首页 | 本学科首页   官方微博 | 高级检索  
     

基于Actor-Critic和神经网络的闭环脑机接口控制器设计
引用本文:孙京诰,杨嘉雄,王硕,薛瑞,潘红光.基于Actor-Critic和神经网络的闭环脑机接口控制器设计[J].控制与决策,2018,33(11):1967-1974.
作者姓名:孙京诰  杨嘉雄  王硕  薛瑞  潘红光
作者单位:华东理工大学信息科学与工程学院,上海200237,华东理工大学信息科学与工程学院,上海200237,华东理工大学信息科学与工程学院,上海200237,华东理工大学信息科学与工程学院,上海200237,西安科技大学电气与控制工程学院,西安710054
基金项目:国家自然科学基金项目(61603295).
摘    要:在皮层神经元放电活动模型的基础上进行单关节自发运动的研究,从控制理论的角度分析闭环脑机接口的工作原理.使用卡尔曼滤波器和人工神经网络设计系统的解码器替代原系统的脊髓电流,并且比较这两种解码器的优劣.由于在无感知反馈的信号下,解码器的性能下降得比较明显,使用强化学习中Actor-Critic算法结合人工神经网络设计PID控制器,用以产生刺激信号来刺激大脑皮层神经元,使其能够跟踪有感知反馈信号时皮层神经元的放电活动,从而恢复解码器的性能.最后,通过与其他控制算法对比,验证了基于强化学习算法的人工感知反馈信号设计的有效性.

关 键 词:大脑皮层放电模型  神经网络  解码器  强化学习  控制器设计

Design of closed-loop brain machine interface controller based on Actor-Critic and neural network
SUN Jing-gao,YANG Jia-xiong,WANG Shuo,XUE Rui and PAN Hong-guang.Design of closed-loop brain machine interface controller based on Actor-Critic and neural network[J].Control and Decision,2018,33(11):1967-1974.
Authors:SUN Jing-gao  YANG Jia-xiong  WANG Shuo  XUE Rui and PAN Hong-guang
Affiliation:College of Information Science and Engineering,East China University of Science and Technology,Shanghai200237,China,College of Information Science and Engineering,East China University of Science and Technology,Shanghai200237,China,College of Information Science and Engineering,East China University of Science and Technology,Shanghai200237,China,College of Information Science and Engineering,East China University of Science and Technology,Shanghai200237,China and College of Electrical and Control Engineering, Xián University of Science and Technology,Xián710054,China
Abstract:In this paper, the spontaneous motion of the single joint is studied on the basis of the cortical neuron firing activity model, and the working principle of the closed-loop brain machine interface is analyzed from the perspective of the control theory. The Kalman filter and artificial neural network are used to design system decoders to replace the original system of spinal cord current, then the advantages and disadvantages of these two decoders are compared. Due to the dramatically decrease of the decoder in the absence of natural proprioception, the reinforcement learning algorithm(Actor-Critic) combined with the artificial neural network is used to design the PID controller, which can generate the stimulus signal to stimulate the neurons of the cerebral cortex, track cortical neuron firing activity with the natural proprioception and restore the performance of the decoder. Finally, the validity of the artificial sensing feedback signal design based on the reinforcement learning algorithm is verified by comparing with other control algorithms.
Keywords:
点击此处可从《控制与决策》浏览原始摘要信息
点击此处可从《控制与决策》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号