Motion Learning and Rapid Generalization for Musculoskeletal Systems Based on Recurrent Neural Network Modulated by Initial States

doi:10.1109/TCDS.2021.3136854

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

	Motion Learning and Rapid Generalization for Musculoskeletal Systems Based on Recurrent Neural Network Modulated by Initial States
	Wang, Xiaona1,2,3 ; Chen, Jiahao1,2,3 ; Qiao, Hong1,2,3,4
发表期刊	IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS
ISSN	2379-8920
	2022-12-01
卷号	14 期号:4 页码:1691-1704
通讯作者	Qiao, Hong(hong.qiao@ia.ac.cn)
摘要	Musculoskeletal robot with high precision and robustness is a promising direction for the next generation of robots. However, motion learning and rapid generalization of complex musculoskeletal systems are still challenging. Therefore, inspired by the movement preparation mechanism of the motor cortex, this article proposes a motion learning framework based on the recurrent neural network (RNN) modulated by initial states. First, two RNNs are introduced as a preparation network and an execution network to generate initial states of the execution network and time-varying motor commands of movement, respectively. The preparation network is trained by a reward-modulated learning rule, and the execution network is fixed. With the modulation of initial states, initial states can be explicitly expressed as knowledge of movements. By dividing the preparation and execution of movements into two RNNs, the motion learning is accelerated to converge under the application of the node-perturbation method. Second, with the utilization of learned initial states, a rapid generalization method for new movement targets is proposed. Initial states of unlearned movements can be computed by searching for low-dimensional ones in latent space constructed by learned initial states and then transforming them into the whole neural space. The proposed framework is verified in simulation with a musculoskeletal model. The results indicate that the proposed motion learning framework can realize goal-oriented movements of the musculoskeletal system with high precision and significantly improve the generalization efficiency for new movements.
关键词	Muscles Recurrent neural networks Mathematical models Bio-inspired control Robot kinematics Tendons Musculoskeletal system Biologically inspired control motor cortex movement preparation musculoskeletal system recurrent neural network (RNN)
DOI	10.1109/TCDS.2021.3136854
关键词[WOS]	MOVEMENT ; DYNAMICS ; NEUROSCIENCE ; SIMULATION ; MODEL
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFB1300203] ; National Natural Science Foundation of China[91648205] ; National Natural Science Foundation of China[61627808] ; National Natural Science Foundation of China[91948303] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050100]
项目资助者	National Key Research and Development Program of China ; National Natural Science Foundation of China ; Strategic Priority Research Program of Chinese Academy of Science
WOS研究方向	Computer Science ; Robotics ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Robotics ; Neurosciences
WOS记录号	WOS:000916821100033
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/51345
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.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing Key Lab Res & Applicat Robot Intelligence, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China
第一作者单位	中国科学院自动化研究所
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	Wang, Xiaona,Chen, Jiahao,Qiao, Hong. Motion Learning and Rapid Generalization for Musculoskeletal Systems Based on Recurrent Neural Network Modulated by Initial States[J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,2022,14(4):1691-1704.
APA	Wang, Xiaona,Chen, Jiahao,&Qiao, Hong.(2022).Motion Learning and Rapid Generalization for Musculoskeletal Systems Based on Recurrent Neural Network Modulated by Initial States.IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS,14(4),1691-1704.
MLA	Wang, Xiaona,et al."Motion Learning and Rapid Generalization for Musculoskeletal Systems Based on Recurrent Neural Network Modulated by Initial States".IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS 14.4(2022):1691-1704.