检索结果-南通市图书馆

Science China(Information Sciences) 2020年第1期63卷 241-243页

作者： Huikang WANG luzheng bi Teng TENG School of Mechanical Engineering Beijing Institute of Technology The 3rd Research Institute of China Electronics Technology Group Corporation

Dear editor,Road traffic accidents constitute a problem of serious concern to the society; approximately1.25 million people are killed and tens of millions of people are injured globally every year1). Statistics have shown that almost 95%of motor vehicle accidents are due to driver behavior to some degree [1]. Furthermore, failing to instantly take the

关键词： Neural correlates and detection of braking intention under critical situations based on the power spectra of electroencephalography signals

Brain-Controlled Multi-Robot at Servo-Control Level Based on Nonlinear Model Predictive Control

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Complex System Modeling and Simulation 2022年第4期2卷 307-321页

作者： Zhenge Yang luzheng bi Weiming Chi Haonan Shi Cuntai Guan the School of Mechanical Engineering Beijing Institute of TechnologyBeijing 100081China. the School of Computer Science and Engineering Nanyang Technological UniversitySingapore 639673Singapore

Using a brain-computer interface(BCI)rather than limbs to control multiple robots(i.e.,brain-controlled multi-robots)can better assist people with disabilities in daily life than a brain-controlled single *** example,one person with disabilities can move by a brain-controlled wheelchair(leader robot)and simultaneously transport objects by follower *** this paper,we explore how to control the direction,speed,and formation of a brain-controlled multi-robot system(consisting of leader and follower robots)for the first time and propose a novel multi-robot predictive control framework(MRPCF)that can track users'control intents and ensure the safety of multiple *** MRPCF consists of the leader controller,follower controller,and formation *** build a whole brain-controlled multi-robot physical system for the first time and test the proposed system through human-in-the-loop actual *** experimental results indicate that the proposed system can track users'direction,speed,and formation control intents when guaranteeing multiple robots’*** paper can promote the study of brain-controlled robots and multi-robot systems and provide some novel views into human-machine collaboration and integration.

关键词： brain-computer interface human-machine collaboration model predictive control multi-robot system

Fuzzy-Based Shared Control for Brain-controlled Mobile Robot

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fuzzy-Based Shared Control for Brain-controlled Mobile Robot

第三十九届中国控制会议

作者： Razzaq Zahid luzheng bi IEEE the School of Mechanical Engineering Beijing Institute of Technology

Brain-Computer Interface（BCI） is a powerful communication tool between users and systems. It allows users, disabled by neuromuscular disorders such as amyotrophic lateral sclerosis, cerebral palsy, stroke, or spinal cord injury, to communicate with or control external devices using brain signals. However, due to limitations of BCIs, brain-controlled mobile robots have confined control performance and poor safety. To address this problem, this paper proposes a shared control method based on fuzzy logic control strategy. Particularly, to blend the tracking user intention and guaranteeing safety of brain-controlled mobile robots into an optimization problem, assistive controller based on fuzzy logic control is designed by using PID gains and fine tuning these gains of fuzzy controller by the trial-and-error method. The experimental results demonstrate the effectiveness of the proposed method in avoiding obstacles while maintaining the control authority of users.

关键词：

Using Noninvasive Neural Signal to Recognize Single-and Multi-task States of Operators

在线全文

cnki会议

学校读者我要写书评

暂无评论

Using Noninvasive Neural Signal to Recognize Single-and Mult...

第三十九届中国控制会议

作者： Shengchao Xia luzheng bi Xiaoguang Wang School of Mechanical Engineering Beijing Institute of Technology

In this paper, we propose an electroencephalogram（EEG） signals-based method to recognize single-and multi-task states of users by using the linear discriminant analysis（LDA） algorithm and convolutional neural network（CNN）. A novel experimental paradigm is designed to validate the proposed method. Experimental results from eight subjects show that the proposed methods perform well. Furthermore, the average accuracy of the recognition model based on CNN reaches 89.13% and is 5% higher than that based on the LDA algorithm. This work not only lays a foundation for the development of adaptive assistant systems based on brain-computer interfaces, but it also advances the study of human state monitoring and human-machine interaction based on EEG signals.

关键词： Electroencephalogram(EEG) signals assistive control brain-computer interface(BCI) single-and multi-task states convolutional neural network(CNN)

Parallel Tracker for Visual Object Tracking

在线全文

cnki会议

学校读者我要写书评

暂无评论

Parallel Tracker for Visual Object Tracking

第30届中国控制与决策会议

作者： Xiangluan Liang Ru Lai luzheng bi School of Automation Beijing Institute of Technology School of Mechanical Engineering Beijing Institute of Technology

In this paper, we present a novel tracker for real-time single object tracking by combining Kernelized Correlation Filter（KCF） and Distractor Aware Tracker（DAT）. KCF is capable of distinguishing object from background effficiently while DAT is robust for object’s appearance and similar distracting reigons. First, we propose a seriesparallel connection structure to make full use of the two trackers’ s complementary advantages, which aims to locate the object position more accurately. Second, we add a revised scale filter to adapt the scale change. Experiments on OTB-100 demonstrate that our approach is better than both two sub-trackers and can run in real-time.

关键词： Object Tracking Correlation Filter Distroctor Aware Scale Filter

Edge-guided Adversarial Network Based on Contrastive Learning for Image-to-Image Translation

在线全文

cnki会议

学校读者我要写书评

暂无评论

Edge-guided Adversarial Network Based on Contrastive Learnin...

第40届中国控制会议

作者： Chen Zhu Ru Lai luzheng bi Xuyang Wang Jiarong Du School of Automation Beijing Institute of Technology School of Mechnical Engineering Beijing Institute of Technology

In recent years, generative adversarial networks have made great progress in image synthesis and image translation tasks in the field of image processing and computer vision. However, the quality of the generated image and the scalability over multiple datasets is still not satisfying. We briefly review some prior works and propose a method for image-to-image translation,which is learning a mapping between different visual domains. The network extracts edge feature from both domains of output and target, and minimizes the difference using a framework based on patchwise contrastive learning. We apply edge feature guidance in our method and select Sobel operator among several classical edge detection operators. We demonstrate that our method outperforms existing approaches in the task of unpaired image-to-image translation across datasets.

关键词： Generative adversarial network Image-to-Image translation Contrastive learning Edge detection

在线全文

cnki会议

学校读者我要写书评

暂无评论

基于认知任务的脑机接口方法研究

计算机工程 2007年第1期33卷 190-192页

作者：毕路拯张然高原吴平东北京理工大学机械与车辆工程学院北京100081 北京理工大学生命与技术学院北京100081 北京理工大学信息科学技术学院北京100081

提出一种通过脑电波来识别放松状态以及乘法作业状态从而实现脑机接口的新方法。利用脑电仪记录受测者放松状态以及乘法作业时的大脑左右半球枕叶部的脑电信号,采用Welch法分别估计出这2个部位8Hz～10Hz、1Hz～13Hz、14Hz～30Hz 3个频... 详细信息

提出一种通过脑电波来识别放松状态以及乘法作业状态从而实现脑机接口的新方法。利用脑电仪记录受测者放松状态以及乘法作业时的大脑左右半球枕叶部的脑电信号,采用Welch法分别估计出这2个部位8Hz～10Hz、1Hz～13Hz、14Hz～30Hz 3个频段的功率谱,以各个功率谱平均值和2Hz～30Hz频段功率谱平均值的比值作为分类特征,采用支持向量机的方法建立了分类器,从而实现了脑机接口。4个受测者的实验结果表明识别准确率都大于94.44%,最高为98.89%。由于只采用了2个采集点,因此如果采用某种编码方式,该脑机接口技术就可更加方便地用于写字、控制轮椅等方面。

关键词：支持向量机脑机接口功率谱认知任务

在线全文

学校读者我要写书评

暂无评论

G-P算法在脑学习机能研究中的应用

计算机应用与软件 2007年第11期24卷 28-29,63页

作者：陈冬冰吴平东毕路拯韩巍北京理工大学机械与车辆工程学院北京100081

运用非线性动力学理论,分析大脑信息处理运动的过程。由混沌动力学吸引子关联维数的物理意义出发,论证了关联维数值与神经元群电发放之间的关系。采用连续加算作业法,同步采集EEG信号,应用分形论中的G-P算法,获取EEG信号的关联维数。实... 详细信息

运用非线性动力学理论,分析大脑信息处理运动的过程。由混沌动力学吸引子关联维数的物理意义出发,论证了关联维数值与神经元群电发放之间的关系。采用连续加算作业法,同步采集EEG信号,应用分形论中的G-P算法,获取EEG信号的关联维数。实验结果表明:连续加算作业法的下半时EEG信号的关联维数明显小于上半时EEG信号的关联维数。因此,基于G-P算法的关联维数可以作为脑学习机能的评价指数。

关键词：混沌 G—P算法脑电关联维数神经元群

在线全文

学校读者我要写书评

暂无评论

闪光视觉诱发电位在脑机接口中的应用研究

计算机应用与软件 2009年第11期26卷 13-16页

作者：黄漫玲吴平东毕路拯刘莹北京理工大学机械与车辆工程学院北京100081 北京政法职业学院北京100024

运用叠加平均与快速傅立叶变化相结合的方法,提取大脑皮层的稳态视觉诱发电位SSVEP(steady state visual evoked po-tential)信号,并作为输入信号应用于脑控机器人系统。通过实验确定了测试电极、视觉刺激颜色与背景亮度等模式参数,并... 详细信息

运用叠加平均与快速傅立叶变化相结合的方法,提取大脑皮层的稳态视觉诱发电位SSVEP(steady state visual evoked po-tential)信号,并作为输入信号应用于脑控机器人系统。通过实验确定了测试电极、视觉刺激颜色与背景亮度等模式参数,并且研究了不同使用者在不同视觉刺激频率下的SSVEP幅值变化趋势。研究结果表明,该方法能更好地提高信噪比,提取出的稳态视觉诱发电位信号能够准确反映使用者的控制意图,应用于脑控机器人系统,取得了很好的效果。

关键词：稳态视觉诱发电位脑机接口脑电

在线全文

学校读者我要写书评

暂无评论

EEG非线性特征参数的研究

北京生物医学工程 2006年第6期25卷 611-614页

作者：陈冬冰吴平东毕路拯韩巍王刚刘莹北京理工大学机械与车辆工程学院北京100081 北京理工大学管理与经济学院北京100081

脑电图(EEG)记录了神经元群的电活动,为脑信息处理特征的研究提供重要的信息。基于相空间重构思想的时间序列分维算法(G-P算法)提取EEG信号的特征参数,讨论了G-P算法的三个重要参数,即无标度域、嵌入维数和延时的确定规则,记录大脑在不... 详细信息

脑电图(EEG)记录了神经元群的电活动,为脑信息处理特征的研究提供重要的信息。基于相空间重构思想的时间序列分维算法(G-P算法)提取EEG信号的特征参数,讨论了G-P算法的三个重要参数,即无标度域、嵌入维数和延时的确定规则,记录大脑在不同状态下的EEG信号并计算其关联维数。实验结果表明,EEG关联维数可以有效地区分大脑不同状态的特征,关联维数可以作为脑信息处理的非线性特征参数。

关键词：脑信息处理脑电图关联维数奇异谱神经元群