检索结果-内蒙古大学图书馆

Towards Safe Autonomous Driving:Decision Making with Observation‑Robust Reinforcement Learning

automotive Innovation 2023年第4期6卷 509-520页

作者： Xiangkun He Chen Lv State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchunChina School of Mechanical and Aerospace Engineering Nanyang Technological University639798 NanyangSingapore

Most real-world situations involve unavoidable measurement noises or perception errors which result in unsafe decision making or even casualty in autonomous *** address these issues and further improve safety,automated driving is required to be capable of handling perception ***,this paper presents an observation-robust reinforcement learning against observational uncertainties to realize safe decision making for autonomous ***,an adversarial agent is trained online to generate optimal adversarial attacks on observations,which attempts to amplify the average variation distance on perturbed *** addition,an observation-robust actor-critic approach is developed to enable the agent to learn the optimal policies and ensure that the changes of the policies perturbed by optimal adversarial attacks remain within a certain ***,the safe decision making scheme is evaluated on a lane change task under complex highway traffic *** results show that the developed approach can ensure autonomous driving performance,as well as the policy robustness against adversarial attacks on observations.

关键词： Autonomous vehicle Robust reinforcement learning Safe decision making Adversarial attack

来源：评论

学校读者我要写书评

暂无评论

Analysis of China’s PM_(2.5)and ozone coordinated control strategy based on the observation data from 2015 to 2020

引用

Journal of Environmental Sciences 2024年第4期138卷 385-394页

作者： Liuwei Kong Mengdi Song Xin Li Ying Liu Sihua Lu Limin Zeng Yuanhang Zhang State Key Joint Laboratory of Environmental Simulation and Pollution Control College of Environmental Sciences and EngineeringPeking UniversityBeijing 100871China

The coordinated control of PM_(2.5)and ozone has become the strategic goal of national air pollution *** the gradual decline in PM_(2.5)concentration and the aggravation of ozone pollution,a better understanding of the coordinated control of PM_(2.5)and ozone is urgently ***,we collected and sorted air pollutant data for 337 cities from 2015 to 2020 to explore the characteristics of PM_(2.5)and ozone pollution based on China’s five major air pollution *** results show that it is necessary to continue to strengthen the emission reduction in PM_(2.5)and ozone precursors,and control NO_(x) and VOCs while promoting a dramatic emission reduction in PM_(2.5).The primary method of curbing ozone pollution is to strengthen the emission control of VOCs,with a long-term strategy of achieving substantial emission reductions in NO_(x),because VOCs and NO_(x) are also precursors to PM_(2.5);hence,their reductions also contribute to the reduction in PM_(2.5).Therefore,the implementation of a multipollutant emission reduction control strategy aimed at the prevention and control of PM_(2.5)and ozone pollution is the only means to realize the coordinated control of PM_(2.5)and ozone.

关键词： PM_(2.5) Ozone Coordinated control Multipollutant reduction

来源：评论

学校读者我要写书评

暂无评论

Fatigue and impact analysis and multi-objective optimization design of Mg/Al assembled wheel considering riveting residual stress

引用

Frontiers of Mechanical engineering 2022年第3期17卷 281-301页

作者： Wenchao XU Dengfeng WANG State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchun130022China

The multi-material assembled light alloy wheel presents an effective lightweight solution for new energy vehicles,but its riveting connection remains a *** address this problem,this paper proposed the explicit riveting-implicit springback-implicit fatigue/explicit impact sequence coupling simulation analysis method,analyzed the fatigue and impact performance of the punching riveting connected magnesium/aluminum alloy(Mg/Al)assembled wheel,and constructed some major evaluation *** accuracy of the proposed simulation method was verified by conducting physical experiments of single and cross lap *** punching riveting process parameters of the assembled wheel joints were defined as design variables,and the fatigue and impact performance of the assembled wheel was defined as the optimization *** connection-performance integration multi-objective optimization design of the assembled wheel considering riveting residual stress was designed via Taguchi experiment,grey relational analysis,analytic hierarchy process,principal component analysis,and entropy weighting *** optimization results of the three weighting methods were compared,and the optimal combination of design variables was *** fatigue and impact performance of the Mg/Al assembled wheel were effectively improved after optimization.

关键词： magnesium/aluminum assembled wheel riveting residual stress fatigue analysis impact analysis multi-objective optimization

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation-Inspired Prediction of Pavement Adhesion Coefficient 7

Semantic Segmentation-Inspired Prediction of Pavement Adhesi...

引用

7th CAA International Conference on Vehicular control and Intelligence, CVCI 2023

作者： Guo, Hongyan Wan, Juncheng Meng, Qingyu Liu, Yanran State Key Laboratory of Automotive Simulation and Control The College of Communication Engineering Jilin University Changchun China

ISBN: (纸本)9798350340488

Accurate prediction of the adhesion coefficient parameters of the road ahead is critical to the driving safety of intelligent driving vehicles, however, the current stage of raw image-based methods are difficult to achieve high-precision and reliable prediction due to the complexity of the elements within the scene. To this end, a road adhesion coefficient recognition algorithm inspired by semantic segmentation is proposed. The method designs a sequential prediction algorithm structure that includes semantic segmentation, road surface extraction, road surface recognition, and adhesion coefficient mapping. Additionally, the method introduces the spatial attention mechanism and channel attention mechanism separately into the semantic segmentation network and road surface classification network, effectively enhancing the accuracy and real-time performance of the adhesion coefficient prediction algorithm. Experimental results illustrate that this real-time adhesion coefficient prediction algorithm achieves good performance in maintaining accuracy, real-time capability, and robustness. It can accurately and rapidly predict road surface adhesion information in driving scenarios. © 2023 IEEE.

关键词： Attention mechanism Real-time performance Road surface adhesion coefficient Semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Feature Extraction and Evaluation Network for Citywide Traffic Condition Prediction

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年第9期9卷 1-16页

作者： Chu, Liang Hou, Zhuoran Jiang, Jingjing Yang, Jun Zhang, Yuanjian State Key Laboratory of Automotive Simulation and Control Jilin University No. 5988 Renmin Street Nanguan District Changchun China Department of Aeronautical and Automotive Engineering Loughborough University Leicestershire UK

Traffic condition prediction is crucial for executing traffic control and scheduling tasks within intelligent transportation systems. With diversified data sources, effectively modeling the complex spatial-temporal dependencies in the whole traffic network and predicting nonlinear general traffic condition changes become primary challenges for intelligent transportation systems. In this paper, a double-layer spatial-temporal feature extraction and evaluation (DL-STFEE) model is proposed, aimed at accurately predicting the traffic condition transferring of the whole traffic network. Firstly, a public traffic dataset is processed to extract the spatial and temporal features of vehicles, as well as the clusters of traffic conditions of the entire traffic network. Secondly, a double-layer deep learning traffic condition predictor is proposed. The model incorporates a spatial-temporal feature extraction layer, which leverages the graph convolution network (GCN) and attention mechanism to obtain spatiotemporal features across the whole traffic network. Additionally, a spatial-temporal combination layer employs a high-dimensional self-attention mechanism to integrate features across spatial-temporal combinations, bolstering prediction accuracy. Finally, through rigorous experiments, the contributions of neural network structures on the spatial-temporal feature extraction are comprehensively analyzed and the experiments also validate the effectiveness of traffic condition prediction by the proposed DL-STFEE model. IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Design and Characteristics of Shape Memory Alloy Bidirectional Torsional Actuator 9

Design and Characteristics of Shape Memory Alloy Bidirection...

引用

2023 9th International Conference on Applied Materials and Manufacturing Technology, ICAMMT 2023

作者： Shen, Chuanliang Zhan, Jincheng Deng, Yifei Gao, Yaohui State Key Laboratory of Automotive Simulation and Control Jilin University Changchun China College of Automotive Engineering Jilin University Changchun China

To overcome the problems of the low power/weight ratio of traditional servo motors, complex transmission systems, and large space occupied by hydraulic drive systems, this paper designs a bidirectional torsional actuator using the shape memory effect of Ti-Ni shape memory alloy (SMA) wire, which aims to realize the folding and unfolding of the wings of flying cars. The model of the designed actuator was established and the theoretical calculation was analyzed, based on which the experimental verification was carried out. It is found that when the heating current is 1.6 A, the mechanism can take into account the economy under the premise of meeting a certain folding speed. When the pre-stretching amount of SMA wire is 3%, the residual strain corresponding to the wire is small, about 0.577%, and it can provide driving torque and torsion angle to meet the design requirements of the actuator. This verifies the feasibility of the actuator and obtains the driving characteristics of the actuator. Finally, the shortcomings and improvement measures of the actuator are analyzed briefly. © Published under licence by IOP Publishing Ltd.

关键词： Titanium alloys

来源：评论

学校读者我要写书评

暂无评论

Aerodynamic Characteristics of Corrugated Features for Ahmed Model 3

Aerodynamic Characteristics of Corrugated Features for Ahmed...

引用

2023 3rd International Conference on Fluid and Chemical engineering, ICFCE 2023

作者： Zhang, Junning Hu, Xingjun Wen, Zhen Guo, Peng Qing, Yuxiao Zhao, Lifei Lv, Daqi Li, Shangyuan Fan, Ziying State Key Laboratory of Automotive Simulation and Control Jilin University Changchun130022 China College of Automotive Engineering Jilin University Changchun130022 China

The numerical simulation method is used to mimic the outflow field of 30 ° Ahmed model. The accuracy of the simulation method is verified by comparing with the wind tunnel test results. Based on the aerodynamic characteristics of the wind tunnel model, the impact of Ahmed on the structure is explored by combining the numerical simulation method of Ahmed model. The results show that the fold structure has more significant effect on lift and less effect on aerodynamic resistance. © Published under licence by IOP Publishing Ltd.

关键词： Lift

来源：评论

学校读者我要写书评

暂无评论

Machine learning driven rational design of dual atom catalysts on graphene for carbon dioxide electroreduction

引用

Nano Research 2025年第1期18卷 186-194页

作者： Dongxu Jiao Xinyi Li Mingzi Sun Lin Liu Jinchang Fan Jingxiang Zhao Bolong Huang Xiaoqiang Cui State Key Laboratory of Automotive Simulation and Control School of Materials Science and Engineeringand Key Laboratory of Automobile Materials of MOEJilin UniversityChangchun 130012China Department of Applied Biology and Chemical Technology The Hong Kong Polytechnic UniversityHung HomKowloonHong KongChina College of Chemistry and Chemical Engineering and Key Laboratory of Photonic and Electronic Bandgap MaterialsMinistry of EducationHarbin Normal UniversityHarbin 150025China

The development of high-performance atomiccatalysts for the carbon dioxide reduction reaction(CO_(2)RR)is atime-consuming process due to the complexity of the reactionmechanism and the uncertainty of the active ***,wehave proposed combining density functional theory(DFT)andmachine learning(ML)to investigate the potential of topologicalgraphene-based dual-atom catalysts(DACs)as CO_(2)*** analyzing the ML results,we identify thenumber of d-orbital electrons in the active site as a key factorinfluencing the CO_(2)RR catalytic ***,wepropose a simple descriptor to measure the CO_(2)RR activity ofthese *** findings provide plausible explanations for thesynergistic interactions between bimetallic atoms in CO_(2)RR andallow us to screen the homogeneous Ni-Ni pair as the mostpromising dual-atom *** work offers a fast MLapproach based on limited DFT calculations to predict the mostelectroactive and stable DACs on carbon support for CO_(2)RR,facilitating rapid screening of high-performance dual-atomcatalysts.

关键词： CO_(2)reaction reduction dual-atom catalysts density functional theory machine learning

来源：评论

学校读者我要写书评

暂无评论

MPC-based strategy for longitudinal and lateral stabilization of a vehicle under extreme conditions

引用

Science China(Information Sciences) 2022年第7期65卷 263-264页

作者： Zihan LI Ping WANG Chaojie ZHU Yunfeng HU Hong CHEN State Key Laboratory of Automotive Simulation and Control Jilin University Department of Control Science and Engineering School of Communication Engineering Jilin University Clean Energy Automotive Engineering Center Tongji University

Dear editor, In recent decades, active safety-control systems have been developed to assist drivers. Wheel slip ratio, yaw rate, and side-slip angle are commonly considered as the control indices of longitudinal and lateral vehicle stabilities [1]. However, if systems that only contain vehicle dynamics in longitudinal or lateral directions work simultaneously, the system objectives may conflict.

关键词： model predictive control stability control combined-slip characteristics LuGre tire model extreme driving conditions

来源：评论

学校读者我要写书评

暂无评论

Review of Crashworthiness Studies on Cellular Structures

引用

automotive Innovation 2023年第3期6卷 379-403页

作者： Hongyu Liang Ying Zhao Shixian Chen Fangwu Ma Dengfeng Wang State Key Laboratory of Automotive Simulation and Control Jilin UniversityChangchun 130022China College of Engineering and Technology Southwest UniversityChongqing 400715China Weichai Power Co. LtdWeifang 261061China

The application of lightweight structures with excellent energy absorption performance is crucial for enhancing vehicle safety and energy *** structures,inspired by the characteristics observed in natural organisms,have exhibited exceptional structural utilization in terms of energy absorption compared with traditional *** recent years,various innovative cellular structures have been proposed to meet different engineering needs,resulting in significant performance *** paper provides a comprehensive overview of novel cellular structures for energy absorption *** particular,it outlines the application forms and design concepts of cellular structures under typical loading conditions in vehicle collisions,including axial loading,oblique loading,bending loading,and blast *** structures have evolved to meet the demands of complex loading conditions and diverse research methods,focusing on achieving high-performance characteristics across multiple load ***,this review discusses manufacturing techniques and strate-gies for enhancing the manufacturing performance of cellular ***,current key challenges and future research directions for cellular structures are *** aim of this study is to provide valuable guidelines for researchers and engineers in the development of next-generation lightweight cellular structures.

关键词： Honeycomb Lattice structure Multi-cell tube Cellular structure filled tube Crashworthiness Multiple load cases

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：