检索结果-南通市图书馆

第二十九届中国控制会议

作者： SHEN Xiaojing 1,2,ZHU Yunmin1,SONG Enbin1,LUO Yingting1,YOU Zhisheng2 1.Department.of Mathematics,Sichuan University Chengdu,Sichuan 610064,P.R.China2.Department of Computer Science,Sichuan University Chengdu,Sichuan 610064,P.R.China

In this paper,a dynamic system with model uncertainty and bounded noises is *** propose several efficient methods of centralized fusion,distributed fusion and fusion of multiple parallel algorithms for minimizing Euclidian estimation error of the state *** make Euclidian estimation error as small as possible,the classic measure of "size" of an ellipsoid-trace of the shape matrix of the ellipsoid is extended to a class of weighted measure which can emphasize the importance of the interested entry of the state vector and make its confidence interval ***,it can be proved that both the centralized fusion and the distributed fusion are better than the estimation of single sensor in the class of the weighted *** results are illustrated by a numerical *** importantly,sufficiently taking advantages of the two facts that minimizing a scalar objective cannot guarantee to derive an optimal multi-dimensional confidence ellipsoid solution,as well as,multiple sensors and multiple algorithms have the feature of advantage complementary,we will construct various estimation fusion methods at both the fusion center and local sensors to yield as significantly as possible interlaced estimate intervals of every entry of the state vector for minimizing Euclidian estimation error.

关键词： multisensor fusion fusion of multiple algorithms Euclidian estimation error

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Generalized LMMSE Filtering with Out-of-Sequence Observations in Arbitrary Constant Delay

引用

Chinese Journal of Electronics 2019年第6期28卷 1217-1226页

作者： LEI Ming BAEHR Christophe JING Zhongliang School of Aeronautics and Astronautics Shanghai Jiao Tong University Météo-France National Meteorological Research Centre/CNRS

Focusing on the problem of state estimation in the presence of sensor faults and Out-of-sequence measurement(OOSM) observations synchronously, we derive a formulation of Linear minimum mean squared error(LMMSE) filter with the arbitrary time delay of OOSM, the generalization of the present work lies in simultaneous treatment of correlated faults together with OOSMs that arrive at an arbitrary delay in a linear-optimal manner. The approach is demonstrated in a numerical comparison.

关键词： Out-of-sequence measurement(OOSM) Linear minimum mean squared error(LMMSE) Arbitrary time delay Sensor faults Fault-tolerant estimation multisensor fusion

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Review:Recent advances in multisensor multitarge11racking using random finite set

引用

Frontiers of Information Technology & Electronic Engineering 2021年第1期22卷 5-24页

作者： Kai DA Tiancheng LI Yongfeng ZHU Hongqi FAN Qiang FU The National Key Laboratory of Science and Technology on ATR Nalional Universily of Defense TechnologyChangsha 410073China MOE Key Laboratory of Information fusion Technology School of AutomationNorthwestern Polytechnical UniversityXi'an 710072China

In this study,we provide an overview of recent advances in multisensor multitarget tracking based on the random finite set(RFS)*** fusion that plays a fundamental role in multisensor filtering is classified into data-level multitarget measurement fusion and estimate-level multitarget density fusion,which share and fuse local measurements and posterior densities between sensors,*** properties of each fusion rule including the optimality and sub-optimality are *** particulax,two robust multitarget density-averaging approaches,arithmetic-and geometric-average fusion,are addressed in detail for various *** research topics and remaining challenges are highlighted.

关键词： Multitarget tracking multisensor fusion Average fusion Random finite set Optimal fusion

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Global Guidance-Based DRL Multi-Sensor fusion Navigation Strategy

Global Guidance-Based DRL Multi-Sensor Fusion Navigation Str...

引用

第35届中国过程控制会议

作者： Yanxu Sun Jiayu Chai Botao Zhang Qiang Lu Weikang Yuan Hongye Yang School of Automation Hangzhou Dianzi University

This thesis presents a novel path planning approach for mobile robots that combines deep reinforcement learning(DRL) with multi-sensor fusion, enhanced by a global guidance strategy to elevate navigation capabilities in complex environments. Leveraging Long Short-Term Memory(LSTM) networks, the method processes extensive sequences of LiDAR data,employs Convolutional Neural Networks(CNNs) for interpreting visual inputs from depth cameras, and integrates Inertial Measurement Unit(IMU) data to consistently direct the robot towards its goal while dynamically adapting to changes in the environment. The learning process is enhanced with an advanced version of the Prioritized Experience Replay(PER) algorithm, which refines the experience replay mechanism to boost the model's precision and resilience. Additionally, by integrating global route pre-planning with local adjustments, this approach not only secures global path optimality but also heightens the system's responsiveness to environmental changes. Extensive numerical simulations validate the model's efficacy in adapting its navigation strategies, thereby ensuring path optimality and safety under varied conditions.

关键词： Mobile Robot Navigation Deep Reinforcement Learning multisensor fusion Prioritized Experience Replay

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

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：