检索结果-内蒙古大学图书馆

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Chen, Yizhu Du, Xiaoming Wang, Xiao Zhang, Jun Jason Wang, Fei-Yue Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China School of Economics and Management University of Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China School of Electrical Engineering and Automation Wuhan University Wuhan China

ISBN: (纸本)9781665433372

The federated ecology provides a new paradigm for breaking the isolated data island problem and fully activating the potential of big data and artificial intelligence, especially in multi-client collaboration tasks. Participant selection strategy in multi-client collaboration is the main limitation for increasing the convergence speed and lowing the communication costs. However, in the face of the unbalanced and non-IID data distributions, the performance of federated optimization algorithms will also decrease. To solve the above problems, we propose an adaptive federated control strategy for participant selection in multi-client collaboration based on the Mann-Kendall test, named FedMK. By adaptively selecting weak participants for training rather than random selection, FedMK can speed up model convergence and reduce communication costs. Experiment results show that our method outperforms the baseline method in non-IID scenarios, and the number of communication rounds on CIFAR-10 and synthetic datasets reduced by more than 15% and 10 %, 9 respectively. © 2021 IEEE.

关键词： Stream flow

来源：评论

学校读者我要写书评

暂无评论

Fusionplanner: A Multi-Task Motion Planner for Mining Trucks Using Multisensor Fusion Method

SSRN

引用

SSRN 2023年

作者： Teng, Siyu Chen, Long Li, Luxi Li, Yuchen Hu, Xuein Li, Lingxi Ai, Yunfeng Department of Computer Science Hong Kong Baptist University Hong Kong The School of Artificial Intelligence Hubei University Wuhan China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China Waytous Inc. Haidian Distinct Beijing China Indianapolis United States School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

In recent years, significant achievements have been made in motion planning for intelligent vehicles. However, as a typical unstructured environment, open-pit mining attracts limited attention due to its complex operational conditions and adverse environmental factors. A comprehensive paradigm for unmanned transportation in open-pit mines is proposed in this research, including a simulation platform, a testing benchmark, and a trustworthy and robust motion planner. Firstly, we introduce the Parallel Mining Simulator (PMS), a high-fidelity simulator specifically designed for open-pit mining scenarios. PMS enables to management and control of open-pit mine transportation from both the single-truck control and multi-truck scheduling perspectives. Then, we develop a novel benchmark called MiningNav, which offers three validation approaches suitable for transportation roads. The purpose of MiningNav is to evaluate the trustworthiness and robustness of algorithms in open-pit mines. Finally, we propose the first multi-task motion planning algorithm, called FusionPlanner, for the mining truck by the multisensor fusion method to adapt both lateral and longitudinal control tasks for unmanned transportation. We validate the performance of our planner using MiningNav in PMS, and empirical results demonstrate a significant reduction in the number of collisions and takeovers of FusionPlanner, thereby improving overall trustworthiness and robustness. © 2023, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Development and path planning of a novel unmanned surface vehicle system and its application to exploitation of Qarhan Salt Lake

引用

Science China(Information Sciences) 2019年第8期62卷 195-197页

作者： Zhibin XUE Jincun LIU Zhengxing WU Sheng DU Shihan KONG Junzhi YU College of Chemical Engineering Qinghai University State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences

Qarhan Salt Lake is rich in mineral resources, such as sodium chloride, potassium, and magnesium [1].At present, liquid mine exploiting is the main exploitation form for the Qarhan Salt Lake. Salt mining ships with mining equipments are widely used to exploit carnallite which is located at the bottom of pools. Conventionally, workmen utilize rude ferric sampler to collect carnallite samples

关键词： USV simulation Development and path planning of a novel unmanned surface vehicle system and its application to exploitation of Qarhan Salt Lake

来源：评论

学校读者我要写书评

暂无评论

The Emerging Intelligent Vehicles and Intelligent Vehicle Carriers Collaborative systems

The Emerging Intelligent Vehicles and Intelligent Vehicle Ca...

引用

IEEE Symposium on Intelligent Vehicle

作者： Zhipeng Shen Chao Huang Hailong Huang Yutong Wang Fei-Yue Wang Abbas Jamalipour Duc Truong Pham Ljubo Vlacic Andrey V. Savkin Department of Aeronautical and Aviation Engineering the Hong Kong Polytechnic University Hong Kong Department of Industrial and Systems Engineering the Hong Kong Polytechnic University Hong Kong State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Engineering Macau University of Science and Technology Macau China School of Electrical and Information Engineering University of Sydney Sydney Australia Department of Mechanical Engineering University of Birmingham Birmingham UK Institute of Intelligent & Integrated Systems and the School of Engineering and Built Environment Griffith University Brisbane Australia School of Electrical Engineering and Telecommunications University of New South Wales Sydney Australia

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In this paper, we propose the innovative use of Intelligent Vehicle Carriers (IVCs) as a key solution to address the energy constraints of small-scale unmanned Intelligent Vehicles (IVs). IVCs function as both transporters and charging stations, significantly boosting the operational range and efficiency of IVs. Our research delves into the IV-IVC collaborative framework, highlighting the existing challenges, exploring potential solutions, and examining a range of applications. This study offers a visionary approach to revolutionizing intelligent transportation systems by leveraging the synergistic relationship between IVs and IVCs.

关键词： Intelligent vehicles Collaboration Charging stations Boosting

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Benchmark for Autonomous Driving in Intersection Scenarios

A Reinforcement Learning Benchmark for Autonomous Driving in...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Yuqi Liu Qichao Zhang Dongbin Zhao The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781728190495

In recent years, control under urban intersection scenarios has become an emerging research topic. In such scenarios, the autonomous vehicle confronts complicated situations since it must deal with the interaction with social vehicles timely while obeying the traffic rules. Generally, the autonomous vehicle is supposed to avoid collisions while pursuing better efficiency. The existing work fails to provide a framework that emphasizes the integrity of the scenarios while deploying and testing reinforcement learning(RL) methods. Specifically, we propose a benchmark for training and testing RL-based autonomous driving agents in complex intersection scenarios, which is called RL-CIS. Then, a set of baselines consisting various algorithms are deployed. The test benchmark and baselines provide a fair and comprehensive training and testing platform for the study of RL for autonomous driving in the intersection scenario, advancing RL-based methods for autonomous driving control. The code of our proposed framework can be found at https://***/liuyufi123/complexUrbanScenarios.

关键词： Training Codes Stochastic processes Reinforcement learning Benchmark testing Sampling methods Concrete

来源：评论

学校读者我要写书评

暂无评论

A reinforcement learning benchmark for autonomous driving in intersection scenarios

arXiv

引用

arXiv 2021年

作者： Liu, Yuqi Zhang, Qichao Zhao, Dongbin The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

In recent years, control under urban intersection scenarios becomes an emerging research topic. In such scenarios, the autonomous vehicle confronts complicated situations since it must deal with the interaction with social vehicles timely while obeying the traffic rules. Generally, the autonomous vehicle is supposed to avoid collisions while pursuing better efficiency. The existing work fails to provide a framework that emphasizes the integrity of the scenarios while being able to deploy and test reinforcement learning(RL) methods. Specifically, we propose a benchmark for training and testing RL-based autonomous driving agents in complex intersection scenarios, which is called RL-CIS. Then, a set of baselines are deployed consists of various algorithms. The test benchmark and baselines are to provide a fair and comprehensive training and testing platform for the study of RL for autonomous driving in the intersection scenario, advancing the progress of RL-based methods for intersection autonomous driving control. The code of our proposed framework can be found at https://***/liuyuqi123/complexUrbanScenarios. Copyright © 2021, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition

A Prototype-Based Generalized Zero-Shot Learning Framework f...

引用

International Conference on Pattern Recognition

作者： Jinting Wu Yujia Zhang Xiaoguang Zhao School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

Hand gesture recognition plays a significant role in human-computer interaction for understanding various human gestures and their intent. However, most prior works can only recognize gestures of limited labeled classes and fail to adapt to new categories. The task of Generalized Zero-Shot Learning (GZSL) for hand gesture recognition aims to address the above issue by leveraging semantic representations and detecting both seen and unseen class samples. In this paper, we propose an end-to-end prototype-based GZSL framework for hand gesture recognition which consists of two branches. The first branch is a prototype-based detector that learns gesture representations and determines whether an input sample belongs to a seen or unseen category. The second branch is a zero-shot label predictor which takes the features of unseen classes as input and outputs predictions through a learned mapping mechanism between the feature and the semantic space. We further establish a hand gesture dataset that specifically targets this GZSL task, and comprehensive experiments on this dataset demonstrate the effectiveness of our proposed approach on recognizing both seen and unseen gestures.

关键词： Human computer interaction Target recognition Semantics Prototypes Human-robot interaction Gesture recognition Detectors

来源：评论

学校读者我要写书评

暂无评论

Study on the COVID-19 epidemic in China's Mainland between November 2022 and January 2023,with prediction of its tendency

引用

Journal of Biosafety and Biosecurity 2023年第1期5卷 39-44页

作者： Yao Bai Zhihang Peng Fengying Wei Zhen Jin Jinjie Wang Ximing Xu Xinyan Zhang Jun Xu Zixiong Ren Bulai Lu Zhaojun Wang Jianguo Xu Senzhong Huang Xi’an Center for Disease Control and Prevention Xi’an 710054ShaanxiChina Department of Biostatistics School of Public HealthNanjing Medical UniversityNanjing 211166JiangsuChina School of Mathematics and Statistics Fuzhou UniversityFuzhou 350116FujianChina Complex Systems Research Center Key Discipline of Computer Science and Technology of“Double-First-Class”Project of Shanxi ProvinceShanxi UniversityTaiyuan 030006ShanxiChina Nankai Institute of Economics Binhai Development InstituteNankai UniversityTianjin 300071China Children’s Hospital of Chongqing Medical University Chongqing 400010China Jinzhou Center for Disease Control and Prevention Jinzhou 121000LiaoningChina School of Statistics and Data Science Nankai UniversityTianjin 300071China Suzhou Center for Disease Control and Prevention Suzhou 215004JiangsuChina State Key Laboratory of Communicable Disease Prevention and Control National Institute for Communicable Disease Control and PreventionChinese Center for Disease Control and PreventionBeijing 102206China Institute of Public Health Nankai UniversityTianjin 300071China School of Statistics and Data Science ZhiYing Research Center for Health DataNankai UniversityTianjin 300071China

The prediction system EpiSIX was used to study the COVID-19 epidemic in China's Mainland between November 2022 and January 2023,based on reported data from December 9,2022,to January 30,2023,released by The Chinese Center for Disease control and Prevention on February 1,*** kinds of reported data were used for model fitting:the daily numbers of positive nucleic acid tests and deaths,and the daily number of hospital beds taken by COVID-19 *** was estimated that the overall infection rate was 87.54%and the overall case fatality rate was 0.078%–0.116%(median 0.100%).Assuming that a new COVID-19 epidemic outbreak would start in March or April of 2023,induced by a slightly more infectious mutant strain,we predicted a possible large rebound between September and October 2023,with a peak demand of between 800,000 and 900,000 inpatient *** no such new outbreak was induced by other variants,then the current COVID-19 epidemic course in China's Mainland would remain under control until the end of ***,it is suggested that the necessary medical resources be prepared to manage possible COVID-19 epidemic emergencies in the near future,especially for the period between September and October 2023.

关键词： COVID-19 Epidemic Infection rate Case fatality rate Prediction

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs 28

Knowledge-Enhanced Natural Language Inference Based on Knowl...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Wang, Zikang Li, Linjing Zeng, Daniel State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Shenzhen China

ISBN: (纸本)9781952148279

Natural Language Inference (NLI) is a vital task in natural language processing. It aims to identify the logical relationship between two sentences. Most of the existing approaches make such inference based on semantic knowledge obtained through training corpus. The adoption of background knowledge is rarely seen or limited to a few specific types. In this paper, we propose a novel Knowledge Graph-enhanced NLI (KGNLI) model to leverage the usage of background knowledge stored in knowledge graphs in the field of NLI. KGNLI model consists of three components: a semantic-relation representation module, a knowledge-relation representation module, and a label prediction module. Different from previous methods, various kinds of background knowledge can be flexibly combined in the proposed KGNLI model. Experiments on four benchmarks, SNLI, MultiNLI, SciTail, and BNLI, validate the effectiveness of our model. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

MixedFusion: 6D Object Pose Estimation from Decoupled RGB-Depth Features

MixedFusion: 6D Object Pose Estimation from Decoupled RGB-De...

引用

International Conference on Pattern Recognition

作者： Hangtao Feng Lu Zhang Xu Yang Zhiyong Liu The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences

Estimating the 6D pose of objects is an important process for intelligent systems to achieve interaction with the real-world. As the RGB-D sensors become more accessible, the fusion-based methods have prevailed, since the point clouds provide complementary geometric information with RGB values. However, due to the difference in feature space between color image and depth image, the network structures that directly perform point-to-point matching fusion do not effectively fuse the features of the two. In this paper, we propose a simple but effective approach, named MixedFusion. Different from the prior works, we argue that the spatial correspondence of color and point clouds could be decoupled and reconnected, thus enabling a more flexible fusion scheme. By performing the proposed method, more informative points can be mixed and fused with rich color features. Extensive experiments are conducted on the challenging LineMod and YCB-Video datasets, which shows that our method significantly boosts the performance without introducing extra overheads. Furthermore, when the minimum tolerance of metric narrows, the proposed approach performs better for the high-precision demands.

关键词： Measurement Three-dimensional displays Image color analysis Fuses Pose estimation Color Pattern recognition

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：