Experiment-free exoskeleton assistance via learning in simulation

Shuzhen Luo, Menghan Jiang, Sainan Zhang, Junxi Zhu, Shuangyue Yu, Israel Dominguez Silva, Tian Wang, Elliott Rouse, Bolei Zhou, Hyunwoo Yuk, Xianlian Zhou and Hao Su ()
Additional contact information
Shuzhen Luo: North Carolina State University
Menghan Jiang: North Carolina State University
Sainan Zhang: North Carolina State University
Junxi Zhu: North Carolina State University
Shuangyue Yu: North Carolina State University
Israel Dominguez Silva: North Carolina State University
Tian Wang: North Carolina State University
Elliott Rouse: University of Michigan
Bolei Zhou: University of California
Hyunwoo Yuk: Korea Advanced Institute of Science and Technology
Xianlian Zhou: New Jersey Institute of Technology
Hao Su: North Carolina State University

Nature, 2024, vol. 630, issue 8016, 353-359

Abstract: Abstract Exoskeletons have enormous potential to improve human locomotive performance1–3. However, their development and broad dissemination are limited by the requirement for lengthy human tests and handcrafted control laws2. Here we show an experiment-free method to learn a versatile control policy in simulation. Our learning-in-simulation framework leverages dynamics-aware musculoskeletal and exoskeleton models and data-driven reinforcement learning to bridge the gap between simulation and reality without human experiments. The learned controller is deployed on a custom hip exoskeleton that automatically generates assistance across different activities with reduced metabolic rates by 24.3%, 13.1% and 15.4% for walking, running and stair climbing, respectively. Our framework may offer a generalizable and scalable strategy for the rapid development and widespread adoption of a variety of assistive robots for both able-bodied and mobility-impaired individuals.

Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41586-024-07382-4 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:630:y:2024:i:8016:d:10.1038_s41586-024-07382-4

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-024-07382-4

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().