Experiment-free exoskeleton assistance via learning in simulation.

Autor: Luo S; Lab of Biomechatronics and Intelligent Robotics, Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USA.; Department of Mechanical Engineering, Embry-Riddle Aeronautical University, Daytona Beach, FL, USA., Jiang M; Lab of Biomechatronics and Intelligent Robotics, Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USA., Zhang S; Lab of Biomechatronics and Intelligent Robotics, Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USA., Zhu J; Lab of Biomechatronics and Intelligent Robotics, Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USA., Yu S; Lab of Biomechatronics and Intelligent Robotics, Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USA., Dominguez Silva I; Lab of Biomechatronics and Intelligent Robotics, Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USA., Wang T; Lab of Biomechatronics and Intelligent Robotics, Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USA., Rouse E; Neurobionics Lab, Department of Robotics, Department of Mechanical Engineering, University of Michigan, Ann Arbor, MI, USA., Zhou B; Department of Computer Science, University of California, Los Angeles, CA, USA., Yuk H; Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea., Zhou X; Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ, USA., Su H; Lab of Biomechatronics and Intelligent Robotics, Department of Mechanical and Aerospace Engineering, North Carolina State University, Raleigh, NC, USA. hao.su796@ncsu.edu.; Joint NCSU/UNC Department of Biomedical Engineering, North Carolina State University, Raleigh, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA. hao.su796@ncsu.edu.
Jazyk: angličtina
Zdroj: Nature [Nature] 2024 Jun; Vol. 630 (8016), pp. 353-359. Date of Electronic Publication: 2024 Jun 12.
DOI: 10.1038/s41586-024-07382-4
Abstrakt: Exoskeletons have enormous potential to improve human locomotive performance 1-3 . However, their development and broad dissemination are limited by the requirement for lengthy human tests and handcrafted control laws 2 . 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.
(© 2024. The Author(s), under exclusive licence to Springer Nature Limited.)
Databáze: MEDLINE
Externí odkaz: