文献类型：期刊文献

中文题名：基于Actor-Critic和神经网络的闭环脑机接口控制器设计

英文题名：Design of closed-loop brain machine interface controller based on Actor-Critic and neural network

作者：孙京诰[1];杨嘉雄[1];王硕[1];薛瑞[1];潘红光[2]

机构：[1]华东理工大学信息科学与工程学院,上海200237;[2]西安科技大学电气与控制工程学院,西安710054

年份：2018

卷号：33

期号：11

起止页码：1967

中文期刊名：控制与决策

外文期刊名：Control and Decision

收录：CSTPCD;;EI(收录号：20190906552522);Scopus;北大核心:【北大核心2017】；CSCD:【CSCD2017_2018】；

基金：国家自然科学基金项目(61603295)

语种：中文

中文关键词：大脑皮层放电模型;神经网络;解码器;强化学习;控制器设计

外文关键词：brain cortical neuron firing model;neural network;decoder;reinforcement learning;controller design

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.
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.