Experiment-free exoskeleton assistance via learning in simulation

• 成果类型: Article
• 署名作者: Luo, Shuzhen; Jiang, Menghan; Zhang, Sainan; Zhu, Junxi; Yu, Shuangyue; Silva, Israel Dominguez; Wang, Tian; Rouse, Elliott; Zhou, Bolei; Yuk, Hyunwoo; Zhou, Xianlian; Su, Hao
• 署名单位: North Carolina State University; Embry-Riddle Aeronautical University; University of Michigan System; University of Michigan; University of California System; University of California Los Angeles; Korea Advanced Institute of Science & Technology (KAIST); New Jersey Institute of Technology; North Carolina State University; University of North Carolina; University of North Carolina Chapel Hill; University of North Carolina School of Medicine
• 刊物名称: Nature
• ISSN/ISSBN: 0028-5461
• DOI: 10.1038/s41586-024-07382-4
• 发表日期: 2024-06-13
• 关键词: metabolic cost; muscle-activity; walking; mechanics; incline; DESIGN; robot

摘要

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. A learning-in-simulation framework for wearable robots uses dynamics-aware musculoskeletal and exoskeleton models and data-driven reinforcement learning to bridge the gap between simulation and reality without human experiments to assist versatile activities.