The DOI matches its Crossref record; 68 of the 68 references it cites were found in a registry or an index.
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Biomechanics and Motor Control of Human Movement
Winter, D. A. (2009) · Wiley eBooks · doi:10.1002/9780470549148 · Cited by 6,112
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
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
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
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
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 967
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
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
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
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
Cited by
Sorted by citations
Items 101–107 of 107
Dobosz, T., Lubitz, S., Ziegenspeck, N., Maufroy, C., Gizzi, L., Schneider, U., & Bauernhansl, T. (2026) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob66782.2026.11681770
“This is within the range reported for joint load estimation in the literature [13], [17].”
Lightweight Unilateral Knee Exoskeleton with IMU-Based Activity-Adaptive Torque Estimation
Hao, J., Zuo, G., & Yu, S. (2026) · IEEE/ASME International Conference on Mechatronic and Embedded Systems and Applications · doi:10.1109/mesa70578.2026.11684272
“To satisfy the practical requirements of portable exoskeletons, the estimation method should also reduce dependence on complex sensors and external computing platforms [8].”
Fast Personalization of Real-Time Human Activity Recognition via Transfer Learning
You, Z., Yuan, Y., Tohfafarosh, M., & Zhou, X. (2026) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob66782.2026.11681440
“This study utilized a dataset from Georgia Tech [16] to train SI models.”
Continual Reinforcement Learning for Walking Control in a Musculoskeletal Simulation of Hemiparesis
Jones, S. T., Young, W. M. J., Uhlrich, S. D., Pilarski, P. M., & Dalrymple, A. N. (2026) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob66782.2026.11681004
“While many controllers are under development for assistive devices [6]–[9], extensively testing new controllers is challenging, limiting their ability to be translated into commercial or clinical use.”
Learning Device-Agnostic Control Policy for Hip Exoskeletons via Sim-to-real Reinforcement Learning
Hou, Z., Hou, J., Ma, T., & Tang, S. (2026) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber71431.2026.11695464
“Learning-based methods, such as reinforcement learning (RL) [2] and supervised learning [3], have shown great potential for developing flexible and adaptive control strategies.”
Nichols, C. J., Nicholas, H., Crane, H. T., Routt, A., Haile, M., Goossens, Q., Shinohara, M., Sawicki, G. S., Jakubowski, K. L., & Inan, O. T. (2026) · Science Robotics · doi:10.1126/scirobotics.aea4580
Fan, X., Ma, T., Yu, N., Han, J., Guan, J., Ni, M., & Sun, T. (2026) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2026.1938657
Metadata
- 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
