检索结果-南通市图书馆

Perception Enhanced Deep Deterministic Policy Gradient for Autonomous Driving in Complex Scenarios

Computer Modeling in Engineering & Sciences 2024年第7期140卷 557-576页

作者： Lyuchao Liao Hankun Xiao Pengqi Xing Zhenhua Gan Youpeng He Jiajun Wang Fujian Provincial Key Laboratory of Automotive Electronics and Electric Drive Fujian University of TechnologyFuzhou350118China Fujian Provincial Universities Engineering research center for intelligent Driving Technology Fuzhou350118China

Autonomous driving has witnessed rapid advancement;however,ensuring safe and efficient driving in intricate scenarios remains a critical *** particular,traffic roundabouts bring a set of challenges to autonomous driving due to the unpredictable entry and exit of vehicles,susceptibility to traffic flow bottlenecks,and imperfect data in perceiving environmental information,rendering them a vital issue in the practical application of autonomous *** address the traffic challenges,this work focused on complex roundabouts with multi-lane and proposed a Perception EnhancedDeepDeterministic Policy Gradient(PE-DDPG)for AutonomousDriving in the ***,themodel incorporates an enhanced variational autoencoder featuring an integrated spatial attention mechanism alongside the Deep Deterministic Policy Gradient framework,enhancing the vehicle’s capability to comprehend complex roundabout environments and make ***,the PE-DDPG model combines a dynamic path optimization strategy for roundabout scenarios,effectively mitigating traffic bottlenecks and augmenting throughput *** experiments were conducted with the collaborative simulation platform of CARLA and SUMO,and the experimental results show that the proposed PE-DDPG outperforms the baseline methods in terms of the convergence capacity of the training process,the smoothness of driving and the traffic efficiency with diverse traffic flow patterns and penetration rates of autonomous vehicles(AVs).Generally,the proposed PE-DDPGmodel could be employed for autonomous driving in complex scenarios with imperfect data.

关键词： Autonomous driving traffic roundabouts deep deterministic policy gradient spatial attention mechanisms

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Reducing Operation Emissions and Improving Work Efficiency Using a Pure Electric Wheel Drive Tractor

引用

Engineering 2024年第6期37卷 230-245页

作者： Chang-Kai Wen Wen Ren Qing-Zhen Zhu Chun-Jiang Zhao Zhen-Hao Luo Sheng-Li Zhang Bin Xie Zhi-Jun Meng research center of intelligent Equipment Beijing Academy of Agriculture and Forestry SciencesBeijing 100097China State Key Laboratory of intelligent Agricultural Power Equipment Beijing 100097China BYD Company Limited Shenzhen 518118China College of Agricultural Engineering Jiangsu UniversityZhenjiang 212013China College of Engineering China Agricultural UniversityBeijing 100083China

In response to the problems of excessive greenhouse-gas and particulate emissions and the low traction efficiency of conventional diesel tractors in the field,a purely electric wheel-side drive tractor was studied,including an electric motor drive system,a battery ballast system,and an electro–hydraulic suspension *** paper develops a dynamics model of an electric tractor-ploughing unit under complex soil conditions,leading to the proposal of an active control method for drive wheel torque and a joint control method for the traction force of the suspension system and the front-and rear-axle loads of a ***,the tractor is prototyped and assembled,and ploughing tests are carried *** ploughing results show that the active torque-distribution control method proposed in this study reduces the tractor slip by 14.83%and increases the traction efficiency by 10.28%compared with the average torquedistribution *** with the conventional traction control mode,the joint control method for traction and ballast proposed in this paper results in a 3.7%increase in traction efficiency,a 15.05%decrease in slip,and a 4.9%reduction in total drive motor energy *** study will help to improve the operation quality and traction efficiency of electric tractors in complex soil conditions.

关键词： Electric tractor Ploughing unit Torque distribution Active ballast Traction performance

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Learning Scalable Task Assignment with Imperative-Priori Conflict Resolution in Multi-UAV Adversarial Swarm Defense Problem

引用

Journal of systems Science & Complexity 2024年第1期37卷 369-388页

作者： ZHAO Zhixin CHEN Jie XIN Bin LI Li JIAO Keming ZHENG Yifan School of Electronics and Information Engineering Tongji UniversityShanghai 201804China Shanghai Institute of intelligent Science and Technology Tongji UniversityShanghai 201804China School of Automation Beijing Institute of TechnologyBeijing 100081China National Key Laboratory of Autonomous intelligent Unmanned systems Beijing 100081China Shanghai Institute of intelligent Science and Technology Tongji UniversityShanghai 201804China.

The multi-UAV adversary swarm defense(MUASD)problem is to defend a static base against an adversary UAV swarm by a defensive UAV *** the problem into task assignment and low-level interception strategies is a widely used ***-based approaches for task assignment are a promising *** studies on learning-based methods generally assume decentralized decision-making architecture,which is not beneficial for conflict *** contrast,centralized decision-making architecture is beneficial for conflict resolution while it is often detrimental to *** achieve scalability and conflict resolution simultaneously,inspired by a self-attention-based task assignment method for sensor target coverage problem,a scalable centralized assignment method based on self-attention mechanism together with a defender-attacker pairwise observation preprocessing(DAP-SelfAtt)is ***,an imperative-priori conflict resolution(IPCR)mechanism is proposed to achieve conflict-free ***,the IPCR mechanism is parallelized to enable efficient *** validate the algorithm,a variant of proximal policy optimization algorithm(PPO)is employed for training in scenarios of various *** experimental results show that the proposed algorithm not only achieves conflict-free task assignment but also maintains scalability,and significantly improve the success rate of defense.

关键词： Conflict resolution reinforcement learning scalability task assignment.

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Investigation of surface textures deterioration on pavement skid-resistance using hysteresis friction models and numerical simulation method

引用

Friction 2024年第4期12卷 745-779页

作者： Haoyuan LUO Siyu CHEN Leyi ZHU Xiyin LIU Yangzezhi ZHENG Runming ZHAO Xiaoming HUANG School of transportation Southeast UniversityNanjing 211189China National Demonstration center for Experimental Education of Road and Traffic Engineering Southeast UniversityNanjing 211189China

Many rubber friction theories or some method combined theories and field-experiments are employed to evaluate the pavement skid-resistance deterioration due to the evolution of surface ***,these methods are difficult to be implemented in the analysis of situations with multi-factor coupling and some extreme *** study developed a framework to evaluate the skid-resistance deterioration of asphalt *** this framework,the portable laser scanning was used to create the digital worn pavement model,and a hydroplaning finite element(FE)model for these digital worn pavements was constructed to evaluate coupling effects of the texture evolution and factors of slip ratio,slip angle,velocity and water film on braking-cornering characteristics of *** this study,the deterioration of skid-resistance of five typical asphalt pavements due the surface texture wear was systematically investigated by this *** with previous works,this study established the rubber friction models for each digital worn pavement considering the energy hysteresis of rubber and the power spectrum density of surface *** the rubber friction model was used to define the interaction behaviors between the tire and corresponding wore pavements in the FE hydroplaning model,rather than using an empirical friction model or a fixed friction coefficient.

关键词： worn pavement skid-resistance friction coefficient textures evolution water film computer numerical simulation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

An Improved JSO and Its Application in Spreader Optimization of Large Span Corridor Bridge

引用

Computer Modeling in Engineering & Sciences 2024年第3期138卷 2357-2382页

作者： Shude Fu Xinye Wu Wenjie Wang Yixin Hu Zhengke Li Feng Jiang Fujian Key Laboratory of Digital Simulations for Coastal Civil Engineering School of Architecture and Civil EngineeringXiamen UniversityXiamen361005China Xiamen transportation Infrastructure intelligent Management and Maintenance Engineering Technology research center Xiamen361005China Fuzhou Company of China Communications Construction Co. Ltd.Fuzhou350005China

In this paper,given the shortcomings of jellyfish search algorithmwith low search ability in the early stage and easy to fall into local optimal solution,this paper introduces adaptive weight function and elite strategy,improving the global search scope in the early stage and the ability to refine the local development in the later *** the numerical study,the benchmark problem of dimensional optimization with a 10-bar truss structure and simultaneous dimensional shape optimization with a 15-bar truss structure is adopted,and the corresponding penalty method is used for constraint *** test results show that the improved jellyfish search algorithm can provide better truss sections as well as *** when the steel main truss of the large-span covered bridge is lifted,the site is limited and the large lifting equipment cannot enter the site,and the original structure does not meet the problem of stress concentration and large deformation of the bolt group,so the spreader is used to lift,and the improved jellyfish search algorithm is introduced into the design optimization of the *** results show that the improved jellyfish algorithm can efficiently and accurately find out the optimal shape and weight of the spreader,and throughMidas Civil simulation,the spreader used canmeet the requirements of weight and safety.

关键词： Truss optimization improved JSO size optimization shape optimization

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Enhancing Offensive Language Detection with Data Augmentation and Knowledge Distillation

引用

research 2024年第2期6卷 29-40页

作者： Jiawen Deng Zhuang Chen Hao Sun Zhexin Zhang Jincenzi Wu Satoshi Nakagawa Fuji Ren Minlie Huang The CoAl group DCSTInstitute for Artificial InteligenceState Key Lab of Intelligent Technology and SystemsBeijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China Graduate School of Information Science&Technology The University of Tokyo.Tokyo 1138654Japan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengduSichuan611731China

Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language *** data is the basis for developing detectors;however,the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English *** significantly affects the accuracy of Chinese offensive language detectors in practical applications,especially when dealing with hard cases or out-of-domain *** alleviate the limitations posed by available datasets,we introduce AugCOLD(Augmented Chinese Offensive Language Dataset),a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model ***,we employ a multiteacher distillation framework to enhance detection performance with unsupervised *** is,we build multiple teachers with publicly accessible datasets and use them to assign soft labels to *** soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network,i.e.,the final offensive *** conduct experiments on multiple public test sets and our well-designed hard tests,demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.

关键词： COLD dealing limitations

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Controllable split polarization singularities for ultra-precise displacement sensing

引用

Photonics research 2024年第7期12卷 1478-1484页

作者： JIAKANG ZHOU HAIXIANG MA SHUOSHUO ZHANG WU YUAN CHANGJUN MIN XIAOCONG YUAN YUQUAN ZHANG Nanophotonics research Centre Institute of Microscale Optoelectronics&State Key Laboratory of Radio Frequency Heterogeneous IntegrationShenzhen UniversityShenzhen 518060China research center for Humanoid Sensing Research Institute of Intelligent SensingZhejiang LabHangzhou 311100China Department of Biomedical Engineering The Chinese University of Hong KongHong KongChina

The topic of optical precise displacement measurement has garnered significant attention and generated widespread interest recently. The use of optical singularity offers a potential solution for this purpose, although effectively manipulating the singularity in an ideal manner remains challenging. In this work, we propose a theoretical approach to achieve controllable position modulation of the C-point in the focal plane, whose spatial position can be easily modulated by adjusting the relative offset factor β and the offset angle α of an azimuthal polarization beam(APB), while the interval and orientation of the C-points can be flexibly regulated. Notably, the chiral polarization state undergoes a distinct reversal along the link-line connecting the two C-points, thereby providing a promising approach for accurate displacement sensing. To evaluate its sensing characteristics, the varying pattern of the scattered field intensity is monitored when sweeping a gold helix and nanoparticle along the link-line. The results of simulation quality index Q verify that the equilibrium factor of the scattering field possesses an obvious linear relationship with the displacement, signifying a precise sub-nanometric *** research introduces new methods for the flexible control of polarization singularities in tightly focused fields,thereby enhancing the utilization of circular polarization properties near C-points for displacement *** findings not only enrich the field of nanometer measurement technology but also pave the way for new avenues of research in this domain.

关键词： polarization displacement precise

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

ST-LaneNet: Lane Line Detection Method Based on Swin Transformer and LaneNet

引用

Chinese Journal of Mechanical Engineering 2024年第1期37卷 130-145页

作者： Yufeng Du Rongyun Zhang Peicheng Shi Linfeng Zhao Bin Zhang Yaming Liu School of Mechanical Engineering Anhui Polytechnic UniversityWuhu 241000China Automotive New Technology Anhui Engineering and Technology research center Anhui Polytechnic UniversityWuhu 241000China School of Automotive and transportation Engineering Hefei University of TechnologyHefei 230009China

The advancement of autonomous driving heavily relies on the ability to accurate lane lines *** deep learning and computer vision technologies evolve,a variety of deep learning-based methods for lane line detection have been proposed by researchers in the ***,owing to the simple appearance of lane lines and the lack of distinctive features,it is easy for other objects with similar local appearances to interfere with the process of detecting lane *** precision of lane line detection is limited by the unpredictable quantity and diversity of lane *** address the aforementioned challenges,we propose a novel deep learning approach for lane line *** method leverages the Swin Transformer in conjunction with LaneNet(called ST-LaneNet).The experience results showed that the true positive detection rate can reach 97.53%for easy lanes and 96.83%for difficult lanes(such as scenes with severe occlusion and extreme lighting conditions),which can better accomplish the objective of detecting lane *** 1000 detection samples,the average detection accuracy can reach 97.83%,the average inference time per image can reach 17.8 ms,and the average number of frames per second can reach 64.8 *** programming scripts and associated models for this project can be accessed openly at the following GitHub repository:https://***/Duane 711/Lane-line-detec tion-ST-LaneNet.

关键词： Autonomous driving Lane line detection Deep learning Swin transformer

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Sparse convolutional model with semantic expression for waste electrical appliances recognition

引用

Science China(Technological Sciences) 2024年第9期67卷 2881-2893页

作者： HAN HongGui LIU YiMing LI FangYu DU YongPing Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational Intelligence and intelligent System Beijing 100124China Engineering research center of Digital Community Ministry of EducationBeijing 100124China Beijing Artificial Intelligence Institute and Beijing Laboratory for intelligent Environmental Protection Beijing 100124China

Deep neural networks play an important role in the recognition of waste electrical appliances. However, deep neural network components still lack reliability in decision-making features. To address this problem, a sparse convolutional model with semantic expression(SCMSE) is proposed. First, a low-rank sparse semantic expression component, combining the benefits of residual networks and sparse representation, is adapted to enhance sparse feature extraction and semantic expression. Second, a reliable network architecture is obtained by iterating the optimal sparse solution, enhancing semantic expression. Finally, the results of visualization experiments on the waste electrical appliances dataset demonstrate that the proposed SCMSE can obtain excellent semantic performance.

关键词： sparse convolutional model deep neural network semantic expression visualization computer vision

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Fast solution to the free return orbit's reachable domain of the manned lunar mission by deep neural network

引用

Journal of systems Engineering and Electronics 2024年第2期35卷 495-508页

作者： YANG Luyi LI Haiyang ZHANG Jin ZHU Yuehe College of Aerospace Science and Engineering National University of Defense TechnologyChangsha 410073China China Astronauts research and Training center Beijing 100094China Hunan Key Laboratory of intelligent Planning and Simulation for Aerospace Missions Changsha 410073China

It is important to calculate the reachable domain(RD)of the manned lunar mission to evaluate whether a lunar landing site could be reached by the spacecraft. In this paper, the RD of free return orbits is quickly evaluated and calculated via the classification and regression neural networks. An efficient databasegeneration method is developed for obtaining eight types of free return orbits and then the RD is defined by the orbit’s inclination and right ascension of ascending node(RAAN) at the perilune. A classify neural network and a regression network are trained respectively. The former is built for classifying the type of the RD, and the latter is built for calculating the inclination and RAAN of the RD. The simulation results show that two neural networks are well trained. The classification model has an accuracy of more than 99% and the mean square error of the regression model is less than 0.01°on the test set. Moreover, a serial strategy is proposed to combine the two surrogate models and a recognition tool is built to evaluate whether a lunar site could be reached. The proposed deep learning method shows the superiority in computation efficiency compared with the traditional double two-body model.

关键词： manned lunar mission free return orbit reachable domain(RD) deep neural network computation efficiency

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：