检索结果-内蒙古大学图书馆

第41届中国控制会议

作者： Junlin Zhang Kaoru Hirota Yaping Dai Sijie Yin School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The inter-class similarity of facial expressions is one of the key challenges in Facial Expression Recognition(FER).In this manuscript,a Latent Facial Action Units Network(LAUNet) is proposed for the problem of inter-class similarity of facial expressions in *** proposed method recognizes subtle differences between facial expressions by learning Latent Facial Action Units Features(LAUFs).Specifically,LAUNet is composed of two parts:the Latent Facial Action Units Features Extraction Network(LEN) and the Latent Facial Action Units Selection Network(LSN).Firstly,LEN extracts LAUFs from the feature map of the backbone using the spatial attention ***,taking advantage of the channel attention mechanism,LSN captures the latent relationships between features from LAUFs to select effective features for *** are performed on the dataset after removing the invalid data of non-face images from the original FER2013 *** with some previous state-of-the-art methods,LAUNet achieves the highest accuracy rate of 71.31%.Depending on the backbone,LAUNet can improve the accuracy by up to 5.46% compared to the original architecture of the backbone.

关键词： Facial Expression Recognition Attention Mechanism Computer Vision

来源：评论

学校读者我要写书评

暂无评论

Energy Consumption Analysis in Multi-legged Robots Based on Gait Planning 35

Energy Consumption Analysis in Multi-legged Robots Based on ...

引用

第35届中国控制会议

作者： DU Xiaolong WANG Shoukun ZONG Xiaoyan WANG Junzheng State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology

ISBN: (纸本)9781509009107

Currently,the multi-legged robots have to confront the problem of low energy utilization that restricts the moving radius of *** at the problem of energy consumption for mobile robots,this paper provides the analysis in terms of the gait ***,two kinds of gait curves respectively,cycloid curve and Bezier curve are introduced and the main difference of two gait patterns is that the Bezier curve can achieve the swing leg retraction(SLR).The length of step(S),the height of step(H) and the duty ratio of gait cycle(P) are set as the primary research points about the gait of mobile *** this work,we formulate two indexes to quantitatively describe the performance of the quadruped robot and related simulations are carried out for gait ***,the results provide some recommendations for the gait planning of the quadruped robot,that is,the changes of gait parameters influence the index of energy consumption and SLR can effectively reduce energy consumption.

关键词： Energy consumption Multi-legged robot Gait planning SLR Gait parameters

来源：评论

学校读者我要写书评

暂无评论

Distributed observer-based coordination for multiple Lagrangian systems using only position measurements

引用

IET control Theory and Applications 2014年第17期8卷 2102-2114页

作者： Yang, Qingkai Fang, Hao Chen, Jie Wang, Xueyuan School of Automation Beijing Institute of Technology Beijing100081 China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing100081 China

This study addresses the distributed coordination problem for multiple Lagrangian systems under a directed graph. Two cases are considered, namely, the distributed tracking control problem with a dynamic leader and the leaderless synchronisation problem. To overcome the difficulty that only positions are measured, a kind of new distributed observer is designed to estimate the velocity for each follower. The velocity observer is updated using only position information from the agent itself and from its neighbours. Based on the outputs of the observer, the distributed control protocols are proposed, respectively, such that the tracking errors locally exponentially converge to zero in the tracking scenario and the agents synchronise in the leaderless synchronisation scenario. Furthermore, the stability of the overall scheme is discussed under the directed interaction graphs that contain a directed spanning tree. Finally, cooperative simulations are provided to show the effectiveness of the proposed observer and control algorithms. © 2014 The Institution of Engineering and Technology.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Approach and landing guidance design for reusable launch vehicle using multiple sliding surfaces technique

引用

Chinese Journal of Aeronautics 2017年第4期30卷 1582-1591页

作者： Xiangdong LIU Fengdi ZHANG Zhen LI Yao ZHAO School of Automation Beijing Institute of Technology Beijing 100081 China National Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing100081 China China Academy of Launch Vehicle Technology Beijing 100076 China

An autonomous approach and landing（A＆L） guidance law is presented in this paper for landing an unpowered reusable launch vehicle（RLV） at the designated runway touchdown. Considering the full nonlinear point-mass dynamics, a guidance scheme is developed in threedimensional space. In order to guarantee a successful A＆L movement, the multiple sliding surfaces guidance（MSSG） technique is applied to derive the closed-loop guidance law, which stems from higher order sliding mode control theory and has advantage in the finite time reaching *** global stability of the proposed guidance approach is proved by the Lyapunov-based *** designed guidance law can generate new trajectories on-line without any specific requirement on off-line analysis except for the information on the boundary conditions of the A＆L phase and instantaneous states of the RLV. Therefore, the designed guidance law is flexible enough to target different touchdown points on the runway and is capable of dealing with large initial condition errors resulted from the previous flight phase. Finally, simulation results show the effectiveness of the proposed guidance law in different scenarios.

关键词： Finite time control Landing guidance Lyapunov stability Reusable launch vehicle Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Improved Model-Predictive Current control of Permanent Magnet Synchronous Motor Drives with Designed Cost Function 41

Improved Model-Predictive Current Control of Permanent Magne...

引用

第41届中国控制会议

作者： Yi Yang Wei Shen Dan Li Luwei Shao State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Model predictive current control(MPCC) is widely applied in electrical drives and power electronics because of its simplicity and ***,steady-state errors are always present because of the inaccurate prediction induced by changing actual *** paper proposes a simple strategy for improving MPCC performance,which reduces steadystate errors and eliminates the additional prediction *** cost function,which is made up of tracking mistakes,is used in MPCC to choose the best switching *** paper introduces a new cost function that also includes actual current *** is a coefficient of actual current errors that enhances the appropriateness of permanent magnet synchronous motor(PMSM) *** results show superior performance of the proposed MPCC to that of conventional MPCC.

关键词： PMSM MPCC Cost function Current errors

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Nonlinear Model Predictive control with Bounded Disturbances and State-dependent Uncertainties

引用

IFAC-PapersOnLine 2017年第1期50卷 9308-9314页

作者： Wang M. Sun J. Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing 100081 China

In this paper, two event-triggered nonlinear model predictive control(NMPC) strategies based on Lyapunov function method for discrete-time nonlinear systems with bounded disturbances and state-dependent uncertainties are proposed. The corresponding event-triggered control law is designed and the feasibility is analyzed. Stability of the event-triggered NMPC systems is studied and sufficient stability conditions are obtained. Finally, simulation results show advantages of the two event-triggered strategies on performance and computational burden. © 2017

关键词： event-triggered control,nonlinear model predictive control, Lyapunov function

来源：评论

学校读者我要写书评

暂无评论

The Energy Consumption Analysis of Hydraulic Quadruped Robot based on Gait Parameters 34

The Energy Consumption Analysis of Hydraulic Quadruped Robot...

引用

第三十四届中国控制会议

作者： ZONG Xiaoyan Wang Shoukun Wang Junzheng Chen Guangrong Zhang Xiaoling State Key Laboratory of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology

ISBN: (纸本)9781467374439

The optimization of the energy consumption is one of the most important problems that face the designers of mobile robots. This implies that it is significant to analyze the energy consumption of hydraulic quadruped robot under different gait parameters. In this paper, the kinematics and dynamics models of a hydraulic quadruped robot are established firstly. Then, the length of step, the height of step, the height of center of mass, and the duty ratio of gait cycle are set as the primary research points about the energy consumption of mobile robot. In addition, the energy consumptions of the feet with and without mechanical springs are compared and analyzed. In order to get the visual observation of energy cost in the hydraulic quadruped robot during a waking cycle and the best set of locomotion variables that achieve the energy optimization, related simulations are done for gait parameters. Finally, the results provide a recommendation for the gait planning of the hydraulic quadruped robot, that is, the quadruped robot should walk with a relatively long step length, a relatively low height of step, a relatively high height of center of mass, and a relatively small duty ratio of gait cycle.

关键词： Hydraulic quadruped robot Kinematics Dynamics Gait parameters Energy consumption

来源：评论

学校读者我要写书评

暂无评论

A survey on the security of cyber-physical systems

引用

control Theory and Technology 2016年第1期14卷 2-10页

作者： Guangyu WU Jian SUN Jie CHEN School of Automation Beijing Institute of Technology Beijing 100081 China Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing 100081 China

Cyber-physical systems （CPSs） are integrations of computation, communication, control and physical processes. Typical examples where CPSs are deployed include smart grids, civil infrastructure, medical devices and manufacturing. Security is one of the most important issues that should be investigated in CPSs and hence has received much attention in recent years. This paper surveys recent results in this area and mainly focusses on three important categories： attack detection, attack design and secure estimation and control. We also discuss several future research directions including risk assessment, modeling of attacks and attacks design, counter-attack strategy and testbed and validation.

关键词： Security cyber-physical systems attack detection secure estimation and control

来源：评论

学校读者我要写书评

暂无评论

A Multimodal Emotion Perception Model based on Context-Aware decision-Level Fusion 41

A Multimodal Emotion Perception Model based on Context-Aware...

引用

第41届中国控制会议

作者： Yishan Chen Zhiyang Jia Kaoru Hirota Yaping Dai School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

A Multimodal Emotion Perception model with Audio and Visual modalities(MEP-AV) is proposed to detect the individual emotions in public *** framework of MEP-AV model consists of four parts,i.e.,data collection module,audio expression analysis module,visual expression analysis module and multimodal fusion *** order to ensure that the emotion perception results meet the requirement of short-term continuity,a Context-Aware decision-Level Fusion(CADLF) model is proposed and applied in multimodal fusion *** CADLF model estimates the affective status by using context information of multimodal *** short-term continuity is considered to improve the accuracy of the emotion perception *** experiment results evaluated by various metrics demonstrate that the performance of the multimodal structure is improved compared with that of unimodal emotion *** MEP-AV model using multimodal fusion algorithm provides the accuracies of70.89% and 77.07% in valence and arousal *** F1-scores reaches 70.2% and 75.6% respectively,indicating the boost performance on emotion perception.

关键词： Emotion Perception decision-level Fusion Context-aware

来源：评论

学校读者我要写书评

暂无评论

An Adversarial Video Moment Retrieval Algorithm 41

An Adversarial Video Moment Retrieval Algorithm

引用

第41届中国控制会议

作者： Mohan Jia Zhongjian Dai Yaping Dai Zhiyang Jia School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

In one-stage methods for video moment retrieval,the common representations indirectly supervised by boundary prediction fail to fully preserve the inherent characteristic of the video and query,which limits the retrieval *** solve this problem,an Adversarial Video Moment Retrieval(AVMR) algorithm is proposed to learn the common representations with modality invariance and cross-modal *** is implemented through the process of adversarial learning between a feature projector and a modality *** feature projector tries to generate a modality-invariant common representation and to confuse the modality *** modality classifier tries to discriminate between different modalities based on the generated representation by the feature *** triplet constraints are further imposed on the feature projector to preserve the underlying cross-modal semantic structure of *** experimental results show that AVMR surpasses the baseline Attentive Cross-modal Relevance Matching(ACRM) by 1.10% and 1.73% in the "mIoU" metric on two public datasets Charades-STA and TACoS,respectively.

关键词： Video Moment Retrieval Cross-modal Retrieval Deep learning Adversarial Learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：