检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

2,875 篇 会议
88 篇 期刊文献
18 册 图书

馆藏范围

2,981 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

1,342 篇 工学
- 862 篇 控制科学与工程
- 765 篇 计算机科学与技术...
- 518 篇 软件工程
- 188 篇 电气工程
- 171 篇 机械工程
- 121 篇 信息与通信工程
- 96 篇 电子科学与技术（可...
- 88 篇 仪器科学与技术
- 70 篇 光学工程
- 67 篇 生物工程
- 66 篇 建筑学
- 66 篇 土木工程
- 65 篇 生物医学工程（可授...
- 53 篇 力学（可授工学、理...
- 50 篇 航空宇航科学与技...
- 46 篇 交通运输工程
- 40 篇 化学工程与技术
- 36 篇 安全科学与工程
- 34 篇 动力工程及工程热...
457 篇 理学
- 277 篇 数学
- 127 篇 物理学
- 77 篇 统计学（可授理学、...
- 76 篇 生物学
- 54 篇 系统科学
- 44 篇 化学
245 篇 管理学
- 212 篇 管理科学与工程(可...
- 73 篇 工商管理
- 45 篇 图书情报与档案管...
40 篇 医学
- 35 篇 临床医学
- 32 篇 基础医学(可授医学...
25 篇 经济学
23 篇 法学
8 篇 教育学
8 篇 农学
8 篇 军事学
1 篇 艺术学

主题

494 篇 computational mo...
256 篇 robotics and aut...
225 篇 robot sensing sy...
211 篇 artificial intel...
210 篇 mobile robots
196 篇 intelligent robo...
190 篇 computational in...
180 篇 automation
178 篇 control systems
161 篇 humans
158 篇 robots
134 篇 orbital robotics
121 篇 robot kinematics
117 篇 navigation
111 篇 robotics
108 篇 service robots
103 篇 neural networks
103 篇 mathematical mod...
97 篇 automatic contro...
89 篇 robustness

机构

26 篇 school of automa...
25 篇 department of au...
23 篇 school of automa...
20 篇 computer and aut...
19 篇 department of au...
17 篇 dept. of automat...
14 篇 hubei key labora...
14 篇 doctoral school ...
11 篇 state key labora...
10 篇 óbuda university...
10 篇 school of mechat...
10 篇 department of au...
10 篇 school of artifi...
9 篇 antal bejczy cen...
9 篇 dep. of electric...
9 篇 university of ch...
8 篇 the robotics ins...
8 篇 computer science...
8 篇 school of automa...
8 篇 institutes for r...

作者

29 篇 radu-emil precup
20 篇 stefan preitl
18 篇 ioan filip
17 篇 józsef k. tar
15 篇 hirota kaoru
14 篇 tamás haidegger
14 篇 dai yaping
13 篇 octavian prostea...
12 篇 iosif szeidert
12 篇 precup radu-emil
11 篇 preitl stefan
11 篇 k. ito
10 篇 korondi péter
10 篇 xingming fan
10 篇 xin zhang
9 篇 wu min
9 篇 n. kubota
9 篇 t. fukuda
9 篇 f. matsuno
8 篇 peter sarcevic

语言

2,945 篇 英文
44 篇 中文
22 篇 其他

检索条件"任意字段=International Symposium on Computational Intelligence in Robotics and Automation"

共 2981 条记录，以下是401-410 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Deep Reinforcement Learning for Active Target Tracking

Deep Reinforcement Learning for Active Target Tracking

引用

IEEE international Conference on robotics and automation (ICRA)

作者： Jeong, Heejin Hassani, Hamed Morari, Manfred Lee, Daniel D. Pappas, George J. Univ Penn Dept Elect & Syst Engn Philadelphia PA 19104 USA Cornell Univ Dept Elect & Comp Engn Ithaca NY 14850 USA

ISBN: (纸本)9781728190778

We solve active target tracking, one of the essential tasks in autonomous systems, using a deep reinforcement learning (RL) approach. In this problem, an autonomous agent is tasked with acquiring information about targets of interests using its on-board sensors. The classical challenges in this problem are system model dependence and the difficulty of computing information-theoretic cost functions for a long planning horizon. RL provides solutions for these challenges as the length of its effective planning horizon does not affect the computational complexity, and it drops the strong dependency of an algorithm on system models. In particular, we introduce Active Tracking Target Network (ATTN), a unified deep RL policy that is capable of solving major sub-tasks of active target tracking - in-sight tracking, navigation, and exploration. The policy shows robust behavior for tracking agile and anomalous targets with a partially known target model. Additionally, the same policy is able to navigate in obstacle environments to reach distant targets as well as explore the environment when targets are positioned in unexpected locations.

关键词： Target tracking Navigation computational modeling Conferences Reinforcement learning Cost function Planning

来源：评论

学校读者我要写书评

暂无评论

Attention-Based Probabilistic Planning with Active Perception

Attention-Based Probabilistic Planning with Active Perceptio...

引用

IEEE international Conference on robotics and automation (ICRA)

作者： Ma, Haoxiang Fu, Jie Worcester Polytech Inst Dept Robot Engn Worcester MA 01609 USA

ISBN: (纸本)9781728190778

Attention control is a key cognitive ability for humans to select information relevant to the current task. This paper develops a computational model of attention and an algorithm for attention-based probabilistic planning in Markov decision processes. In attention-based planning, the robot decides to be in different attention modes. An attention mode corresponds to a subset of state variables monitored by the robot. By switching between different attention modes, the robot actively perceives task-relevant information to reduce the cost of information acquisition and processing, while achieving near-optimal task performance. Though planning with attention-based active perception inevitably introduces partial observations, a partially observable MDP formulation makes the problem computational expensive to solve. Instead, our proposed method employs a hierarchical planning framework in which the robot determines what to pay attention to and for how long the attention should be sustained before shifting to other information sources. During the attention sustaining phase, the robot carries out a sub-policy, computed from an abstraction of the original MDP given the current attention. We use an example where a robot is tasked to capture a set of intruders in a stochastic gridworld. The experimental results show that the proposed method enables information- and computation-efficient optimal planning in stochastic environments.

关键词： Costs computational modeling Active perception Switches Predictive models Probabilistic logic Planning

来源：评论

学校读者我要写书评

暂无评论

Command Filtered Tracking Control for High-order Systems with Limited Transmission Bandwidth

Command Filtered Tracking Control for High-order Systems wit...

引用

IEEE international Conference on robotics and automation (ICRA)

作者： Bao, Jialei Liu, Peter Xiaoping Wang, Huanqing Zheng, Minhua Zhao, Ying Beijing Jiaotong Univ Sch Mech Elect & Control Engn Beijing 100044 Peoples R China Carleton Univ Dept Syst & Comp Engn Ottawa ON K1S 5B6 Canada Bohai Univ Sch Math Jinzhou 121000 Peoples R China

ISBN: (纸本)9781728190778

This paper investigates the tracking control problem of a class of high-order distributed systems subjected to limited communication bandwidth. An event-triggered control method is proposed, where the controller is triggered only when specific events happen. Moreover, the computational complexity is reduced by introducing command filters for virtual control signals. Specifically, the backstepping scheme is adopted as the main design framework, by which the n-th order nonlinear system is divided into n command-cascaded first order subsystems. And virtual control commands are sent through a second-order low-pass filter, by which the time derivatives of the virtual commands can be obtained directly. The theoretical analysis shows the stability of the proposed method. The tracking performance is illustrated by a simulation example.

关键词： Backstepping Conferences computational modeling Decentralized control Low-pass filters Bandwidth Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient Reachability Analysis of Closed-Loop Systems with Neural Network Controllers

Efficient Reachability Analysis of Closed-Loop Systems with ...

引用

IEEE international Conference on robotics and automation (ICRA)

作者： Everett, Michael Habibi, Golnaz How, Jonathan P. MIT Aerosp Controls Lab Cambridge MA 02139 USA

ISBN: (纸本)9781728190778

Neural Networks (NNs) can provide major empirical performance improvements for robotic systems, but they also introduce challenges in formally analyzing those systems' safety properties. In particular, this work focuses on estimating the forward reachable set of closed-loop systems with NN controllers. Recent work provides bounds on these reachable sets, yet the computationally efficient approaches provide overly conservative bounds (thus cannot be used to verify useful properties), whereas tighter methods are too intensive for online computation. This work bridges the gap by formulating a convex optimization problem for reachability analysis for closed-loop systems with NN controllers. While the solutions are less tight than prior semidefinite programbased methods, they are substantially faster to compute, and some of the available computation lime can be used to refine the bounds through input set partitioning, which more than overcomes the tightness gap. The proposed framework further considers systems with measurement and process noise, thus being applicable to realistic systems with uncertainty. Finally, numerical comparisons show that our approach based on linear programming and partitioning can give 10x reduction in conservatism in 1/2 of the computation time compared to the state-of-the-art, and the ability to handle various sources of uncertainty is highlighted on a quadrotor model.

关键词： Uncertainty computational modeling Artificial neural networks Robot sensing systems computational efficiency Safety Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Path Planning Based on Improved RRT Algorithm

Path Planning Based on Improved RRT Algorithm

引用

Control Engineering and robotics (ISCER), international symposium on

作者： Yanguo Huang Chao Jin School of electrical engineering and automation Jiangxi University of technology Ganzhou Jiangxi China

The traditional path-exploring Random Trees (RRT) algorithm has the defects of low search efficiency and high path curvature. Based on the basic RRT algorithm, target bias strategy and pruning optimization algorithm are adopted to reduce unnecessary blank search and improve the computational speed. By introducing stretch function, the generated path is searched forward along the end node, and the two non-adj acent nodes with no obstacles in the middle are merged to reduce redundant paths. The cubic B-spline function is used to make the path curve smoother. In the matlab simulation environment simulation. Simulation results show that compared with the traditional RRT algorithm, the improved path planning algorithm greatly reduces the length of path planning and the path search time, and verifies the effectiveness of the path planning algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Simulation Modeling of Highly Dynamic Omnidirectional Mobile Robots Based on Real-World Data

Simulation Modeling of Highly Dynamic Omnidirectional Mobile...

引用

IEEE international Conference on robotics and automation (ICRA)

作者： Marvin Wiedemann Ossama Ahmed Anna Dieckhöfer Renato Gasoto Sören Kerner Department AI and Autonomous Systems Fraunhofer Institute for Material Flow and Logistics Dortmund Germany NVIDIA Santa Clara CA USA Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Simulation is a key technology in robotics as it enables the generation of environmental data and testing scenarios for development and maintenance purposes. However, simulations are an imperfect representation of the real-world and the so-called sim-to-real gap between simulation and reality hinders the deployment of virtual developed solutions without additional effort. Modeling complex systems like highly dynamic and holonomic mobile robots presents additional complexities in simulation. This paper addresses these challenges through a case study on creating a model for a highly dynamic logistics robot. The study considers the modeling of the entire system down to creating suitable colliders for the rollers of a Mecanum wheel. Additionally, the impact of significant physics parameters is presented. To bridge the sim-to-real gap, a pipeline is developed that utilizes a Motion Capture system to compare the behavior of a real robot with its simulated counterpart across various motions. By leveraging expert knowledge gained from the real-world data, the simulation model is manually tuned to replicate complex system behaviors, such as sliding effects.

关键词： computational modeling Pipelines Dynamics Manuals Data models Mobile robots Complex systems

来源：评论

学校读者我要写书评

暂无评论

Research on the Application of Deep Learning Algorithm in Visual Perception and Recognition of Artificial intelligence Robot

Research on the Application of Deep Learning Algorithm in Vi...

引用

Electrical, automation and Computer Engineering (ICEACE), international Conference on

作者： Yujia Li Siheng Ren Na Yang School of Metallurgy Northeastern University Shenyang China Space Engineering University Beijing China

ISBN: (数字)9798350368208

ISBN: (纸本)9798350368215

With the rapid advancement of science and technology, artificial intelligence (AI) has emerged as a focal point in the realm of technology. Among its core branches, deep learning endows computers with formidable data processing capabilities by emulating the cognitive processes of the human brain. This work delves into the application of deep learning in robotic visual perception, encompassing areas such as image recognition, object detection, and motion planning, thereby illustrating how deep learning algorithms can markedly enhance a robot’s visual perception capabilities. To validate these enhancements, the YOLOv5 model was employed for real-time object detection, which was further integrated with the A* algorithm for robotic path planning. The outcomes demonstrate that the YOLOv5-based object detection algorithm performs admirably in complex environments. Collectively, this research furnishes fresh perspectives and methodologies for the progression of robotics technology in the future.

关键词： Deep learning YOLO Computers Heuristic algorithms computational modeling Real-time systems Path planning Vehicle dynamics Robots Visual perception

来源：评论

学校读者我要写书评

暂无评论

Motion Planning of Tree Fruit Robot Picker in Presence of Obstacles Using Heuristic Approach

Motion Planning of Tree Fruit Robot Picker in Presence of Ob...

引用

international symposium on Applied computational intelligence and Informatics ( SACI)

作者： Aleksandar Rodić Jelena Kljajić Robotics department Mihajlo Pupin Institute Serbia Serbia

ISBN: (数字)9798350329520

ISBN: (纸本)9798350329537

The paper introduces a heuristic approach for planning the motion of fruit-picking robots operating among various, randomly placed obstacles within the task's operational space. A linear robot, equipped by three degrees of Cartesian-type freedom, has been designed for this task, featuring an additional telescopic arm and a specialized gripper. This gripper is uniquely fitted with two rotational joints at the wrist, enabling precise orientation adjustment of the tool in relation to the fruit on the branches. The planning of the robot's movement leverages machine vision and artificial intelligence algorithms, including artificial neural networks and fuzzy logic for decision making. This heuristic approach to the robot picker's movement planning draws inspiration from human-inspired techniques used in manual fruit picking on fruit plantations. The methodology employed utilizes environmental data to determine the shortest paths for the robot's gripper to reach specific targets, and to assess the relative position (orientation) of the actuator in relation to the target or obstacles encountered along the way (such as branches, clusters of leaves, trees, etc.). The effectiveness of this movement planning methodology has been confirmed through simulation models of the robot and its environment.

关键词： Wrist Machine vision Plantations Manuals Manipulators Planning Grippers

来源：评论

学校读者我要写书评

暂无评论

Towards Real-time Semantic RGB-D SLAM in Dynamic Environments

Towards Real-time Semantic RGB-D SLAM in Dynamic Environment...

引用

IEEE international Conference on robotics and automation (ICRA)

作者： Ji, Tete Wang, Chen Xie, Lihua Nanyang Technol Univ Sch Elect & Elect Engn 50 Nanyang Ave Singapore 639798 Singapore Carnegie Mellon Univ Robot Inst Pittsburgh PA 15213 USA

ISBN: (纸本)9781728190778

Most of the existing visual SLAM methods heavily rely on a static world assumption and easily fail in dynamic environments. Some recent works eliminate the influence of dynamic objects by introducing deep learning-based semantic information to SLAM systems. However such methods suffer from high computational cost and cannot handle unknown objects. In this paper, we propose a real-time semantic RGB-D SLAM system for dynamic environments that is capable of detecting both known and unknown moving objects. To reduce the computational cost, we only perform semantic segmentation on keyframes to remove known dynamic objects, and maintain a static map for robust camera tracking. Furthermore, we propose an efficient geometry module to detect unknown moving objects by clustering the depth image into a few regions and identifying the dynamic regions via their reprojection errors. The proposed method is evaluated on public datasets and real-world conditions. To the best of our knowledge, it is one of the first semantic RGB-D SLAM systems that run in real-time on a low-power embedded platform and provide high localization accuracy in dynamic environments.

关键词： Geometry Location awareness Visualization Simultaneous localization and mapping Semantics Real-time systems computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Towards Reliable CIDS: Hybrid Reputation and Challenge Strategies for Combating Internal Attacks

Towards Reliable CIDS: Hybrid Reputation and Challenge Strat...

引用

robotics, Control and automation (ICRCA), international Conference on

作者： Yuandong Min Jingjing Zhang Sicong Liu Jia Li Furong Yu Jianjun Chen Hao Zhang National Engineering Research Center for E-Learning Faculty of Artificial Intelligence in Education Central China Normal University Wuhan China Wuhan Maritime Communication Research Institute (WMCRI) Wuhan China

ISBN: (数字)9798331544577

ISBN: (纸本)9798331544584

Collaborative Intrusion Detection Systems (CIDS) serve as crucial firewalls, maintaining system security through necessary information exchange and integration among nodes in distributed systems. While CIDS excel at defending against external network attacks, internal threats remain a significant challenge. To identify malicious internal nodes, researchers typically adopt trust management mechanisms. However, current methods often fail to effectively take into account nodes' global reputation and historical behavior. Recognizing the similarities between distributed networks and social networks, we propose a hybrid trust computation mechanism based on social network reputation theory and develop a high-performance node clustering model. Simulated experiments conducted on a network with 50 nodes demonstrate that our method achieves higher accuracy and recall rates in identifying malicious nodes under adverse conditions compared to traditional methods, thereby enhancing the resilience of distributed networks against internal attacks.

关键词： Social networking (online) Firewalls (computing) computational modeling Intrusion detection Reliability theory Network security Trust management Robots Information exchange Resilience

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共299页 << < 37 38 39 40 41 42 43 44 45 46 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：