检索结果-内蒙古大学图书馆

Chinese Automation Congress (CAC)

作者： Zeze Si Hongxia Zhao Haina Tang Fenghua Zhu Yisheng Lv Hao Lu State Key Laboratory for Management and Control of Complex Systems Institute of Autamation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academic of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China

In many driving situations, human mobility is an important topic in trajectory prediction. Considering the pedestrian trajectory as a sequence generative task, a prediction algorithm based on Social Long Short-Term Memory (Social LSTM) is implemented. In order to simulate the social interaction between pedestrians, Social Pooling (S-Pooling) is used to aggregate the hidden state of pedestrians, while the attention mechanism is utilized to aggregate information differently according to the importance of surrounding pedestrians. Furthermore, Convolutional Neural Networks (CNN) is introduced into Social LSTM model to consider both the interaction between people and the characteristic of scene scale in the prediction process. Experiments are carried out against baseline methods, and the results demonstrated that combining Social LSTM with attention mechanism or CNN can improve the performance of pedestrian trajectory prediction.

关键词： Automation Aggregates Predictive models Prediction algorithms Trajectory Convolutional neural networks Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Study on Decentralized Autonomous Organizations Based Intelligent Transportation System enabled by Blockchain and Smart Contract

A Study on Decentralized Autonomous Organizations Based Inte...

引用

2021 China Automation Congress, CAC 2021

作者： Hou, JiaChen Ding, WenWen Liang, Xiaolong Zhu, FengHua Yuan, Yong Wang, FeiYue Institute of Systems Engineering Macau University of Science and Technology China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Mathematics Renmin University of China Beijing China

ISBN: (纸本)9781665426473

With the rapid development of the transportation industry, Intelligent Transportation System (ITS) tries to adapt to industry changes through constructing new organizational forms, management methods, and incentive mechanisms. However, many new governance issues have arisen due to the transportation system's complexity, diversity, and uncertainty. DAO(Decentralized autonomous organization) enabled by blockchain and smart contracts are regarded as effective methods to solve the organizational governance problems for complex systems. Therefore, this article analyzes the main issues currently faced by ITS. Then, this paper proposed a 6-layer DAO structure framework for ITS and discussed its key research issues. Finally, a case study for the Macau transportation system is carried out, and further research directions are proposed. The DAO-based transportation system will represent the future trend of ITS development. This paper aims to motivate more discussion for this new direction and provide helpful guidance and reference for future research work. © 2021 IEEE

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

FISS GAN:A Generative Adversarial Network for Foggy Image Semantic Segmentation

引用

IEEE/CAA Journal of Automatica Sinica 2021年第8期8卷 1428-1439页

作者： Kunhua Liu Zihao Ye Hongyan Guo Dongpu Cao Long Chen Fei-Yue Wang School of Computer Science and Engineering Sun Yat-sen UniversityGuangzhou 510006China State Key Laboratory of Automotive Simulation and Control and the Department of Control Science and Engineering Jilin University(Campus Nanling)Changchun 130025China Mechanical and Mechatronics Engineering Department at the University of Waterloo 200 University Avenue West WaterlooON N2L 3G1Canada State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

Because pixel values of foggy images are irregularly higher than those of images captured in normal weather(clear images),it is difficult to extract and express their *** method has previously been developed to directly explore the relationship between foggy images and semantic segmentation *** investigated this relationship and propose a generative adversarial network(GAN)for foggy image semantic segmentation(FISS GAN),which contains two parts:an edge GAN and a semantic segmentation *** edge GAN is designed to generate edge information from foggy images to provide auxiliary information to the semantic segmentation *** semantic segmentation GAN is designed to extract and express the texture of foggy images and generate semantic segmentation *** on foggy cityscapes datasets and foggy driving datasets indicated that FISS GAN achieved state-of-the-art performance.

关键词： Edge GAN foggy images foggy image semantic segmentation GAN semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

ReCUS: Reconvolution and Upsampling Network for Object Detection 7

ReCUS: Reconvolution and Upsampling Network for Object Detec...

引用

7th IEEE International Conference on Cloud Computing and Intelligence systems, CCIS 2021

作者： Li, Fudong Gao, Dongyang Yang, Yuequan Cao, Zhiqiang Wang, Wei Yangzhou225000 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China Affiliated Hospital of Yangzhou University Yangzhou225012 China

ISBN: (纸本)9781665441490

Most of the mainstream object detection models such as RetinaNet, SSD, YOLO, and Faster RCNN hardly achieve a good balance between detection accuracy and speed. A major reason is rich deep feature semantic information of images is not fully exploited. To solve this problem, a novel deep convolutional network structure termed as reconvolution and upsampling network (ReCUS) is proposed. In the ReCUS, a modified path aggregation network(mPAN) is added after the backbone, which is beneficial to strengthen the foreground salient feature information and weaken background information. Moreover, two new spatial pyramid pooling (SPP) modules are embedded before output heads for multi-scale fusion of local and global features. The experiments show that the effectiveness of our proposed ReCUS. Furthermore, the better detectability of the ReCUS network is demonstrated for both small scale objects and large scale objects. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Moving Target Shooting Control Policy Based on Deep Reinforcement Learning

Moving Target Shooting Control Policy Based on Deep Reinforc...

引用

2021 International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2021

作者： Li, Boyu Jin, Tao Zhu, Yuanheng Li, Haoran Wu, Yingnian Zhao, Dongbin Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China Beijing Information Science and Technology University School of Automation Beijing100192 China

ISBN: (纸本)9781665402453

Robots are playing a more and more important role in people's production and life, recently. However, robot control in dynamic environment is still a difficulty. With the great breakthrough of deep reinforcement learning in the field of video games, this method is also extended to the field of robots. Due to the gap between the simulation environment and the real environment, the deep reinforcement learning algorithm trained in the simulation environment is difficult to be applied to the real environment. Aiming at the gimbal control with two degrees of freedom (DOF), a pipline combining system identification and deep reinforcement learning is proposed. On the one hand, the shooting accuracy of the gimbal to moving objects is improved through deep reinforcement learning algorithm. On the other hand, the gap between simulation and reality is reduced through system identification. The method is verified in the RoboMaster University AI Challenge (RMUA) shooting system. The results show that the shooting accuracy is better than the classical control method. © 2021 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

UCAS-hand: An underactuated powered hand exoskeleton for assisting grasping task

UCAS-hand: An underactuated powered hand exoskeleton for ass...

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Li, Houcheng Cheng, Long Li, Zhengwei Li, Guotao Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9781665436786

This paper presents a novel underactuated coupled adaptive hand exoskeleton, called UCAS-Hand, which is designed to assist users with weak muscle strength to complete the operation of daily living items. In mechanical design, the proposed UCAS-Hand considers the human-robot kinematic compatibility, grasping adaptability for different objects, portability with motors attached to the hand, force transfer efficiency with applying normal force to the finger phalanges, and passive backdrivability with low gear reduction ratio motor. The UCAS-Hand can realize finger underactuated motions such as flexion/extension and thumb underactuated motions such as flexion/extension, abduction/adduction, and thumb opposability. To minimize the backlashes of bevel gear transmission, a spherical four-bar mechanism and a spherical seven-bar mechanism are designed for the index finger and thumb mechanisms, respectively. Finally, the experiment is implemented to reveal the characteristics of the UCAS-Hand. © 2021 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Parallel Theaters in CPSS: From Shadows of ISDOS to Intelligence of Decision Theaters

引用

IEEE/CAA Journal of Automatica Sinica 2025年第6期12卷 1059-1062页

作者： Qinghua Ni Buday Viktória Fei Lin Jun Huang Levente Kovács Nan Zheng Fei-Yue Wang Department of Engineering Science Faculty of Innovation Engineering Macau University of Science and Technology Macau China Innovation Management Doctoral School Obuda University Budapest Hungary John von Neumann Faculty of Informatics Obuda University Budapest Hungary State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China DeSci Center of Parallel Intelligence and the University Research and Innovation Center at Obuda University State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China

As Artificial Intelligence (AI) is moving fast from Large Language Models (LLMs) to AI Agents and Agentic Intelligence, the need to incorporate new AI into Decision Intelligence (DI) is becoming more and more urgent for both practical and theoretic reasons: both decision and process complexities would be significantly increased due to the use of advanced AI tools and agents, and both traditional and recent thinking must be rethought and reconstructed accordingly. Our perspective would like to address this important issue based on some historical milestone developments in Computer-Aided Software Engineering (CASE) and recent efforts in digital theatrical technology [1].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Framework and key Technologies for High-speed Railway Comprehensive Transport Hub

Framework and Key Technologies for High-speed Railway Compre...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Gang Xiong Wei Zhang Xiaoming Liu Zhiming Yuan Fenghua Zhu Zundong Zhang State Key Laboratory for Multimodal Artificial Intelligence Systems Chinese Academy of Sciences Beijing China School of Electrical and Control Engineering North China University of Technology Beijing China Communication Signal Research Institute China Academy of Railway Science Beijing China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China

The surge in urban population density in China has underscored the vital role of high-speed rail and subway systems in urban transit. Comprehensive transportation hubs, notably high-speed rail passenger terminals, have emerged as linchpins for seamless multimodal transit both within and beyond urban centers. China's railway sector vigorously champions the innovative concept of "station-city integration" and has articulated a forward-looking "16-word policy" for modern railway stations: "Seamless integration, environmental friendliness, economic viability, and intelligent accessibility". The judicious allocation of resources and the augmentation of coordination and control capabilities within comprehensive transportation hubs are imperative for the harmonious evolution of urban transit. The implementation of intelligent control systems for transportation hubs has emerged as a pivotal area of research. This study delves into the framework and critical technologies for high-speed railway comprehensive transport hubs, encompassing various components and their intricate interplay, including transport modalities, infrastructure, travelers, environmental factors, and information systems, thus forming a prototypical cyber-physical-social system. Addressing the prevalent and pressing imperative for the advancement of "station-city integration" high-speed railway comprehensive transport hubs, this research endeavor aims to surmount bottleneck challenges and refine the oversight of passenger flows at high-speed rail terminals. The findings hold noteworthy theoretical import and portend promising practical applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Robot Torque Prediction Method Based on CNN-TCN Model

A Collaborative Robot Torque Prediction Method Based on CNN-...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Lina Tong Decheng Cui Chen Wang Liang Peng School of Mechanical Electronic and Information Engineering China University of Mining and Technology Beijing Beijing China State Key Laboratory of Management and Control for Complex Systems (SKLMCCS) Institute of Automation Chinese Academy of Science Beijing China

The traditional dynamical models show lower accuracy when predicting joint movement, and should be compensated. This paper proposed a model combined with the convolutional network(CNN) and temporal convolutional network(TCN) to compensate for the joint torque prediction values that are calculated from the sensing information. The experiments on the Cooperative Universal Robotic Assistant 6 DoF(CURA6) open dataset, including multi-load and multi-velocity, showed the prediction error can be reduced by 20% compared to other network models. Since there are many kinds of joint movement information, the input data form of the deep learning model should be improved. Thus, the kinetic linearization model is proposed to modify the input of sensing data. According to the different motion types of the CURA6 dataset, comparative experiments were taken, and the mean absolute error was less than 6.8%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

引用

Frontiers of Information Technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong 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：