检索结果-内蒙古大学图书馆

Deep Reinforcement Learning Enabled Decision-Making for Autonomous Driving at Intersections

Automotive Innovation 2020年第4期3卷 374-385页

作者： Guofa Li Shenglong Li Shen Li Yechen Qin Dongpu Cao Xingda Qu Bo Cheng Institute of Human Factors and Ergonomics College of Mechatronics and Control EngineeringShenzhen UniversityShenzhen 518060China Department of Mechanical and Mechatronics Engineering University of WaterlooWaterlooON N2L 3G1Canada Department of Civil and Environmental Engineering University of Wisconsin-MadisonMadisonWI 53706USA School of Mechanical Engineering Beijing Institute of TechnologyBeijing 100081China State Key Laboratory of Automotive Safety and Energy School of Vehicle and MobilityTsinghua UniversityBeijing 100084China

Road intersection is one of the most complex and accident-prone traffic scenarios,so it’s challenging for autonomous vehicles(AVs)to make safe and efficient decisions at the *** of the related studies focus on the solution to a single scenario or only guarantee safety without considering driving *** address these problems,this study proposed a deep reinforcement learning enabled decision-making framework for AVs to drive through intersections automatically,safely and *** mapping relationship between traffic images and vehicle operations was obtained by an end-to-end decision-making framework established by convolutional neural *** images collected at two timesteps were used to calculate the relative velocity between *** decision process was employed to model the interaction between AVs and other vehicles,and the deep Q-network algorithm was utilized to obtain the optimal driving policy regarding safety and *** verify the effectiveness of the proposed decision-making framework,the top three accident-prone crossing path crash scenarios at intersections were simulated,when different initial vehicle states were adopted for better generalization *** results showed that the developed method could make AVs drive safely and efficiently through intersections in all of the tested scenarios.

关键词： Autonomous vehicles Driving safety and efficiency Intersection Decision-making Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multiple α sub-variants and anisotropic mechanical properties of an additively-manufactured Ti-6Al-4V alloy

引用

Journal of Materials Science & Technology 2021年第11期70卷 113-124页

作者： Yinling Zhang Zhuo Chen Shoujiang Qu Aihan Feng Guangbao Mi Jun Shen Xu Huang Daolun Chen School of Materials Science and Engineering Tongji UniversityShanghai 201804China Department of Mechanical and Industrial Engineering Ryerson UniversityTorontoOntario M5B 2K3Canada Aerospace Hiwing(Harbin)Titanium Industrial Co. Ltd.Harbin High Tech ZoneHarbin 150028China Shanghai Key Lab.of D&A for Metal-Functional Materials School of Materials Science&EngineeringTongji UniversityShanghai 201804China Aviation Key Laboratory of Science and Technology on Advanced Titanium Alloys AECC Beijing Institute of Aeronautical MaterialsBeijing 100095China College of Mechatronics and Control Engineering Shenzhen UniversityShenzhen 518060China

Additive manu facturing(AM)is a promising material processing method which gains significant momentum in the aerospace and biomedical ***,the anisotropy in the mechanical properties of additively-manufactured materials is still poorly *** study was aimed at elucidating crystallographic feature-anisotropy-mechanical property relationship for a Ti-6Al-4V alloy manufactured via selective electron beam melting(SEBM).Abundantαlamellae with six variants were present inside the columnar prior-βgrains with a<100>fiber texture duringβ→αphase *** sixαvariants followed the Burgers orientation relationship of{110}_(β)//{0001}_(α)and<1-11>_(β)//<11-20>_(α).Multiple sub-variants in eachαvariant were observed for the first *** anisotropy in the mechanical properties was mainly related to the relative amount of sixα*** the horizontally-oriented samples had a lower yield strength,they exhibited a higher ductility and longer fatigue life than the vertically-oriented *** softening occurred at higher strain amplitudes,and cyclic stabilization sustained at lower strain *** crack mainly initiated from the specimen surface at lower strain amplitudes,while multiple crack initiation tended to occur at higher strain *** propagation was characterized by fatigue striations along with some secondary cracks.

关键词： Titanium alloy 3D printing Deformation behavior Anisotropy Burgers orientation relationship

来源：评论

学校读者我要写书评

暂无评论

Global solution to sensor network localization: A non-convex potential game approach and its distributed implementation

arXiv

引用

arXiv 2024年

作者： Xu, Gehui Chen, Guanpu Hong, Yiguang Fidan, Baris Parisini, Thomas Johansson, Karl H. Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing100190 China The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden Department of Control Science and Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China The Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada The Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom The Department of Engineering and Architecture University of Trieste Trieste34127 Italy

Consider a sensor network consisting of both anchor and non-anchor nodes. We address the following sensor network localization (SNL) problem: given the physical locations of anchor nodes and relative measurements among all nodes, determine the locations of all non-anchor nodes. The solution to the SNL problem is challenging due to its inherent non-convexity. In this paper, the problem takes on the form of a multi-player nonconvex potential game in which canonical duality theory is used to define a complementary dual potential function. After showing the Nash equilibrium (NE) correspondent to the SNL solution, we provide a necessary and sufficient condition for a stationary point to coincide with the NE. An algorithm is proposed_ to reach the NE and shown to have convergence rate O(1/√k). With the aim of reducing the information exchange within a network, a distributed algorithm for NE seeking is implemented and its global convergence analysis is provided. Extensive simulations show the validity and effectiveness of the proposed approach to solve the SNL problem. Copyright © 2024, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Directed energy deposition powder stream modeling using a Gaussian beam ray representation

arXiv

引用

arXiv 2022年

作者： Martinez-Marchese, Alexander Klumpp, Maximilian Toyserkani, Ehsan Lab Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Institute of Analysis Dynamics and Modeling University of Stuttgart Pfaffenwaldring 57 Stuttgart70569 Germany

The powder stream from a side feed nozzle, or part of the powder stream in some coaxial nozzles, in a directed energy deposition via powder feeding (DED-PF) machine, can be modeled using a particle velocity field that has a constant downward component and a linearly increasing outward component, in proportion to the powder stream's center line distance [1]. However, when the powder stream is subject to a force field, it was found that the shape of the powder concentration function close to the center of the powder stream diverges considerably at high degrees of focusing. This discrepancy is reduced by modeling the powder stream based on the ray representation of a Gaussian beam [2]. Experimental results from high-speed camera particle tracking and numerically extrapolating the trajectories to the nozzle exit suggests that the statistics of the powder stream correspond to this model. A novel method to compute the particle concentration along the stream using an optical system analog, with the focusing force field modeled as the transfer matrix of a graded refractive index (GRIN) lens, is also demonstrated. This method is orders of magnitude faster than the corresponding Lagrangian simulation. Copyright © 2022, The Authors. All rights reserved.

关键词： Gaussian beams

来源：评论

学校读者我要写书评

暂无评论

Fabrication of Translucent Graded Dental Crown Using Zirconia-Yttrium Multi-Slurry Tape Casting 3d Printer

SSRN

引用

SSRN 2024年

作者： Romario, Yulius Shan Bhat, Chinmai Ramezani, Maziar Pasang, Tim Chen, Zhangwei Jiang, Cho-Pei Graduate Institute of Manufacturing Technology National Taipei University of Technology 1 Sec. 3 Zhongxiao E. Rd. Taipei10608 Taiwan High-value Biomaterials Research and Commercialization Center National Taipei University of Technology 1 Sec. 3 Zhongxiao E. Rd. Taipei10608 Taiwan Department of Mechanical Engineering Auckland University of Technology Auckland1010 New Zealand Department of Engineering Design Manufacturing and Management Systems Western Michigan University KalamazooMI4900-5200 United States Additive Manufacturing Institute Shenzhen University Shenzhen518060 China Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robotics College of Mechatronics and Control Engineering Shenzhen University Shenzhen518060 China Department of Mechanical Engineering National Taipei University of Technology Taiwan 1 Sec. 3 Zhongxiao E. Rd. Taipei10608 Taiwan

This paper aims to fabricate functionally graded dental crown using a multi-slurry tape casting additive manufacturing technology. The different luminescence of the dental crown was obtained with different composition of zirconia and yttria. Zirconia with tunable mechanical properties and translucency are obtained by adding 3, 3.5, 4, 4.5, and 5 mol% of yttrium oxide to zirconia powder. After obtaining the printable slurry with maximum solid loading, the green bodies are prepared using the in-house built high speed multi-ceramic tape casting technology. They are later sintered with two-stage sintering method. After the successful fabrication, the mechanical properties and translucency of the specimens were evaluated with Vickers hardness, three-point bending and translucency parameter tests. Finally, an FGM tooth crown with five photocurable slurries is proposed to demonstrate the translucent gradient effect of sintered part. The solid loading of 80% zirconia and 20% resin delivered samples without any surface cracks. The shrinkage ratio analysis showed that the sintered sample dimension was reduced by 20%, 20%, and 23% along X, Y, and Z directions. The samples fabricated with 3% yttrium oxide to zirconia delivered excellent hardness (1687 HV) and flexural strength (650.6 MPa). However, the relative luminescence increased with increasing the yttrium oxide for 3 – 5 mol%. With the optimized process parameters, the proposed dental crown is fabricated and analyzed for their shrinkage ratio, mechanical, and translucency properties. The study proposes the potential of fabricating customized dental crown with gradient translucent appearance. © 2024, The Authors. All rights reserved.

关键词： Zirconia

来源：评论

学校读者我要写书评

暂无评论

A Fair and Effective Approach to Managing Distributed Energy Resources Through Peer-to-Peer Energy Trading with Load Prioritization Among Smart Homes

SSRN

引用

SSRN 2023年

作者： Ahmed, Syed Adrees Huang, Qi Amin, Waqas Afzal, Muhammad Hussain, Fazal Haider, Muhammad Husnain 1Sichuan Provincial Key Lab of Power System Wide-Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Sichuan China Chengdu University of Technology China National University of Sciences and Technology Pakistan Superior University Pakistan School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Sichuan China

This paper proposes a novel approach to managing distributed energy resources (DERs) through peer-to-peer (P2P) energy trading among smart homes, incentivizing peers to trade surplus energy to maximize social welfare. The proposed day-ahead demand-side management (DSM) technique considers load prioritization based on users' needs. It utilizes an energy allocation method that incentivizes peers to buy energy at a reduced price and sell energy at a higher price. This method maximizes the time of energy traded to higher-priority loads, followed by lower-priority loads while considering user choice. The proposed method results in an average reduction in energy costs from 14.8% to 2.82% for all consumers and an average increase in revenues from 17.35% to 9.07% for all prosumers compared to the grid and previously proposed studies. The simulation results show significant economic benefits for all market participants, improved community self-sufficiency, and reduced dependence on the main grid. The proposed methodology provides an effective and fair solution for managing DERs through P2P energy trading by prioritizing the load in smart homes, which describes its potential to create a sustainable and efficient energy ecosystem. © 2023, The Authors. All rights reserved.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Forward Calculation Model for Utilization of Energy and Mass in Laser-Directed Energy Deposition

SSRN

引用

SSRN 2022年

作者： Ren, Ke Di, Yuelan Wang, Gang Wang, Liping Wang, Haidou Rong, Yiming School of Mechatronics Engineering Harbin Institute of Technology Harbin150001 China Department of Mechanical and Energy Engineering Southern University of Science and Technology Shenzhen518055 China Department of Equipment Support and Remanufacturing Army Academy of Armored Forces Beijing100072 China Beijing Key Lab of Precision/Ultra-precision Manufacturing Equipments and Control Department of Mechanical Engineering Tsinghua University Beijing100084 China

Precise control of energy and mass utilization is essential for the process design and optimization of powder-based laser-directed energy deposition (L-DED). However, fully comprehending the actual changes in the energy and the mass, which have complex nonlinear relationships with all inputs, is still challenging. In powder-based L-DED, the energy absorptivity is closely related to the powder catchment efficiency, owing to the effects of the laser incidence angle and the material properties. In this study, a forward calculation model was established for the utilization of energy and mass in powder-based L-DED without data regression of experimental measurements. Interactions between the laser, powders, and substrate were analyzed in detail in terms of three major effects: energy absorption of the substrate, powder catchment, and deposition shape variation. A secondary correction of the incidence angle was included in the geometric change of the deposited passes, and the boundary shift of the molten pool, which resulted from the melting point differences of the dissimilar deposited and substrate materials, was considered. The model prediction results matched the multipass deposition experimental results well. The average prediction error validated that the catchment efficiency did not exceed 5.2%. The scanning speed and the powder feed rate showed the largest effects on the energy absorptivity, which varied in the range of approximately 40%–65%. The developed model presents good universality and can be fundamental for understanding the forming mechanism, optimizing the process, and predicting the deposition quality of powder-based L-DED. © 2022, The Authors. All rights reserved.

关键词： Catchments

来源：评论

学校读者我要写书评

暂无评论

Fabrication grammars: bridging design and robotics to control emergent material expressions

引用

Construction Robotics 2021年第1期5卷 35-48页

作者： Iremnur Tokac Johan Philips Herman Bruyninckx Andrew Vande Moere Design Department of Architecture KU Leuven Leuven Belgium Robotics Automation and Mechatronics Department of Mechanical Engineering KU Leuven Leuven Belgium Flanders Make@KU Leuven Core Lab ROB Heverlee Belgium Control Systems Technology Department of Mechanical Engineering Technical University Eindhoven Eindhoven Netherlands

Designers physically engage with a material to experience how certain characteristics allow the fabrication of unique expressions. In digital fabrication, however, this improvisational negotiation is typically replaced by a virtual simulation that predicts how a material expression can be fabricated, limiting the resulting design language to algorithmic forms. In contrast, we believe that digital fabrication can also produce ‘emergent’ material expressions that are so confounded that they appear slightly differently even when being produced by identical operations. This paper argues that such expressions can be executed by a domain-driven feedback paradigm, which integrates a human-in-the-loop to encode the tacit fabrication knowledge that is generated by reviewing intermediate outcomes. We encode this tacit knowledge by fabrication grammars, rule-based descriptions that causally relate fabrication parameters to qualitative descriptions of material expressions. By documenting a set of Single Point Incremental Forming experiments, this paper demonstrates how emergent material expressions can be controlled by semantically meaningful fabrication grammars, which even can be combined towards purposeful design goals. We believe our findings might allow the digital fabrication of material expressions that appear to have been produced manually or naturally; and support the future sharing of tacit fabrication knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Player Potential Game Approach for Sensor Network Localization with Noisy Measurements

arXiv

引用

arXiv 2024年

作者： Xu, Gehui Chen, Guanpu Fidan, Baris Hong, Yiguang Qi, Hongsheng Parisini, Thomas Johansson, Karl H. The Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden The Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Department of Control Science and Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China The Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom The Department of Engineering and Architecture University of Trieste Trieste34127 Italy

Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multi-player non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies. Copyright © 2024, The Authors. All rights reserved.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Non-convex potential games for finding global solutions to sensor network localization

arXiv

引用

arXiv 2023年

作者： Xu, Gehui Chen, Guanpu Hong, Yiguang Fidan, Baris Parisini, Thomas Johansson, Karl H. Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden Department of Control Science and Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Engineering and Architecture University of Trieste Trieste34127 Italy

Sensor network localization (SNL) problems require determining the physical coordinates of all sensors in a network. This process relies on the global coordinates of anchors and the available measurements between non-anchor and anchor nodes. Attributed to the intrinsic non-convexity, obtaining a globally optimal solution to SNL is challenging, as well as implementing corresponding algorithms. In this paper, we formulate a non-convex multi-player potential game for a generic SNL problem to investigate the identification condition of the global Nash equilibrium (NE) therein, where the global NE represents the global solution of SNL. We employ canonical duality theory to transform the non-convex game into a complementary dual problem. Then we develop a conjugation-based algorithm to compute the stationary points of the complementary dual problem. On this basis, we show an identification condition of the global NE: the stationary point of the proposed algorithm satisfies a duality relation. Finally, simulation results are provided to validate the effectiveness of the theoretical results. Copyright © 2023, The Authors. All rights reserved.

关键词： Sensor networks

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：