Generalizable and precise control based on equilibrium-point hypothesis for musculoskeletal robotic system

doi:10.1108/RIA-01-2024-0022

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Generalizable and precise control based on equilibrium-point hypothesis for musculoskeletal robotic system
	Wu, Yaxiong 1; Chen, Jiahao2 ; Qiao, Hong2,3
发表期刊	ROBOTIC INTELLIGENCE AND AUTOMATION
ISSN	2754-6969
	2024-06-11
页码	9
通讯作者	Qiao, Hong(hong.qiao@ia.ac.cn)
摘要	PurposeThe purpose of this study is realizing human-like motions and performance through musculoskeletal robots and brain-inspired controllers. Human-inspired robotic systems, owing to their potential advantages in terms of flexibility, robustness and generality, have been widely recognized as a promising direction of next-generation robots.Design/methodology/approachIn this paper, a deep forward neural network (DFNN) controller was proposed inspired by the neural mechanisms of equilibrium-point hypothesis (EPH) and musculoskeletal dynamics.FindingsFirst, the neural mechanism of EPH in human was analyzed, providing the basis for the control scheme of the proposed method. Second, the effectiveness of proposed method was verified by demonstrating that equilibrium states can be reached under the constant activation signals. Finally, the performance was quantified according to the experimental results.Originality/valueBased on the neural mechanism of EPH, a DFNN was crafted to simulate the process of activation signal generation in human motion control. Subsequently, a bio-inspired musculoskeletal robotic system was designed, and the high-precision target-reaching tasks were realized in human manner. The proposed methods provide a direction to realize the human-like motion in musculoskeletal robots.
关键词	Musculoskeletal system Humanoid motion control Equilibrium-point hypothesis Muscle model
DOI	10.1108/RIA-01-2024-0022
关键词[WOS]	CROSS-BRIDGE MODEL ; DYNAMIC SIMULATIONS ; REACHING MOVEMENTS ; MUSCLE ; FORCE ; ARM ; CONTRACTION ; PARAMETERS ; SYNERGIES ; HEAT
收录类别	SCI
语种	英语
资助项目	Major Project of Science and Technology Innovation[2030-Brain] ; Major Project of Science and Technology Innovation[2021ZD0200408] ; National Natural Science Foundation of China (NSFC)[91948303] ; National Natural Science Foundation of China (NSFC)[62203439] ; National Natural Science Foundation of China (NSFC)[62203443]
项目资助者	Major Project of Science and Technology Innovation ; National Natural Science Foundation of China (NSFC)
WOS研究方向	Automation & Control Systems ; Engineering
WOS类目	Automation & Control Systems ; Engineering, Manufacturing
WOS记录号	WOS:001240943400001
出版者	EMERALD GROUP PUBLISHING LTD
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58686
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
通讯作者	Qiao, Hong
作者单位	1.Univ Sci & Technol Beijing, Sch Mech Engn, Beijing, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wu, Yaxiong,Chen, Jiahao,Qiao, Hong. Generalizable and precise control based on equilibrium-point hypothesis for musculoskeletal robotic system[J]. ROBOTIC INTELLIGENCE AND AUTOMATION,2024:9.
APA	Wu, Yaxiong,Chen, Jiahao,&Qiao, Hong.(2024).Generalizable and precise control based on equilibrium-point hypothesis for musculoskeletal robotic system.ROBOTIC INTELLIGENCE AND AUTOMATION,9.
MLA	Wu, Yaxiong,et al."Generalizable and precise control based on equilibrium-point hypothesis for musculoskeletal robotic system".ROBOTIC INTELLIGENCE AND AUTOMATION (2024):9.