检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Wang, Xinzhu Gong, Xiaoyan Liu, Xiwei Yan, Yan Zhang, Nan Luo, Jie State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Faculty of Education Beijing Normal University Beijing China Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China Chinese Association of Automation Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China

ISBN: (纸本)9781728128535

Teacher's Online Practice in Community (TOPIC) is an informal and practical online learning community that improves teachers' professional development. Domestic researches on TOPIC have begun to take shape. By sorting out relevant literature retrieved from China National Knowledge Infrastructure (CNKI), this article summarizes research topics such as knowledge management, teacher professional development, and community management and summarizes qualitative and quantitative research methods commonly used by domestic researches. This article finally puts forward some limitations of current researches in this field and forecasts the possible future research directions. © 2019 IEEE.

关键词： Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Conservative Policy Gradient in Multi-critic Setting

Conservative Policy Gradient in Multi-critic Setting

引用

Chinese Automation Congress (CAC)

作者： Bao Xi Rui Wang Shuo Wang Tao Lu Yinghao Cai University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex System Institute of Automation Beijing China

Twin Delayed Deep Deterministic policy gradient algorithm (TD3) addressed the overestimation bias problem by adopting a clipped Double Q-Learning method. As the two Q networks are different, the updation of a policy to maximize one Q function might minimize another, which is called inconsistency in this paper. Therefore, we propose an algorithm based on TD3, conservative policy gradient (CPG), that optimizes the policy with respect to the lower bound of the two Q functions to deal with the inconsistancy. In Q function learning, one-step estimate is usually used in target value estimation. However, due to the constantly changing target networks, there will be fluctuations in the estimation. As the target Q function is changing slowly, we combine the one-step estimate with zero-step estimate to avoid sharp changes. The experimental results illustrate that CPG outperforms TD3 and some other reinforcement learning methods on multiple MuJoCo benchmarks.

关键词： Training Benchmark testing Estimation Learning (artificial intelligence) Games Robots Task analysis

来源：评论

学校读者我要写书评

暂无评论

GPO: Global plane optimization for fast and accurate monocular SLAM initialization

arXiv

引用

arXiv 2020年

作者： Du, Sicong Guo, Hengkai Chen, Yao Lin, Yilun Meng, Xiangbing Wen, Linfu Wang, Fei-Yue PA2R2T Group State Key Laboratory of Complex System Management and Control Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing10049 China ByteDance AI Lab Beijing100089 China

Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems. This paper focuses on a novel initialization method for monocular SLAM based on planar features. The algorithm starts by homography estimation in a sliding window. It then proceeds to a global plane optimization (GPO) to obtain camera poses and the plane normal. 3D points can be recovered using planar constraints without triangulation. The proposed method fully exploits the plane information from multiple frames and avoids the ambiguities in homography decomposition. We validate our algorithm on the collected chessboard dataset against baseline implementations and present extensive analysis. Experimental results show that our method outperforms the fine-tuned baselines in both accuracy and real-time. Copyright © 2020, The Authors. All rights reserved.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

key technologies of GNSS/INS/VO deep integration for UGV navigation in urban canyon 11

Key technologies of GNSS/INS/VO deep integration for UGV nav...

引用

2017 11th Asian control Conference, ASCC 2017

作者： Meiling, Wang Yafeng, Li Guoqiang, Feng Yi, Yang Tong, Liu Xiao, Xuan School of Automation State Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781509015733

As a new emerging integrated navigation technology, the GNSS/INS/VO deep integration system can fully leverage the synergistic and complementary characteristics of the three involved subsystems to achieve cost reduction while improving navigation accuracy, availability, and robustness, by mutual aiding between subsystems. In this paper, firstly, based on a brief review of the technical background and research status of the GNSS/INS/VO deep integration technology, the processing flows of this deep integration mode in both signal and information domains are analyzed, and its performance advantages are summarized. Then, the top-level technology roadmap of the GNSS/INS/VO deep integration for UGV navigation in the urban canyon is presented, and several key technical issues from scheme demonstration to engineering implementation are explored. At last, the short and medium term development prospects of the GNSS/INS/VO deep integration are envisaged. The proposed research ideas and system design concept for GNSS/INS/VO deep integration could be used as a reference for relevant technicians in navigation field. © 2017 IEEE.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Optimize Student Learning via Random Forest-Based Adaptive Narrative Game

Optimize Student Learning via Random Forest-Based Adaptive N...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Ryan Hare Ying Tang Wei Cui Joleen Liang Department of Electrical and Computer Engineering Rowan University Glassboro USA State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China Squirrel AI Learning Shanghai China

ISBN: (数字)9781728169040

ISBN: (纸本)9781728169057

This paper presents an adaptive narrative game system that focuses on sequential logic design. The system adapts a random forest machine learning model to estimate a student's current level of domain knowledge relative to the problem presented to him through his game-playing behavior data, such as time taken to find solutions, errors in solutions, and emotional indicators. Hints, prompts, and/or individualized lessons are then offered to the player to guide their learning in a positive and productive direction. Our preliminary pilot study demonstrates that the model can make accurate classifications, from which proper assistance can then be provided to individual students as they play.

关键词： Games Databases Forestry Education Problem-solving Presses Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

An Obstacles Avoidance Algorithm Based on Improved Artificial Potential Field

An Obstacles Avoidance Algorithm Based on Improved Artificia...

引用

IEEE International Conference on Mechatronics and Automation

作者： Si Xi Lu En Li Rui Guo School of Artificial Intelligence University of Chinese Academy of Sciences No.19(A) Yuquan Road Beijing China The State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Science 95 East ZhongGuanCun Road Beijing China State Grid Shandong Electric Power Company Jinan China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Obstacle avoidance is one of the most important issue in the motion planning and control of robot. There are many algorithms to avoid obstacles, but obstacle avoidance algorithm for manipulator is needed consider not only end effector, but also all links of manipulator. In terms of real-time and speed of all system, the algorithm also should be easy as possible. In this paper, an algorithm based on the improved artificial potential field is proposed to solve the problem of the local optimum. The idea of improvement is to find a path by fitting curve with target point and critical oscillating points. There is also a comparison in this paper with planning a path by tangent line. The conclusion proves that the path is much smoother by the algorithm based on improved artificial potential field in this paper. Furthermore, the problem of judder on the trajectory of traditional artificial potential field is also solved in this paper by an improved repulsive potential field function. Finally, the algorithm is proved by planning a smooth path for obstacle avoidance on manipulator: KinovaGen3 in MATLAB.

关键词： Mechatronics Fitting End effectors Real-time systems Planning Trajectory Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

A two-level adaptive target recognition and tracking method based on vision for multi-robot system

A two-level adaptive target recognition and tracking method ...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Ren, Liang Cao, Zhiqiang Tan, Min Zhao, Peng Chen, Xuechao University of Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems CASIA Beijing China 21st Research Institute of China Electronics Technology Group Corporation Shanghai China BIT Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing China

ISBN: (纸本)9781728163215

The vision-based target recognition and tracking have received much attention in the field of robotics. Existing methods mainly focus on the vision perception of individual robot with a single view, however, the performance is susceptible to illumination and occlusion. Multi-robot collaborative perception provides a potential solution to deal with the limitation of single-view observation, however, the challenging of environmental adaptability for multi-robot collaborative decision still remains unsolved. To solve this problem, this paper proposes a two-level adaptive target recognition and tracking method based on vision for multi-robot system. The problem of multi-robot target recognition and tracking is solved under a two-level framework, which contains the features fusion level of individual robot and the cooperation level of multi-robot system. In the first level, the features measuring results that influence the visual perception of individual robot are fused, while the second level combines the voting of each robot together to determine the target for multi-robot system. Both the features measuring weights and robots voting weights are adaptively updated according to their evaluation, which lead to a beneficial result where the features and robots with higher accuracy play major roles in the first and second levels, respectively. Therefore, a good adaptability to the environments can be guaranteed. The experimental results show that the proposed approach can realize the coordination of multi-robot system in target recognition and tracking with an effective performance. © 2019 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Social Manufacturing for High-end Apparel Customization

引用

IEEE/CAA Journal of Automatica Sinica 2018年第2期5卷 489-500页

作者： Xiuqin Shang Fei-Yue Wang Gang Xiong Timo R. Nyberg Yong Yuan Sheng Liu Chao Guo Sen Bao State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Science at Aalto University Aalto FI-00076 Finland Qingdao Academy of Intelligent Industries Qingdao 266109 China IEEE

Social manufacturing(SM), a novel distributed,collaborative and intelligent manufacturing mode, is proposed and developed for high-end apparel customization. The main components of SM cloud are designed, and its research topics are summarized. Then, SM's key technologies are studied. 3D technologies for apparel customization, like 3D modeling, 3D fitting mirror and 3D customization, are developed to improve the customization precision and user experience. Information based collaborative management is realized to share, communicate,and handle the information efficiently among all groups and individuals of SM cloud. Suppliers' evaluation mechanism is designed to support the optimal decisions making. Next, SM cloud is constructed in five layers for high-end apparel *** using SM cloud based crowd-sourcing, social resources can be allocated rationally and utilized efficiently, consumer can customize the product in any processes like innovation, design,making, marketing and service, and traditional apparel enterprise can be upgraded into SM mode for keeping it competitive in the future customization markets.

关键词： Index Terms-Big data collaborative management social man-ufacturing cloud 3D apparel customization.

来源：评论

学校读者我要写书评

暂无评论

A Human-Robot Skill Transfer Framework of Mobile Medical Robots for Autonomous Motion with Teaching by Demonstration

A Human-Robot Skill Transfer Framework of Mobile Medical Rob...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Jiehao Li Junzheng Wang Shoukun Wang Hui Peng Qi Wen Longbin Zhang Meina Lin Politecnico di Milano Milan Italy State Key Laboratory of Complex System Intelligent Control and Decision Beijing Institute of Technology Beijing China College of Intelligence Science and Technology National University of Defense Technology Changsha China BioMEx Center KTH Mechanics KTH Royal Institute of Technology Stockholm Sweden Guangdong Key Laboratory of IoT Information Technology Guangdong University of Technology Guangzhou China

ISBN: (数字)9781728164793

ISBN: (纸本)9781728164809

The accuracy of autonomous motion is the main challenge for mobile medical robots, especially running in narrow space conditions to transport the casualties in the hospital. This article mainly centers on the human-robot transmission of the mobile medical robot for narrow space autonomous motion. In order to enable mobile medical robots to autonomously and smoothly transport hospital casualties through narrow aisles, in this paper, we present a robot skill transfer technology, namely a human-robot skill transfer framework of mobile medical robots for autonomous motion with teaching by demonstration, which is that a smooth optimal path is planned through the human motion, and then the Kinect sensor is used to detect human bone movement to learn its motion trajectory so as to achieve trajectory tracking control. Meanwhile, using the Remote Center of Motion (RCM) constraint to minimize the error between the actual trajectory of the medical robot and the tracking reference path to control the motion trajectory accurately, human-computer interactive mobile medical robots can smoothly pass through narrow channels. Through research and analysis, it is demonstrated that the mobile medical robot proposed in this paper has great feasibility, which is of great reference value in the field of medical rescue.

关键词： Medical robotics Education Trajectory Mobile robots Tracking Hospitals

来源：评论

学校读者我要写书评

暂无评论

Capsule Network-Based Text Sentiment Classification

引用

IFAC-PapersOnLine 2020年第5期53卷 698-703页

作者： Bingyang Chen Zhidong Xu Xiao Wang Long Xu Weishan Zhang School of Computer Science and Technology China University of Petroleum Qingdao 266580 China School of security National Defence University PLA China Beijing 100091 China Beijing 100091 China Qingdao Academy of Intelligent Industries Shandong Qingdao 266109 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

To improve text sentiments classification issues, such as information loss and insensitivity to spatial information, this paper proposes a text sentiment classification model based on the capsule network (T-Caps), which uses the Transformer to extract low-level text features. The method iteratively updates capsule network parameters through optimized dynamic routing algorithms and global parameter sharing, and it obtains the relationship between local features of the text and the overall emotional polarity to save the information integrity of text features. By comparing with multiple models, we find that the Transformer has the strongest feature extraction capability. The experimental results show that our model is capable of extracting more discriminative semantic features and yields a significant performance gain compared to other baseline methods.

关键词： Sentiment classification Capsule network Transformer Deep learning Attention

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：