检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yi, Xinlei Li, Xiuxian Yang, Tao Xie, Lihua Hong, Yiguang Chai, Tianyou Johansson, Karl H. Lab for Information & Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States Department of Control Science and Engineering College of Electronics and Information Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper considers distributed online convex optimization with adversarial constraints. In this setting, a network of agents makes decisions at each round, and then only a portion of the loss function and a coordinate block of the constraint function are privately revealed to each agent. The loss and constraint functions are convex and can vary arbitrarily across rounds. The agents collaborate to minimize network regret and cumulative constraint violation. A novel distributed online algorithm is proposed and it achieves an O(T max{c,1−c}) network regret bound and an O(T 1−c/2) network cumulative constraint violation bound, where T is the number of rounds and c ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds (i.e, there is a point that strictly satisfies the inequality constraints), the network cumulative constraint violation bound is reduced to O(T 1−c). Moreover, if the loss functions are strongly convex, then the network regret bound is reduced to O(log(T)), and the network cumulative constraint violation bound is reduced to O(√log(T)T) and O(log(T)) without and with Slater’s condition, respectively. To the best of our knowledge, this paper is the first to achieve reduced (network) cumulative constraint violation bounds for (distributed) online convex optimization with adversarial constraints under Slater’s condition. Finally, the theoretical results are verified through numerical simulations. Copyright © 2023, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

EDOLAB: An Open-Source Platform for Education and Experimentation with Evolutionary Dynamic Optimization Algorithms

arXiv

引用

arXiv 2023年

作者： Peng, Mai Yazdani, Delaram She, Zeneng Yazdani, Danial Luo, Wenjian Li, Changhe Branke, Juergen Nguyen, Trung Thanh Gandomi, Amir H. Yang, Shengxiang Jin, Yaochu Yao, Xin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Research Institute Faculty of Engineering and Technology Liverpool John Moores University United Kingdom School of Computer Science and Technology Harbin Institute of Technology China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and Technology Harbin Institute of Technology Peng Cheng Laboratory China School of Artificial Intelligence Anhui University of Sciences & Technology China Information Systems Management and Analytics in Warwick Business School University of Warwick United Kingdom Faculty of Engineering & Information Technology University of Technology Sydney Australia Obuda University Hungary School of Computer Science and Informatics De Montfort University United Kingdom Department of Artificial Intelligence School of Engineering Westlake University China School of Computer Science University of Birmingham United Kingdom

Many real-world optimization problems exhibit dynamic characteristics, posing significant challenges for traditional optimization techniques. Evolutionary Dynamic Optimization Algorithms (EDOAs) are designed to address these challenges effectively. However, in existing literature, the reported results for a given EDOA can vary significantly. This inconsistency often arises because the source codes for many EDOAs, which are typically complex, have not been made publicly available, leading to error-prone re-implementations. To support researchers in conducting experiments and comparing their algorithms with various EDOAs, we have developed an open-source MATLAB platform called the Evolutionary Dynamic Optimization laboratory (EDOLAB). This platform not only facilitates research but also includes an educational module designed for instructional purposes. The education module allows users to observe: a) a 2-dimensional problem space and its morphological changes following each environmental change, b) the behaviors of individuals over time, and c) how the EDOA responds to environmental changes and tracks the moving optimum. The current version of EDOLAB features 25 EDOAs and four fully parametric benchmark generators. © 2023, CC BY-NC-SA.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Vehicle control in Highway Traffic by Using Reinforcement Learning and Microscopic Traffic Simulation 18

Vehicle Control in Highway Traffic by Using Reinforcement Le...

引用

18th IEEE International Symposium on Intelligent systems and Informatics, SISY 2020

作者： Szoke, Laszlo Aradi, Szilard Becsi, Tamas Gaspar, Peter Budapest University of Technology and Economics Department of Control for Transportation and Vehicle Systems Megyetem rkp. 3 BudapestH-1111 Hungary Computer and Automation Research Institute Hungarian Academy of Sciences Systems and Control Laboratory Kende u. 13-17 BudapestH-1111 Hungary

ISBN: (纸本)9781728173528

The paper presents a simple yet powerful and intelligent driver agent, designed to operate in a preset highway situation using Policy Gradient Reinforcement Learning (RL) agent. The goal is to navigate safely in dense highway traffic and proceed through the defined length with the shortest time possible. The algorithm uses a dense neural network as a function approximator for the agent with discrete action space on the control level, e.g., acceleration and steering. The developed simulation environment uses the open-source traffic simulator called Simulation of Urban MObility (SUMO), integrated with an interface, to interact with the agent in real-time. With this tool, numerous driving and highway situations can be created and fed to the agent from which it can learn. The environment opens the opportunity to randomize and customize the other road users' behavior. Thus the experience can be more diverse, and thus the representation becomes more general. The article describes the modeling environment, the details on the learning agent, and the rewarding scheme. After evaluating the experiences gained from the training, some ideas for optimization and further development goals are also proposed. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An IoT Edge Computing System Architecture and its Application

An IoT Edge Computing System Architecture and its Applicatio...

引用

2020 IEEE International Conference on Networking, Sensing and control, ICNSC 2020

作者： Chen, Shichao Li, Qijie Zhang, Hua Zhu, Fenghua Xiong, Gang Tang, Ying Macau University of Science and Technology State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences China Beijing University of Technology State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Aerospace Smart Manufacturing Technology Development Co. Ltd Platform Research and Development Department Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Engineering Research Center of Intelligent Systems and Technology Institute of Automation Cloud Computing Center Chinese Academy of Sciences Beijing China Rowan University Department of Electrical and Computer Engineering GlassboroNJ United States Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China

ISBN: (纸本)9781728168531

As the number of devices connected to the Internet of things (IoT) surges, the amount of data explodes. Therefore it not only increases the bandwidth load of data transmission but also aggravates the computing and storage load of a cloud platform. At the same time, the traditional computing paradigm centered on cloud computing cannot meet the real-time requirements in many application scenarios. The emergence of edge computing can solve the problems of realtime data processing and network bandwidth occupation in the current IoT scene. In this paper, according to the characteristics of IoT, such as fragmented data, heterogeneous network, and limited energy consumption, the architecture of an IoT edge computing system is constructed to suit better an IoT scene. In addition, the application of edge computing key technologies such as virtualization, edge intelligence, computing offload, collaborative scheduling and micro-services in resource-constrained IoT scenarios is analyzed in detail. Finally, the functions and application of energy consumption monitoring and optimization to a central air-conditioning system are analyzed and summarized, which is a typical application of edge computing in the context of the IoT. © 2020 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Multimodal Information-Based Broad and Deep Learning Model for Emotion Understanding

Multimodal Information-Based Broad and Deep Learning Model f...

引用

第40届中国控制会议

作者： Min Li Luefeng Chen Min Wu Witold Pedrycz Kaoru Hirota School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Department of Electrical and Computer Engineering University of Alberta Tokyo Institute of Technology

Multimodal information-based broad and deep learning model（MIBDL） for emotion understanding is proposed, in which facial expression and body gesture are used to achieve emotional states recognition for emotion understanding. It aims to understand coexistence multimodal information in human-robot interaction by using different processing methods of deep network and broad network, which obtains the features of depth and width dimensions. Moreover, random mapping in the initial broad learning network could cause information loss and its shallow layer network is difficult to cope with complex tasks. To address this problem, we use principal component analysis to generate the nodes of the broad learning, and the stacked broad learning network is adapted to make it easier for the existing broad learning networks to cope with complex tasks by creating deep variations of the existing network. To verify the effectiveness of the proposal, experiments completed on benchmark database of spontaneous emotion expressions are developed, and experimental results show that the proposal outperforms the state-of-theart methods. According to the simulation experiments on the FABO database, by using the proposed method, the multimodal recognition rate is 17,54%, 1.24%, and 0.23% higher than those of the temporal normalized motion and appearance features（TN）,the multi-channel CNN（MCCNN）, and the hierarchical classification fusion strategy（HCFS）, respectively.

关键词： Convolution neural network broad learning emotion understanding facial expression body gesture

来源：评论

学校读者我要写书评

暂无评论

Structural reduction of CRNs with linear sub-CRNs

引用

IFAC-PapersOnLine 2021年第14期54卷 149-154页

作者： Katalin M. Hangos György Lipták Gábor Szederkényi Systems and Control Laboratory Computer and Automation Research Institute P.O. Box 63 H-1518 Budapest Hungary Department of Electrical Engineering and Information Systems University of Pannonia Veszprém Hungary Faculty of Information Technology and Bionics Péter Pázmány Catholic University Budapest Hungary

A novel systems theory-based structural reduction method is proposed in this paper that can be applied to chemical reaction networks (CRNs) including subsystems consisting of linear reactions, i.e. a linear sub-CRN. The reduced model is a delayed CRN with distributed delays having less complexes (monomials) and reactions than the original model. The reduction is based on the fact that the input/output response of a linear sub-CNR can be seen as a time-delayed input to output relationship, therefore linear sub-CNRs can be interpreted as reactions with distributed delay from their input to their output complexes. The practically important example of a kinetic model describing the spread of the COVID-19 epidemic is used as a case study to illustrate the basic concepts and the computation method.

关键词： Delay Model reduction Chemical Reaction Networks COVID

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

IEEE International Conference on Industrial Informatics (INDIN)

作者： Weipeng Cao Xuyang Yao Zhiwu Xu Yinghui Pan Yixuan Sun Dachuan Li Bohua Qiu Muheng Wei Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model's capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods.

关键词： Visualization Adaptation models Semantics Zero shot learning Neural networks Termination of employment Transformers Market research Sun Optimization

来源：评论

学校读者我要写书评

暂无评论

Parallel Planning:A New Motion Planning Framework for Autonomous Driving

引用

IEEE/CAA Journal of Automatica Sinica 2019年第1期6卷 236-246页

作者： Long Chen Xuemin Hu Wei Tian Hong Wang Dongpu Cao Fei-Yue Wang IEEE School of Data and Computer Science Sun Yat-sen University the School of Computer Science and Information Engineering Hubei University Institute of Measurement and Control Systems Karlsruhe Institute of Technology Department of Mechanical and Mechatronics Engineering University of Waterloo the State Key Laboratory of Management and Control for Complex Systems.Institute of Automation Chinese Academy of Sciences the Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology

Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human ***, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.

关键词： Autonomous driving artificial traffic scene deep learning emergencies motion planning parallel planning

来源：评论

学校读者我要写书评

暂无评论

S4TP: Social-Suitable and Safety-Sensitive Trajectory Planning for Autonomous Vehicles

arXiv

引用

arXiv 2024年

作者： Wang, Xiao Tang, Ke Dai, Xingyuan Xu, Jintao Du, Quancheng Ai, Rui Wang, Yuxiao Gu, Weihao Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei230031 China Haomo Technology Co. Ltd. Beijing100192 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Qingdao266114 China The School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S4TP) framework. Specifically, S4TP integrates the Social-Aware Trajectory Prediction (SATP) and Social-Aware Driving Risk Field (SADRF) modules. SATP utilizes Transformers to effectively encode the driving scene and incorporates an AV’s planned trajectory during the prediction decoding process. SADRF assesses the expected surrounding risk degrees during AVs-HDVs interactions, each with different social characteristics, visualized as two-dimensional heat maps centered on the AV. SADRF models the driving intentions of the surrounding HDVs and predicts trajectories based on the representation of vehicular interactions. S4TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs’ trajectories as input. With the integration of SADRF, S4TP executes real-time online optimization of the planned trajectory of AV within low-risk regions, thus improving the safety and the interpretability of the planned trajectory. We have conducted comprehensive tests of the proposed method using the SMARTS simulator. Experimental results in complex social scenarios, such as unprotected left-turn intersections, merging, cruising, and overtaking, validate the superiority of our proposed S4TP in terms of safety and rationality. S4TP achieves a pass rate of 100% across all scenarios, surpassing the current state-of-the-art methods Fanta of 98.25% and Predictive-Decision of 94.75%. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Exact Differentiator with Lipschitz Continuous Output and Optimal Worst-Case Accuracy Under Bounded Noise

Exact Differentiator with Lipschitz Continuous Output and Op...

引用

IEEE Conference on Decision and control

作者： Rodrigo Aldana-López Richard Seeber Hernan Haimovich David Gómez-Gutiérrez Department of Computer Science and Systems Engineering University of Zaragoza Zaragoza Spain Christian Doppler Laboratory for Model Based Control of Complex Test Bed Systems Institute of Automation and Control Graz University of Technology Graz Austria Centro Internacional Franco-Argentino de Ciencias de la Información y de Sistemas (CIFASIS) CONICET-UNR Rosario Argentina Intel Tecnología de México Intel Labs Intelligent Systems Research Lab Jalisco Mexico Tecnológico Nacional de México Instituto Tecnológico José Mario Molina Pasquel y Henríquez Unidad Académica Zapopan Jalisco Mexico

The online differentiation of a signal contaminated with bounded noise is addressed. A differentiator is developed that generates a Lipschitz continuous output, is exact in the absence of noise, and provides the optimal worst-case accuracy among all possible exact differentiators when noise is present. This combination of features is not shared by any previously existing differentiator. Tuning of the developed differentiator is very simple, requiring only the knowledge of a bound for the second-order derivative of the signal. The approach consists in regularizing the possibly highly noisy output of a recently introduced linear adaptive robust exact differentiator and feeding it to a first-order sliding-mode filter designed to maintain optimal accuracy. The proposed regularization and filtering of this output allows trading the speed with which exactness is obtained for the feature of a Lipschitz continuous, hence less noisy, output. An illustrative example is provided to highlight the features of the developed differentiator.

关键词：

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：