citing works
Self-citationKang, I., Molinaro, D. D., Choi, G., Camargo, J., & Young, A. J. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3165547 · Cited by 55 · see citing works
Self-citationA human lower-limb biomechanics and wearable sensors dataset during cyclic and non-cyclic activities
Scherpereel, K. L., Molinaro, D. D., Inan, O. T., Shepherd, M. K., & Young, A. J. (2023) · Scientific Data · doi:10.1038/s41597-023-02840-6 · Cited by 52 · see citing works
Self-citationPredicting biological joint moment during multiple ambulation tasks
Camargo, J., Molinaro, D. D., & Young, A. J. (2022) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2022.111020 · Cited by 42 · see citing works
Self-citationLenton, G. K., Doyle, T., Lloyd, D., Higgs, J. P., Billing, D., & Saxby, D. (2019) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2018.11.036 · Cited by 35 · see citing works
Leveraging user preference in the design and evaluation of lower-limb exoskeletons and prostheses
Ingraham, K. A., Tucker, M., Ames, A. D., Rouse, E. J., & Shepherd, M. K. (2023) · Current Opinion in Biomedical Engineering · doi:10.1016/j.cobme.2023.100487 · Cited by 34 · see citing works
Self-citationFang, Y., Orekhov, G., & Lerner, Z. F. (2021) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2021.3137447 · Cited by 33 · see citing works
Walking on Real-World Terrain With an Ankle Exoskeleton in Cerebral Palsy
Tagoe, E. A., Fang, Y., Williams, J. R., & Lerner, Z. F. (2023) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2023.3328649 · Cited by 32 · see citing works
Franks, P. W., Bryan, G. M., Martin, R., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.02.19.431882 · Cited by 25 · see citing works
Reducing the energy cost of running using a lightweight, low-profile elastic exosuit
Yang, J., Park, J., Kim, J., Park, S., & Lee, G. (2021) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-021-00928-x · Cited by 25 · see citing works
Lin, J., Divekar, N., Thomas, G. C., & Gregg, R. D. (2022) · IEEE Open Journal of Control Systems · doi:10.1109/ojcsys.2022.3165733 · Cited by 21 · see citing works
Molinaro, D. D., Park, E. O., & Young, A. J. (2023) · 2023 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra48891.2023.10161286 · Cited by 14 · see citing works
Self-citationLower-limb kinematics and kinetics during continuously varying human locomotion
Reznick, E., Embry, K., Neuman, R. M., Bolívar-Nieto, E., Fey, N. P., & Gregg, R. D. (2021) · Scientific Data · doi:10.1038/s41597-021-01057-9 · Cited by 11 · see citing works
Optimal Energy Shaping Control for a Backdrivable Hip Exoskeleton
Zhang, J., Lin, J., Peddinti, V., & Gregg, R. D. (2023) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc55779.2023.10155839 · Cited by 10 · see citing works
Spine-Inspired Continuum Soft Exoskeleton for Stoop Lifting AssistancePreprint
Yang, X., Huang, T.-H., Hu, H., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.02562 · Cited by 6 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Wearable Robots for Rehabilitation and Assistance of Gait: A Narrative Review
Cha, J. M., Hong, J., Yoo, J., & Rha, D. (2025) · Annals of Rehabilitation Medicine · doi:10.5535/arm.250093 · Cited by 40 · see citing works
“Wearable exoskeletons have shown significant potential to enhance mobility and independence in individuals with neurological and musculoskeletal conditions, including stroke, SCI, CP, and PD [64].”
From material-derived to artificial intelligence-empowered intelligent hydrogels
Zheng, S., Zhu, Z., & Sun, D.-W. (2025) · Coordination Chemistry Reviews · doi:10.1016/j.ccr.2025.217198 · Cited by 26 · see citing works
AI in therapeutic and assistive exoskeletons and exosuits: Influences on performance and autonomy
van der Kooij, H., van Asseldonk, E. H. F., Sartori, M., Basla, C., Esser, A., & Riener, R. (2025) · Science Robotics · doi:10.1126/scirobotics.adt7329 · Cited by 22 · see citing works
Wearable technologies for assisted mobility in the real world
Gao, S., Chen, J., Xia, Y., Li, X., Ma, W., Yang, H., Li, J., Zhou, X., Jia, T., Xu, Y., et al. (2025) · Nature Communications · doi:10.1038/s41467-025-67126-4 · Cited by 21 · see citing works
“These devices incorporate sensorslikeIMUsandforce-sensitiveresistorstocontinuouslymonitor the patient ’ s movement intentions and physical condition, allowing real-time,adaptiveassistance 89,90 (Fig.4a).”
OpenExo: An open-source modular exoskeleton to augment human function
Williams, J. R., Cuddeback, C. F., Fang, S., Colley, D. G., Enlow, N., Cox, P., Pridham, P., & Lerner, Z. F. (2025) · Science Robotics · doi:10.1126/scirobotics.adt1591 · Cited by 17 · see citing works
Ali, A., Cai, R., Wang, T., Zhang, C., Liu, C., Ma, D., Hou, H., Lei, Q., Xia, Y., Wang, S., et al. (2025) · Chemical Engineering Journal · doi:10.1016/j.cej.2025.165358 · Cited by 17 · see citing works
Comprehensive human locomotion and electromyography dataset: Gait120
Boo, J., Seo, D., Kim, M., & Koo, S. (2025) · Scientific Data · doi:10.1038/s41597-025-05391-0 · Cited by 15 · see citing works
Moya-Esteban, A., Refai, M. I. M., Sridar, S., van der Kooij, H., & Sartori, M. (2025) · Wearable Technologies · doi:10.1017/wtc.2025.3 · Cited by 11 · see citing works
“Reductions of metabolic cost of walking while wearing an exosuit have been achieved by providing delayed biological hip and knee torque estimates (Molinaro et al., 2024).”
Khan, S. U. E., Varghese, R. J., Kassanos, P., Farina, D., & Burdet, E. (2025) · Cyborg and Bionic Systems · doi:10.34133/cbsystems.0477 · Cited by 10 · see citing works
“For example, Molinaro et al. [ 279 ] demonstrated a deep neural network-based controller that rapidly estimates lower-limb joint moments, enabling exoskeletons better to assist users in a wide range of movements.”
Pang, Z., Zhang, L., Liu, F., Meng, A., Yu, H., & Hu, B. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108612 · Cited by 10 · see citing works
Sartori, M., Refai, M. I. M., Gaudio, L. A., Cop, C. P., Simonetti, D., Damonte, F., Hambly, M. J., Lloyd, D. G., Pizzolato, C., & Durandau, G. (2025) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2025.3643986 · Cited by 9 · see citing works
“With respect to today’s end-to-end machine learning-based controllers requiring hours of training data [29], CEINMS-RT required less than a minute of training data [19], [23], [47].”
InfluentialFlexible sensor arrays with high-resolution and high-density
Huang, J., Liu, J., Zhang, G., Nie, L., Xiong, Y., Zhu, Y., Wang, Z. L., & Sun, Q. (2026) · Nano Energy · doi:10.1016/j.nanoen.2026.111748 · Cited by 9 · see citing works
Chen, S., Peng, C., Yang, B., Lin, J., Zhou, L., Jiang, Z., Liu, Z., Liu, Y., & Tang, L. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00083-5 · Cited by 9 · see citing works
Wu, X., Xu, M. Y., Zhou, Z., Lou, W., Zhang, T., Zhou, Y., Mai, J., & Wang, Q. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3621405 · Cited by 8 · see citing works
“These exoskeletons generated muscle activation inspired [9], [17], [59], [60] or joint power inspired [8], [19], [34], [45], [58] assistive profiles to cooperate with humans and augment human performance.”
InfluentialStride-Wise Adaptive Assistance Strategy for Ankle Exoskeleton Under Varying Walking Conditions
Yin, W., Jing, Z., Ding, J., Han, J., Han, J., & Zhang, J. (2025) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2025.3602098 · Cited by 7 · see citing works
“Effective assistance must achieve personalization, which accounts for user-specific motion strategies, and generalization, which ensures applicability across diverse tasks and environments [4], [21].”
Tang, Z.-L., Wang, Y., Mao, S., & Wei, D. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3632757 · Cited by 5 · see citing works
“These include LSTM [16] and GRU [17], which serve as classical benchmarks for sequential modeling; TCN [4], [18], representing convolution-based approaches; and two Transformer-based models—Informer [21] and the recently introduced iTransformer [22]—as advanced baselines.”
InfluentialMachine Learning Enables Rapid Detection of Slips Using a Robotic Hip Exoskeleton
Peterson, R. R., Leestma, J. K., Kang, I., & Young, A. J. (2025) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2025.3560331 · Cited by 5 · see citing works
“…drop in detection time may be that while CNN’s and other deep learning models have historically shown impressive results in exoskeleton-based applications [31], [43], [45], these applications were more general, with large, multi-task datasets, which are great for data-hungry deep learning models.”
Self-citationDeep-Learning Control of Lower-Limb Exoskeletons via Simplified Therapist Input
Vianello, L., Lhoste, C., Küçüktabak, E. B., Short, M. R., Hargrove, L. J., & Pons, J. L. (2025) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr66766.2025.11063140 · Cited by 5 · see citing works
“One potential solution to reduce controller complexity and calibration time is to employ data-driven methods that relate sensor readings with command outputs [9]–[11].”
Deep domain adaptation eliminates costly data required for task-agnostic wearable robotic control
Scherpereel, K. L., Gombolay, M., Shepherd, M. K., Carrasquillo, C., Inan, O. T., & Young, A. J. (2025) · Science Robotics · doi:10.1126/scirobotics.ads8652 · Cited by 4 · see citing works
Self-citationOuyang, J., Li, P., Zou, Y., Liu, G., Zeng, H., Han, R., Li, D., Zheng, W., Sun, J., & Tao, G. (2025) · National Science Review · doi:10.1093/nsr/nwaf560 · Cited by 4 · see citing works
Ye, Q., Yang, X., Zhao, R., Ji, Y., Cai, X., Zheng, Q. S., & Fan, Y. (2025) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2025.3646165 · Cited by 4 · see citing works
“…modalities—such as pairing stable IMU/encoder data with predictive signals like sEMG or vision—fusion strategies can integrate both internal physiological states and external environmental awareness [142], [143], [144], [145], [146], [147], [148], [149], [150], [151], [163], [164], [165].”
Li, J. Q., Zhang, B., Tan, X., Chen, W., Liu, Z., Zhang, J. L., Huo, W., Huang, J., Liu, L., & Zhao, X. (2026) · The International Journal of Robotics Research · doi:10.1177/02783649261444046 · Cited by 4 · see citing works
“As shown in Figure 22 (d), an end-to-end controller developed based on our dataset can dynamically adjust to changing motion tasks while ensuring scalability (Molinaro et al., 2024b).”
Prete, A. D., Gandolla, M., Andreoni, G., & Braghin, F. (2025) · Sensors · doi:10.3390/s25071958 · Cited by 4 · see citing works
“Moreover, while simulation environments have already been increasingly employed in other domains, such as lower-limb exoskeletons, to develop intelligent high-level control strategies [26,27], they have also led to significant performance improvements in final implementations.”
Ankle Exoskeleton Control via Data-Driven Gait Estimation for Walking, Running, and Inclines
Shetty, P. R., Menezes, J. A., Song, S., Young, A. J., & Shepherd, M. K. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3561566 · Cited by 4 · see citing works
“These techniques range from task classification [14], environment estimation [15] (such as ground incline or the presence of stairs), prediction of physiological state [6], [16], or prediction of gait state.”
Self-citationLv, J., Huang, B., & Qiang, L. (2025) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-025-00164-6 · Cited by 4 · see citing works
“As a wearable mechanical device, exoskeleton robots have gained widespread application in various specialized work scenarios in recent years, particularly in fields such as climbing, rescue, and military operations (Molinaro et al. 2024).”
Imitation Learning for Adaptive Control of a Virtual Soft Exoglove
Lyu, S., Caggiano, V., Leonetti, M., Farina, D., & Gionfrida, L. (2025) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr66766.2025.11063210 · Cited by 3 · see citing works
Human-Interface Dynamics of Knee Exoskeletons with Lateral and Anteroposterior Attachment
Wang, Y., Pérez, J. A. M., Gregg, R. D., & Thomas, G. C. (2025) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr66766.2025.11062962 · Cited by 3 · see citing works
“Exoskeletons that attach laterally to the joint and limb, such as the M-BLUE platform [5], [12] or clothing-integrated exoskeleton [13] developed under Skip and Arc’teryx have a simple design concept that is well-suited to a lightweight construction.”
Optimizing Human–Exoskeleton Physical Interaction Through Spatial Trajectory Adaptation
Shushtari, M., Murray, L., Siavashani, A. G., & Arami, A. (2026) · IEEE Transactions on Robotics · doi:10.1109/tro.2026.3663979 · Cited by 3 · see citing works
“…has been realized using a variety of approaches, including estimation of user-desired joint torques via electromyography [8] or kinetic and kinematic measurements [9], [10], energy shaping [11], [12], hybrid feedback–feedforward control strategies [13], and reflex-based controllers [14], [15].”
InfluentialLee, J.-H., Nam, G. J., Lee, J., Seo, J., Ryu, G., Kim, K., & Lee, W. G. (2025) · Sensors and Actuators A Physical · doi:10.1016/j.sna.2025.116567 · Cited by 3 · see citing works
Bechet, R., Tisserand, R., Fradet, L., & Colloud, F. (2025) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2025.112860 · Cited by 2 · see citing works
Casey, R. T. F., Nuesslein, C. P. O., Davenport, F., Wheeler, J. W., Mazumdar, A., Sawicki, G. S., & Young, A. J. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3589996 · Cited by 2 · see citing works
“It was further developed by Molinaro et al. [32] for the purposes of biological moment estimation for hip/knee exoskeleton control.”
InfluentialSelf-citationEnhanced gastrocnemius-mimicking lower limb powered exoskeleton robot
Chen, T., Liu, Z., Li, C., Chen, X., Hu, J., & He, Y. (2025) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-025-01703-y · Cited by 2 · see citing works
“Furthermore, the absence of effective energy transfer mechanisms leads to unnecessary energy consumption, reducing the endurance of the device wearer [28, 29].”
Squat Training Assisted by a Rigid-Soft Hybrid Knee Exoskeleton: A Preliminary Study
Dai, X., Xu, M. Y., Zhong, H., Zhou, Z., Wang, R., Rong, X., Li, Y., & Wang, Q. (2025) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2025.3604140 · Cited by 2 · see citing works
“Wearable robotic technology has shown promise in providing supportive assistance, effectively reducing muscle activation and metabolic demand [14], [15], [16], [17], [18].”
Assistive Control of Knee Exoskeletons for Human Walking on Sandy Terrain
Zhu, C., Chen, X., & Yi, J. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3608132 · Cited by 2 · see citing works
“Recent advancements, such as task-agnostic exoskeleton control based on biological joint moment estimation [29], have demonstrated the potential to adapt to different activities and walking speeds.”
Guo, Y. G., Yang, X., Chen, Z., Yan, X., & Liu, F. (2025) · Robotica · doi:10.1017/s0263574725102142 · Cited by 2 · see citing works
“Meanwhile, Molinaro et al. [38] also proposed a task-agnostic exoskeleton control method.”
A Rigid-Flexible Coupled Lower Limb Exoskeleton for Enhancing Load-Bearing Ambulation
Tian, Y.-T., Chen, C., Wu, X., & Cao, W. (2025) · Biomimetics · doi:10.3390/biomimetics10110757 · Cited by 2 · see citing works
“The research conducted by the Molinaro team reveals that exoskeletons composed of integrated rigid components and soft outer garments achieved a maximum reduction of 19.70% in metabolic cost during tests with an 11 kg load [22].”
InfluentialRaz, D., Özay, N., & Umberger, B. R. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11252786 · Cited by 2 · see citing works
“124 s reported in the literature [20], [21].”
Miller, E. Y., Tan, T., Falisse, A. M. D., & Uhlrich, S. D. (2026) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2026.3691975 · Cited by 2 · see citing works
The perceptual and biomechanical effects of scaling back exosuit assistance to changing task demands
Chung, J., Quirk, D. A., Cherin, J. M., Friedrich, D., Kim, D., & Walsh, C. J. (2025) · Scientific Reports · doi:10.1038/s41598-025-94726-3 · Cited by 2 · see citing works
“Increasing device adaptability can improve biomechanical effectiveness 33,34 , which benefits back exos.”
InfluentialJoint moment estimation for hip exoskeleton control: A generalized moment feature generation method
Zhang, Y., Xiong, J., Xian, H., Chen, C., Chen, X., Liang, H., Fu, C., & Leng, Y. (2025) · Biomimetic Intelligence and Robotics · doi:10.1016/j.birob.2025.100246 · Cited by 2 · see citing works
Ramella, G., Ijspeert, A. J., & Bouri, M. (2025) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr66766.2025.11063198 · Cited by 2 · see citing works
“During multi-terrain locomotion, exoskeletons must dynamically adapt the assistance strength to meet varying demands across terrains [13]–[15].”
Paing, S. L., Alili, A., Nalam, V., & Huang, H. (2025) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr66766.2025.11063194 · Cited by 2 · see citing works
“While there is an increasing prevalence of exoskeletons developed for lower limb assistance, most devices primarily target assistance in the anteroposterior (AP) direction [13]– [15].”
Model-Based Control Strategies Comparison of One Bionic Ankle Tensegrity Exoskeleton: BATE
Wei, D., Mao, S., Zhang, Z., Wei, X., Gao, T., & Ficuciello, F. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127237 · Cited by 2 · see citing works
“Lower extremity exoskeletons hold great promise in various areas [1]–[5], including industrial assistance with heavy lifting [6], medical rehabilitation [7], [8], and military load support applications [9].”
A single-fibre computer reshapes the future of wearable electronics
Peng, X., & Zhang, Y. (2025) · 中国科学通报：英文版 · doi:10.1016/j.scib.2025.04.054 · Cited by 1 · see citing works
Direct User Control of Knee Exoskeletons
Bucknor-Smartt, Z., Mustafa, J., Graves, L., Bannick, W., Korwani, M., & Thomas, G. C. (2025) · Systems and Information Engineering Design Symposium · doi:10.1109/sieds65500.2025.11021159 · Cited by 1 · see citing works
Optimizing Locomotor Task Sets for Training a Biological Joint Moment Estimator
An, J., Song, C.-S., Halilaj, E., & Kang, I. (2025) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr66766.2025.11063074 · Cited by 1 · see citing works
“Studies have demonstrated that user-independent models typically require data from at least a dozen participants completing multiple tasks [12], [16], with some relying on even larger groups and more diverse tasks [10], [11].”
InfluentialPowell, J. C., Schonhaut, E. B., Molinaro, D. D., & Young, A. J. (2026) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2026.3712823 · Cited by 1 · see citing works
“This study employs the TCN developed by Molinaro et al. [18], where biological joint moment estimates are produced instantaneously upon receiving exoskeleton sensor data.”
InfluentialSelf-citationTu, Y., Song, J., Zhu, A., Zhang, B., Yu, F. R., & Li, Q. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247763 · Cited by 1 · see citing works
Towards Data-Driven Adaptive Exoskeleton Assistance for Post-stroke Gait
Weigend, F. C., Choe, D. K., Canete, S., & Walsh, C. J. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246935 · Cited by 1 · see citing works
“[12] and then [13] further evaluated their TCN architecture across a wide range of dynamic tasks, highlighting its versatility.”
InfluentialInteraction-based rapid heuristic optimization of exoskeleton assistance during walking
Chen, J., Yin, W., Ding, J., Han, J., Zhang, L., Han, J., & Zhang, J. (2025) · Communications Engineering · doi:10.1038/s44172-025-00574-4 · Cited by 2 · see citing works
“Among them, state-of-the-art exoskeleton planning methods mainly fall into two categories: instantaneous neural-network-based ones 21,22,30 , and adaptive personalization-based ones 5,17 .”
InfluentialGIDMP-based Gait Generation and Adaptive Switching Control for Lower Limb Exoskeleton
Long, Y., Guo, H., Cai, Z., He, L., Dong, W., Liu, T., & Yi, J. (2026) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2026.3656391 · Cited by 1 · see citing works
“The research by Molinaro et al. [34] remains highly instructive.”
Wang, X., Shi-sheng, Z., Li, J., Sun, W., Ren, Z., Cao, W., Yin, M. D., & Wu, X. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3668388 · Cited by 1 · see citing works
“Given the shortage of rehabilitation therapists and the high skill requirements, robot-assisted rehabilitation is becoming the trend of the future [3], [4].”
Scherpereel, K. L., Bath, J. E., Roumiantseva, A., Marks, J., Wang, D. D., & Franks, P. W. (2026) · Frontiers in Robotics and AI · doi:10.3389/frobt.2026.1770510 · Cited by 1 · see citing works
“…results indicate that participant-specific models may be worth pursuing for other estimates, such as more end-to-end AI-based controls approaches (Molinaro et al., 2024), where improved estimation performance may be more tied to user outcomes than it was for gait-phase-based spline control on…”
Self-citationSynthetic Data-Driven Exoskeleton Control via Contralateral Gait Fusion for Variable-Speed Walking
Shi, J., Zhu, H., Yang, Y., Liu, B., & Wang, X. (2026) · Biomimetics · doi:10.3390/biomimetics11050319 · Cited by 1 · see citing works
Qiu, H., Xiang, Q., Weng, Z., Xu, P., Xue, W., & Liao, N. (2026) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2026.140269 · Cited by 1 · see citing works
Jakubowski, K. L., Sawicki, G. S., & Ting, L. H. (2026) · Journal of NeuroEngineering and Rehabilitation · doi:10.1186/s12984-026-02035-1 · Cited by 1 · see citing works
“Machine learning has recently been shown to be a promising approach for predicting physiological states across different tasks [34].”
InfluentialRobotic exoskeleton adapts to changes in leg movements in real time
Kim, M., & Major, M. J. (2024) · Nature · doi:10.1038/d41586-024-03546-4 · Cited by 1 · see citing works
High-Frequency Terrain Characterization with a Wearable Visual Device
Zhao, S., Tan, J., Liu, F., Ruan, L., & Wang, Q. (2025) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar64901.2025.11073008 · Cited by 1 · see citing works
Nabipour, M., Sawicki, G. S., & Sartori, M. (2025) · IEEE Transactions on Medical Robotics and Bionics · doi:10.1109/tmrb.2025.3560385
“These approaches encompass proportional myoelectric control [8], real-time EMG-driven model-based techniques [9], and deep neural network-based proportionate joint moment control [10].”
Monteiro, A. S., Major, M. J., & Fey, N. P. (2025) · International Conference on Rehabilitation Robotics · doi:10.1109/icorr66766.2025.11063117
“Recent studies show promising ubiquitous exoskeleton assistance through instantaneous estimates of lower-limb biological joint moments [29].”
Bian, Q., Yin, W., Han, J., Han, J., & Zhang, J. (2025) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr65461.2025.11072635
Engineering snags for spatial curvature in weaves: fabrication, mechanics, and inverse design
Tu, G., & Filipov, E. T. (2025) · Soft Matter · doi:10.1039/d5sm00813a
“Therefore, our strategy for inverse design of snagged plain-woven surfaces can be easily applied to make customized human exoskeleton suits 40,49 .”
A Reduced Gravity Simulation System for Astronauts Training Based on Lower Limb Exoskeleton Robot
Xian, H., Zhang, Y., Xiong, J., Lei, C., Fu, C., & Leng, Y. (2025) · IEEE International Conference on Cyborg and Bionic Systems (CBS) · doi:10.1109/cbs65871.2025.11267641
“And there is a possibility that the simulation of microgravity under multiple terrains will provide better training [16], [17].”
Yin, W., Ding, J., Wang, L., Jing, Z., Han, J., & Zhang, J. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3654730
“W EARABLE robotic systems, particularly lower-limb exoskeletons, represent transformative technologies for mobility enhancement, rehabilitation, and human–robot collaboration [1], [2], [3], [4].”
Predictive torque assistance for balance recovery: a task-level feature model for knee exoskeletons
Wang, P., Cao, Y., Chen, Z., Ma, B., Han, Y., & Liang, J. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131264
Dual-Branch Fusion Network: Precise Decoding of Lower Limb Multi-Joint Torque
Liang, F., Shi, X., Lu, H., Qin, P., Huang, L., Yang, Z., & Liu, Y. (2026) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2026.3661176
“These features collectively provide notable advantages for processing biomechanical signals [23], [25].”
Zhang, L., Zhu, M., Jiang, S. B., & Jiang, B. (2026) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-026-03529-9
Chen, L., Cui, F., & Lu, H. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3666397
A Simulation-based Lower-Limb Exoskeleton Control Method
Zhou, Y., Chen, C., Zhang, J., Liu, Y., Zhang, R., Zhang, Z., & Wu, X. (2025) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio66223.2025.11377519
“These methods, often built on deep neural networks, exhibit strong adaptability—enabling a single network to learn assistance strategies for multiple tasks [3] and showing improved generalization as task diversity increases [4].”
Optimization of an Axial Flux Motor-Cycloid Gear Actuator for Sizing Wearable Robots
Cooper, M., Canete, S., Chappell, D., & Walsh, C. J. (2026) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2026.3662305
“For this reason, quasi-direct drive actuators have gained popularity in wearable robotics [7], [8].”
Exploring Variable Achilles Tendon Loading via Active Acoustics
Rosa, L. G., Ozmen, G. C., Nichols, C. J., Sawicki, G. S., & Inan, O. T. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3671165
“While there are ID methods that can overcome these, as those leveraging shoe insoles for GRFs [7], there is limited research that explores these conditions [59], [60], [61] and that properly controls for variables like hop height, multijoint activation schemes, and participant technique, all of…”
InfluentialMotion Adaptation for Exoskeletons Across Users and Tasks via Meta-Learning
Ma, M., Xia, X., Han, L.-J., Li, H., & Cheng, L. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3673986
“[16]developedatask-agnostic controller that significantly reduced user energy expenditure across 28 different tasks.”
Azam, H., Xu, W., Feng, L., Yang, C., Gerževič, M., & Yang, W. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132047
Zhu, Z., Chen, W., Kao, P.-C., Clark, J. P., Behnke, L., Kramer-Bottiglio, R. K., Yanco, H. A., & Gu, Y. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3675944
“2) Learning-Based Estimation: Machine learning methods have been widely adopted for human movement estimation and to address nonlinearities of wearable soft sensors [11], [12], [13].”
Adaptive Support and Integrated Force Measurement for Passive Exoskeletons
Vur, B., Panter, L., Petzoldt, C., Boger, D., Jathe, N., & Freitag, M. (2026) · Procedia Computer Science · doi:10.1016/j.procs.2026.02.010
Experiment-free learning of exoskeleton assistance remains an unsolved problemPreprint
Collins, S. H., Groote, F. D., Gregg, R. D., Huang, H., Lenzi, T., Sartori, M., Sawicki, G. S., Si, J., Slade, P., & Young, A. J. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.04.01.715109
“We also analyzed Molinaro et al. (2024), which used a data-driven neural network similar to that used by Luo et al., and obtained an energy ratio of 1:0.8.”
InfluentialSelf-citationInteraction-Aware Stiffness Design for Muscle-Inspired Tensegrity Exoskeleton
Wei, D., Cui, C., & Cao, Y. (2026) · Journal of Bionic Engineering · doi:10.1007/s42235-026-00897-8
Diff-MomentFormer: Generative Diffusion-Augmented Transformer for End-to-End Joint Moment Estimation
Qiao, C., Liu, E., Ren, J., & He, L. (2026) · Sensors · doi:10.3390/s26102944
Bioinspired multisegment knee exoskeletons with variable stiffness and kinematic compatibility
Xu, M., Zhou, Z., Lou, W., Dai, X., Wang, R., Agrawal, S. K., & Wang, Q. (2026) · The International Journal of Robotics Research · doi:10.1177/02783649261443651
A gym on a fiber: Intelligent resistance bands empowering the digital training revolution
Chen, Y. H., Guo, P., Liu, X., & Shen, C. (2026) · FlexMat. · doi:10.1002/flm2.70080
Flat Inflatable Hydraulic Artificial Muscle (fiHAM) Actuator Based Wearable Robot for Exoskeleton
Harris, A. V., Bi, J., Kurabayashi, K., Wei, R., Tokuda, J., & Li, R. (2026) · International Symposium on Medical Robotics · doi:10.1109/ismr69606.2026.11536400
More isn’t always better: Too much exoskeleton torque can disrupt balancePreprint
Kim, J. G., Rastogi, R., Martino, G., Beck, O. N., Shepherd, M. K., Sawicki, G. S., Ting, L. H., & Jakubowski, K. L. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.02.729541
Self-citationDynamics-Informed Neural Estimation of Human Joint Torques for Lower-Limb Exoskeletons
Yin, B., Zhao, T., Yu, H., Ge, J., Zhang, Y., & Yuan, J. (2026) · International Symposium on Intelligent Robotics and Systems (ISoIRS) · doi:10.1109/isoirs70157.2026.11545223
Yu, M., Dean, J., & Lv, G. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3706926
“Learning-basedapproachesfurtherrelaxkine-maticconstraintsbydirectlyestimatingandcompensatingfor biologicaljointtorques[13],buttypicallyrequirelargedatasets fortraining[14]andmaynotgeneralizewelltocontinuously varyingtasks.”
Zuo, G., Zhang, M., Wu, Q., & Yu, S. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11560368
From body hulls to musculoskeletal models: Personalized inertial parameter estimation
Gambietz, M., Azam, P. Q., Amon, P., Wechsler, I., Hille, E. M., Menzel, T., Ott, T., Botsch, M., Braun, M., Miehling, J., et al. (2026) · PLoS ONE · doi:10.1371/journal.pone.0349886
“The metabolic reduction observed from altering inertial parameters through SIPP of up to 12.8% is relevant, as it is larger than the typical improvements seen with advanced footwear [43] and comparable to the gains achieved with modern exoskeleton assistance [44–46].”
InfluentialGeometry-Informed Magnetic Sensing for Real-Time Control of a Soft Wrist-Assistive Device
Masiero, F., Su, H., Nicchiarelli, G., Mišković, L., Sinibaldi, E., & Masia, L. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3709454
“…intention detection strategies can be broadly categorized as 1) methods based on mechanical events (kinematic or kinetic transduction) [6], [13], [14]; 2) methods based on neuromuscular activity (e.g., electromyography) [15], [16], [17]; and 3) methods based on multimodal sensing and sensor…”
Knee Angle-Based Lower-Limb Locomotion Detection Algorithm With Sensor-Minimal Design
Cho, H. J., Yoon, S. G., Song, J., Han, S.-C., Choi, H. R., & Cho, J. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3717331
“According to Dean D. Molinaro et al., the optimal assistance delay is around 100 ms, suggesting that the system’s delay requires improvement [17].”
Wang, Y., Ding, J., Jing, Z., Han, J., & Zhang, J. (2026) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac71005.2026.11616454
“Current planning methods are primarily divided into two categories: neural network-based open-loop strategies [6]–[8] and closed-loop optimization strategies relying on biological signal feedback [9], [10].”
A State-Scheduled Regional Variable Impedance Control for Lower-Limb Exoskeletons*
Long, Q., Liao, Y., Yi, S., Lu, H., & Guo, Z. (2026) · International Conference on Control and Automation · doi:10.1109/icca69928.2026.11618101
“Impedance-based control has been widely adopted for rehabilitation exoskeletons due to its inherent compliance and robustness in physical human–exoskeleton interaction [8], [9].”
Pană, C. F., Pătrașcu-Pană, D. M., Maican, C. A., & Rădulescu, V. M. (2026) · Actuators · doi:10.3390/act15080431
Fanti, V., Ahmad, J., Refai, M. I. M., Caldwell, D. G., Sartori, M., & Natali, C. D. (2026) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2026.105684
Knee Joint Angle Estimation Based on EMG-FMG Fusion Temporal Convolutional Network
Lu, X., Chen, L., Wang, M., & Guo, S. (2026) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma69663.2026.11647410
“…and leveraging the powerful temporal feature extraction capabilities and bimodal fusion mechanisms of TCN, this research aims to overcome the limitations of single-sensor modalities in dynamic and complex environments, achieving precise and robust prediction of lower-limb joint angles [21] II.”
Will you be wearing an exoskeleton in ten years? The tech that could change how we move
Stokel-Walker, C. (2026) · Nature · doi:10.1038/d41586-026-02527-z
Ding, J., Wang, L., Han, J., & Zhang, J. (2026) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr69988.2026.11642770
“Recent advancements in deep learning, particularly temporal sequence modeling, have further improved the accuracy of mapping inertial signals to complex biomechanical variables [8], [9].”
Personalized Hip Assistance to Improve Gait Performance in Individuals with Parkinson’s DiseasePreprint
Kim, S., Noh, S., Yun, S. J., Hwang, J., Kwon, Y., Lim, B., Lee, Y., Seo, H. G., Kim, K., & Kim, J. (2026) · Research Square · doi:10.21203/rs.3.rs-10612204/v1
A roadmap for end-to-end task-agnostic exoskeleton control
Shepherd, M. K., Schonhaut, E. B., Scherpereel, K. L., Tourk, F. M., & Young, A. J. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-026-01297-7
“With strategically selected tasks that span key dimensions of human movement, as few as 10–15 tasks can support extrapolation to a much broader set of activities 1,33 .”
InfluentialSelf-citationKim, J. H., Rastogi, R., Martino, G., Beck, O. N., Shepherd, M. K., Sawicki, G. S., Ting, L. H., & Jakubowski, K. L. (2026) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2026.113574
“Namely, to minimize metabolic cost, exoskeleton torque at the hip or ankle should be delayed relative to the biological torque by approximately 100 ms (Molinaro et al., 2024; Young et al., 2017).”
Self-citationVersatile Exoskeleton Control Supports Elderly Joint Energetics During Hip-Intensive Tasks
Zhang, J., Divekar, N., Krishnan, C., & Gregg, R. D. (2026) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2026.3732581
“A plausible explanation is the added distal mass from the knee module in [32], which can impose a larger weight (and inertia) penalty during dynamic tasks such as stair ascent [70].”
- Authors
- Molinaro, D. D., Scherpereel, K. L., Schonhaut, E. B., Evangelopoulos, G., Shepherd, M. K., & Young, A. J.
- Affiliations
- Georgia Institute of Technology (US)
- Google (United States) (US)
- Northeastern University (US)
- Corresponding author
- Molinaro, Dean D.
- ORCID
- Venue
- Nature
- Published
- 2024-11-13
- Volume
- 635
- Issue
- 8038
- Pages
- 337-344
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- OpenAlex
- W4404305449
- Cited by
- 107
- References
- 67
- Citations by year
- 2026: 55 · 2025: 51 · 2024: 1
- FWCI
- 11.69
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Nature (publishedVersion)
- PubMed (publishedVersion)
- RePEc: Research Papers in Economics (submittedVersion)
- Topics
- Physical Sciences › Engineering › Biomedical Engineering › Prosthetics and Rehabilitation Robotics
- Physical Sciences › Engineering › Biomedical Engineering › Muscle activation and electromyography studies
- Physical Sciences › Engineering › Biomedical Engineering › Soft Robotics and Applications
- Keywords
- lower limb exoskeleton, deep neural network, metabolic cost reduction, gait assistance, impedance control
- MeSH terms
- Exoskeleton Device, Deep Learning, Adult, Biomechanical Phenomena, Energy Metabolism, Female, Hip Joint, Humans, Knee Joint, Locomotion, Male, Running, Walking, Weight-Bearing, Neural Networks, Computer, Torque, Lower Extremity, Young Adult
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
