检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Biomimetics

作者： Jake Jie Hou Xinrui Wu Jiwei Shan Dun Li Hesheng Wang Department of Automation Shanghai Jiao Tong University China Shanghai Karlang Industrial Nantong Intelligent Technology Co. Ltd China Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9781665481106

SLAM is significant to autonomous mobile robots. In order to realize drift-free state estimation and provide accurate localization results for the subsequent navigation, we develop an optimization-based framework consisting of a high-frequency Inertial-Wheel Odometry(IWO), Visual-Inertial-Wheel Odometry(VIWO) and a global fusion module. To fuse the local state with the position provided by GNSS, we perform ternary edge in factor graph optimization to estimate the transformation between the local frame and ENU coordinate. Thanks to the tightly-coupled VIWO, the localization property of the odometry presents more robustness, and improve the accuracy of global fusion. A noise repropagation strategy is introduced to ensure the consistency of the IMU and wheel odometer. We evaluate the proposed system on public datasets and test it in real-world scenario. The experimental results show that our system achieves accurate pose estimation in outdoor environments.

关键词： Location awareness Global navigation satellite system Simultaneous localization and mapping Robot kinematics Wheels Robustness Sensors

来源：评论

学校读者我要写书评

暂无评论

A Retina-LGN-V1 Structure-like Spiking Neuron Network for Image Feature Extraction 21

A Retina-LGN-V1 Structure-like Spiking Neuron Network for Im...

引用

Proceedings of the 2021 5th International Conference on Video and Image Processing

作者： Sheng Ji Qijun Gu Ye Yuan Peng Zhao Tao Fang Hong Huo Xin Niu Department of Automation_School of Electronic Information and Electrical Engineering_Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Jiao Tong University China College of Computer Science and Technology on Parallel and Distributed Laboratory National University of Defense Technology China

ISBN: (纸本)9781450385893

SNNs have achieved great attention in recent years as they contain neurons more like those in the brain and use spikes to encode and transmit information efficiently among neurons with lower energy consumption. A Retina-LGN-V1 structure-like spiking neuron network (RLVSL-SNN) is proposed in this paper. It is inspired by the structure of mammalian primary visual pathway, and simulates different biological structures of Retina, LGN and V1. Noise reduction circuit and light adaptation circuit are also simulated for enhancing the robustness of its extracted features. RLVSL-SNN is a bio-plausible neuron network as it has firing rates of neurons in each layer that are similar to those of biological experiments. Besides, a full-connected SNN (FC SNN) is implemented following RLVSL-SNN for classification to evaluate the extracted features. The additive spiking timing dependent plasticity (STDP) learning rules and the ANN-to-SNN conversion method are utilized to train RLVSL-SNN and FC SNN, respectively. The experiments on MNIST dataset have verified that RLVSL-SNN is comparable to AlexNet for classification by features from spikes.

关键词： Additive Spiking Timing Dependent Plasticity Learning Primary Visual Pathway Image Classification Spiking Neural Network

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal-Rule-based Traffic Movement Status Interpretation at Intersections *

Spatial-Temporal-Rule-based Traffic Movement Status Interpre...

引用

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

作者： Hanyang Zhuang Liyang Gao Yeqiang Qian Chunxiang Wang Ming Yang University of Michigan – Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China Department of Automation Shanghai Jiao Tong University Shanghai Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

Traffic light is the most significant component of road transportation. Traffic lights control the traffic movement at intersections by allowing the movement of some lanes and forbidding that of the others to ensure safety and efficiency. It is important for intelligent vehicles to understand the meaning of traffic lights. Conventional research works on traffic light detection and tracking consider each light independently, so the occlusion of some lights may mislead the decision of the vehicle. Since all traffic lights at an intersection work together, it is more essential to understand the traffic movement status controlled by the traffic lights rather than the perception of a single light. Therefore, this paper proposes a spatial-temporal-rule-based framework to interpret the current traffic movement status and predict the next status. The spatial information, including position and class, is obtained by traffic light detection. The temporal information is perceived by the proposed topologic-feature-based tracking method. The rule information is recognized by combination of spatial and temporal information. A dual-view camera system consisting of a telephoto camera and a wide-angle camera is adopted to ensure long perception distance and wide coverage simultaneously. The successful tracking of traffic lights from 200 m to 10 m away provides enough data to recognize the phase-change rule, which leads to correct interpretation and prediction. A customized dataset was collected, and experiments were conducted to illustrate the capability of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recurrent Attentional Reinforcement Learning for Machinery Fault Diagnosis

SSRN

引用

SSRN 2024年

作者： Tang, Zhenhui Wang, Jingcheng Wu, Shunyu The Department of Automation The Key Laboratory of System Control and Information Processing Ministry of Education of China The Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University No.800 Dongchuan Road Shanghai200240 China The SJTU Sanya Yazhou Bay Institute of Deepsea Science and Technology Sanya572024 China The Autonomous Systems and Intelligent Control International Joint Research Center Xi’an Technological University Xi’an710021 China

Recognizing fault types of machinery system is a fundamental but challenging task in industrial application. Although remarkable progress has been attained by learning fault features and predicting the corresponded fault type with deep neural networks, the existing fault diagnosis pipelines usually learn non-discriminative information. Contextual sequence dependency between the localized time fragments is often ignored. To deal with these problem, a recurrent attention framework with reinforcement learning is proposed to find a series of informative features of local time fragments related to different faults in an iterative manner. Fault labels are further predicted on these time fragments. The proposed framework also explicitly models long-term dependencies among these attentional time fragments to capture historical fault information. Experiments on two typical machinery systems, bearing system and hydraulic system, show that the proposed framework achieves superior diagnosis performance and increases no computation burden on CPU. © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Federated Cubic Regularized Newton Learning with Sparsification-amplified Differential Privacy

arXiv

引用

arXiv 2024年

作者： Huo, Wei Liu, Changxin Ding, Kemi Johansson, Karl Henrik Shi, Ling Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China

This paper investigates the use of the cubic-regularized Newton method within a federated learning framework while addressing two major concerns that commonly arise in federated learning: privacy leakage and communication bottleneck. We introduce a federated learning algorithm called Differentially Private Federated Cubic Regularized Newton (DP-FCRN). By leveraging second-order techniques, our algorithm achieves lower iteration complexity compared to first-order methods. We also incorporate noise perturbation during local computations to ensure privacy. Furthermore, we employ sparsification in uplink transmission, which not only reduces the communication costs but also amplifies the privacy guarantee. Specifically, this approach reduces the necessary noise intensity without compromising privacy protection. We analyze the convergence properties of our algorithm and establish the privacy guarantee. Finally, we validate the effectiveness of the proposed algorithm through experiments on a benchmark dataset. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Passenger hazard perception based on EEG signals for highly automated driving vehicles

arXiv

引用

arXiv 2024年

作者： Yu Xuan Tan, Ashton Yang, Yingkai Zhang, Xiaofei Li, Bowen Gao, Xiaorong Zheng, Sifa Wang, Jianqiang Gu, Xinyu Li, Jun Zhao, Yang Zhang, Yuxin Stathaki, Tania Wang, Hong School of Vehicle and Mobility Tsinghua University Beijing100084 China Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom School of Medicine Tsinghua University Beijing100084 China School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China State Key Laboratory of Automotive Simulation and Control Jilin University Changchun130025 China

Enhancing the safety of autonomous vehicles is crucial, especially given recent accidents involving automated systems. As passengers in these vehicles, humans’ sensory perception and decision-making can be integrated with autonomous systems to improve safety. This study explores neural mechanisms in passenger-vehicle interactions, leading to the development of a Passenger Cognitive Model (PCM) and the Passenger EEG Decoding Strategy (PEDS). Central to PEDS is a novel Convolutional Recurrent Neural Network (CRNN) that captures spatial and temporal EEG data patterns. The CRNN, combined with stacking algorithms, achieves an accuracy of 85.0%±3.18%. Our findings highlight the predictive power of pre-event EEG data, enhancing the detection of hazardous scenarios and offering a network-driven framework for safer autonomous vehicles. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Vector Angular Spectrum Model for light travelling in scattering media

arXiv

引用

arXiv 2024年

作者： Liu, Kaige Zhang, Hengkang Liu, Zeqi Zhang, Bin Fu, Xing Yuan, Qiang Liu, Qiang Ministry of Education Beijing100084 China State Key Laboratory of Precision Measurement Technology and Instruments Department of Precision Instrument Tsinghua University Beijing100084 China Research Center of Laser Fusion China Academy of Engineering Physics Mianyang621900 China Beijing Institute of Control Engineering Beijing100190 China Beijing Institute of Electronic System Engineering Beijing100854 China

Strongly scattering media disrupt both the wavefront distribution and the polarization state of the incident light field. controlling and effectively utilizing depolarization effects are crucial for optical applications in highly scattering environments, such as imaging through dense fog. However, current simulation models have difficulty simulating the evolution of vector light fields within scattering media, posing challenges for studying vector light fields in strongly scattering environments. Here, we propose the Vector Angular Spectrum (VAS) model for simulating the propagation of vector light fields within scattering media. By introducing the angular spectrum distribution of vector light scattering and polarization conversion mechanisms, this model can simulate the depolarization effects of vector light propagating through strongly scattering media. The VAS model has also been used to investigate the focusing of vector scattered light through scattering media. Furthermore, the simulation results of the model have been validated through experiments. The proposed VAS model is expected to play a role in the theoretical research of vector scattered light and optical applications in strongly scattering environments. Copyright © 2024, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Modeling and control of a half Car Active Suspension system using Sliding Mode controller and Linear Quadratic Regulator controller

Modeling and Control of a half Car Active Suspension System ...

引用

Renewable Energy & Sustainability (ieCRES), International engineering Conference on

作者： Abdussalam Ali Ahmed Hisham.F. A. Ramadhan Mohamed El Malki Yasser Fathi Nassar Mechanical Engineering Department Bani Waleed University Bani Waleed Libya Control System Engineering College of Electronic Technology Bani Walid Libya Department of Physics Faculty of Sciences Mohammed First University Oujda Morocco Mechanical and Renewable Energy Eng. Dept. Wadi Alshatti University Brack Libya

This paper illustrates the use of two distinct control strategies. Namely, the Sliding Mode control (SMC) and a Linear Quadratic Regulator (LQR) controller to monitor and handle the suspension system vibrations that occurred. We used a half car suspension model with (4DOF). The necessary suspension performance attributes, such as ride comfort, suspension deflection and car handling require a comprehensive control system. Three components make up this control system, which is carried out using the MATLAB application: the controller, the suspension system model, and input signals (road profile and actuator force). A comparison of the half car active suspension system LQR and SMC controllers as well as the uncontrolled suspension system is presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Platoon-Based Distributed control for Automated Material Handling systems

Platoon-Based Distributed Control for Automated Material Han...

引用

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Alessandro Bozzi Jose-Fernando Jimenez Camilo Hernandez-Rodriguez Eliana-Maria Gonzalez-Neira Damien Trentesaux Department of Informatics Bioengineering Robotics and Systems Engineering (DIBRIS) University of Genova Italy Laboratory System and Materials for Mechatronics (SYMME) Université Savoie Mont Blanc Annecy France Industrial Engineering Department Pontificia Universidad Javeriana Bogota Columbia Laboratory of Industrial and Human Automation Control Mechanical Engineering and Computer Science (LAMIH) Université Polytechnique Hauts-de-France Valenciennes France

Smart manufacturing systems combine collaborative and autonomous control systems to provide optimal performance and respond to volatile demands. A key component of smart manufacturing is material management, as raw materials, work-in-progress, and finished products must be transported to the right location at the right time. However, during the production phase, it is imperative to establish an optimal traffic control scheme in order to avoid congestion and optimize material flow. This paper proposes a platooning-based control procedure implemented in a virtual agent-based manufacturing environment to increase the material flow efficiency on a manufacturing shop floor. An analysis of the production makespan and an indicator of the level of congestion in the material handling system was conducted in order to determine productivity improvements. An agent-based simulation is used to test the effectiveness of the novel platooning approach versus a traditional basic approach. A multivariate analysis of variance (MANOVA) reveals that the inclusion of a platoon-based procedure improves production performance and reduces congestion risks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Review of Integrated Optimization Method of Batch Planning and Scheduling for Steelmaking-Continuous Casting-Hot Rolling Production Under Uncertain Environment Based on Lagrangian Relaxation Framework

引用

Complex system Modeling and Simulation 2024年第4期4卷 387-401页

作者： Liangliang Sun Xirang Hao Yunpeng Li Jinghan Xue Natalia M.Matsveichuk Yuri N.Sotskov Qichun Zhang School of Control Engineering Northeastern University at QinhuangdaoQinhuangdao 066004China Sydney Smart Technology College Northeastern UniversityQinhuangdao 066004China Department of Production Management Automation System Belarusian Stage Agrarian Technical UniversityMinsk 220012Belarus United Institute of Informatics Provlems National Academy of Sciences of BelarusMinsk 220012Belarus Buckinghamshire New University High Wycombe HP13UK

The integrated process of steelmaking,continuous casting,and hot rolling(SM-CC-HR)covers the entire process from refining liquid steel to manufacturing semi-finished steel *** batch planning and scheduling are connected to the production contract plan at the upper level and the production process contro at the lower level,which is the key to achieving eficient and full process steel *** planning determines the location of the slabs to be produced in the converter,ladle,continuous casting machine,and hot roling mill by combining production orders,process standards,and production *** scheduling,guided by batch planning,combines production performance indicators,process constraints,etc..to determine the equipment selection and start-stop times of speciic production units at each *** synergy of the two aims to optimize production profitability,energy consumption,efficiency,etc.,through rational decisions,ensuring the efficiency and flexibility of the steel production ***,due to the traditional"divide and conguer"management mode and the influence of many uncertain factors,it is dificult to ensure the flexible balance between the demand and capacity,as well as a reasonable matching of logistics and resources among the production processes that operate *** the uncertain environment and the integration of SM-CC-HR,this paper summarizes the research status of previous scholars from three aspects:mathematical modeling,model optimization,and algorithm optimization based on the Lagrangian *** discusses the research status of batch planning and scheduling methods for SM-CC HR production based on the Lagrangian relaxation framework,analyzes the problems existing in current research,and points out the main research directions and important research contents in the future,in order to promote the research and application of batch planning and scheduling problems for SM-CC-HR under uncertain

关键词： steelmaking-continuous castinghot rolling batch planning production scheduling uncertain Lagrangian relaxation

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：