检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Caiji Zhang Bin Tian Shi Meng Shuangying Qi Yang Sun Yunfeng Ai Long Chen School of Artificial Intelligence University of Chinese Academy of Sciences and With the National Key Laboratory for Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Bin Tian is With the National Key Laboratory for Multi-Modal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and With the School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China National Key Laboratory for Multi-Modal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences and With the School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Chongqing Iron and Steel Group Mining Co. Ltd. Chongqing China School of Mechanical and Equipment Engineering Hebei University of Engineering Handan China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Waytous Inc. Qingdao China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Waytous Ltd. Qingdao China

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In recent years, research on Vehicle-to-Everything (V2X) cooperative perception algorithms mainly focuses on the fusion of intermediate features from LiDAR point clouds. Since the emergence of excellent single-vehicle visual perception models like BEVFormer, collaborative perception schemes based on camera and late-fusion have become feasible approaches. This paper proposes a V2X-collaborative 3D object detection structure in Bird's Eye View (BEV) space, based on global non-maximum suppression and late-fusion (V2X-BGN), and conducts experiments on the V2X-Set dataset. Focusing on complex road conditions with extreme occlusion, the paper compares the camera-based algorithm with the LiDAR-based algorithm, validating the effectiveness of pure visual solutions in the collaborative 3D object detection task. Additionally, this paper highlights the complementary potential of camera-based and LiDAR-based approaches and the importance of object-to-ego vehicle distance in the collaborative 3D object detection task.

关键词： Point cloud compression Visualization Three-dimensional displays Laser radar Roads Collaboration Object detection

来源：评论

学校读者我要写书评

暂无评论

The Quality Evaluation of Academic Papers in Carbon Capture, Utilization, and Storage

The Quality Evaluation of Academic Papers in Carbon Capture,...

引用

Machine Learning, control, and Robotics (MLCR), International Conference on

作者： Hangyue Zhang Jie Bai School of Computer Science and Technology Sun Yat-sen University Guangzhou P. R. China City State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing P. R. China

ISBN: (纸本)9781665454605

Carbon capture, utilization, and storage (CCUS) technology is a research hotspot worldwide owing to global climate change and warm gas control. CCUS papers from the last twenty years, derived from the Web of Science database, were analyzed to investigate the impact and citation of academic papers using machine learning methods. Firstly, nine author characteristics, keywords, and three other categories were extracted from the literature. Then, the natural logarithm distribution of the annual average number of citations was obtained, and five evaluation grades were decided based on the citations. Next, the keyword evolution of papers in the CCUS field is analyzed, and a model on the keyword evolution trend index is proposed. Data integration and imbalance processing were conducted after random sampling. A citation prediction model was proposed to evaluate the quality of CCUS academic papers and was verified on the recent five years' CCUS papers by comparing it with nine other mainstream machine learning models. The results indicate that the random forest model exhibits the best performance, with an accuracy rate reaching 88.7%; an ablation experiment was also conducted using the same algorithm. The results prove the effectiveness of our proposed method, shedding light on the quality of academic papers and technology development in CCUS.

关键词： Machine learning Climate change Random forests Modeling Energy storage

来源：评论

学校读者我要写书评

暂无评论

Stackelberg Game Optimal Scheduling of User-Side Energy Storage Considering Source-Load Uncertainty

Stackelberg Game Optimal Scheduling of User-Side Energy Stor...

引用

International Joint Conference on Energy, Electrical and Power Engineering, CoEEPE 2021

作者： Luo, Kui Guo, Zhidong Rui, Tao Hu, Cungang State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems China Electric Power Research Institute Beijing100000 China School of Electrical Engineering and Automation Anhui University Hefei230601 China Engineering Research Center of Power Quality Ministry of Education Anhui University Hefei230601 China

ISBN: (纸本)9789811919213

Aiming at the distributed energy storage optimal scheduling problem considering source load uncertainty, a user side energy storage stochastic optimal scheduling strategy considering master–slave game is proposed in this paper. This method comprehensively considers the uncertainty of photovoltaic (PV) power generation and user side load, and constructs a Stackelberg game model with distribution network operators as leaders and user side as followers. By solving the internal optimal electricity price, the electric energy interaction between the user side and distribution network operator (DNO) is stimulated. While improving the operation economy of both sides of the game, promote the consumption of renewable energy at the distribution network side. At the same time, the optimal scheduling plan of user side energy storage is obtained. The example results show that the optimization method proposed in this paper can effectively adapt to PV power consumption and improve the operation economy and stability of distribution network operators and users. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Scheduling

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Detection for Autonomous Vehicles Using Virtual-to-Real Augmentation

Pedestrian Detection for Autonomous Vehicles Using Virtual-t...

引用

Chinese automation Congress (CAC)

作者： Bo Lu Min Huang Xi Li Yunhao Nie Qinghai Miao Yisheng Lv School of Artificial Intelligence University of Chinese Academy of Sciences Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China

Annotated data are essential to the success of training deep neural models for autonomous driving. Practically, it is both expensive and time consuming to collect and annotate plenty of data driving cross the city. It is even harder to cover the corner cases involving rare pedestrian poses with occlusions. To tackle this problem, we propose a data augmentation method for pedestrian detection. First, we take a SMPL model to generate pedestrians with a variety of poses and textures. Second, we insert the rendered pedestrians into images with real traffic background according to vanishing point. Occlusions can also be set easily by taking use of segmentation annotations of original real dataset. We evaluated the effectiveness of the generated synthetic dataset using multiple detectors. Results of three experiments shown that detectors trained with mixture of synthetic and real data outperform those trained on only real datasets.

关键词： Training Image segmentation Urban areas Neural networks Detectors Data models Labeling

来源：评论

学校读者我要写书评

暂无评论

Multi-View Spatio-Temporal Deep Graph Neural Network for Travel Demand Prediction

SSRN

引用

SSRN 2022年

作者： Zhao, Tianhong Huang, Zhengdong Tu, Wei Biljecki, Filip Chen, Long School of Architecture and Urban Planning Shenzhen University China Department of Architecture National University of Singapore Singapore Department of Real Estate National University of Singapore Singapore State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China

Predicting travel demand is an essential task in urban mobility management. Previous methods use the spatio-temporal dependencies of travel demand to improve the prediction accuracy, but pay less attention to the cross-modal dependency among different transportation modes (bus, metro, taxi, etc.). We propose a multi-view spatio-temporal graph neural networks (MSTGNN) model to predict the travel demand. The development, bridging the gaps of the state of the art, emphasizes the ability to capture cross-view dependencies, derived from the interaction of multiple transportation modes. Specifically, a multi-view graph with the bus, metro, and taxi views is constructed according to spatial adjacency and transportation interaction adjacency. A multi-view attention temporal graph convolution module is designed to capture spatio-temporal and cross-view dependencies. Additionally, the cross-view features spatial consistency loss is presented to overcome the problem of uneven distribution of multi-view features. Taking the bus travel demand as an example, intensive experiments are conducted using real-world bus, metro, and taxi data in Shenzhen. The results indicate that the MAE of the MSTGNN model improves baseline methods by 9.13%. The contributions of different transportation modes and local/global cross-view dependencies are demonstrated in the ablation experiments. The attention mechanism in the MSTGNN model demonstrates certain interpretability of the interaction between different transportation modes. The dataset generated in this research has been released as open data. © 2022, The Authors. All rights reserved.

关键词： Smart cards

来源：评论

学校读者我要写书评

暂无评论

Model-Based and Data-Driven control of Event- and Self-Triggered Discrete-Time LTI systems

arXiv

引用

arXiv 2022年

作者： Wang, Xin Berberich, Julian Sun, Jian Wang, Gang Allgöwer, Frank Chen, Jie The Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing10081 China The Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China The University of Stuttgart Institute for Systems Theory and Automatic Control Stuttgart70550 Germany The Department of Control Science and Engineering Tongji University Shanghai201804 China The State Key Lab of Intelligent Control and Decision of Complex Systems School of Automation Beijing Institute of Technology Beijing100081 China

The present paper considers the model-based and data-driven control of unknown linear time-invariant discretetime systems under event-triggering and self-triggering transmission schemes. To this end, we begin by presenting a dynamic event-triggering scheme (ETS) based on periodic sampling, and a discrete-time looped-functional approach, through which a model-based stability condition is derived. Combining the model-based condition with a recent data-based system representation, a data-driven stability criterion in the form of linear matrix inequalities (LMIs) is established, which also offers a way of co-designing the ETS matrix and the controller. To further alleviate the sampling burden of ETS due to its continuous/periodic detection, a self-triggering scheme (STS) is developed. Leveraging pre-collected input-state data, an algorithm for predicting the next transmission instant is given, while achieving system stability. Finally, numerical simulations showcase the efficacy of ETS and STS in reducing data transmissions as well as of the proposed co-design methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Linear matrix inequalities

来源：评论

学校读者我要写书评

暂无评论

Concept, Principle, and Modeling of Driving Risk Entropy Based on Human-Vehicle-Road Coupling Model for Autonomous Vehicle

SSRN

引用

SSRN 2024年

作者： Gao, Hongbo Yang, Hanqing Zhu, Juping Su, Huiping Wang, Ning Xie, Liping Li, Keqiang Department of Automation University of Science and Technology of China Hefei230026 China Institute of Advanced Technology University of Science and Technology of China Hefei230088 China School of Electrical and Electronic Engineering Nanyang Technological University 639798 Singapore Chongqing College of Mobile Communication Chongqing400044 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China State Key Laboratory of Automotive Safety and Energy Tsinghua University Beijing100084 China

Driving risk entropy, based on entropy law, is an innovative concept proposed for intelligent driving systems. The concept deals with the driving risks caused by the human-vehicle-road system from the driving information obtained;however, driving risks are difficult to assess due to many influencing factors and great uncertainty. The risk entropy model of vehicles is visualized by introducing the concept of basic isotropic risk elliptic line (BIREL). Further incorporating the concept of information entropy, risk entropy models for vehicle interaction and vulnerable participants are established, and the risk entropy model for roads is developed using raster coordinates. Ultimately, a three-dimensional driving risk entropy model is constructed based on the human-vehicle-road coupling model, with appropriate weights assigned to each parameter through the DDPG algorithm. Experimental results demonstrate the effectiveness of the driving risk entropy model. © 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

Visuotactile Feedback Parallel Gripper for Robotic Adaptive Grasping

Visuotactile Feedback Parallel Gripper for Robotic Adaptive ...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Boyue Zhang Shaowei Cui Chaofan Zhang Jingyi Hu Shuo Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Institute of Automation Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China

ISBN: (纸本)9781665481106

In robot grasp and dexterous manipulation tasks, tactile sensing is important for the control adjustment of the manipulator. In this paper, we present a novel low-cost parallel gripper with high-resolution tactile sensing, named the GelStereo Gripper. Furthermore, an adaptive grasp strategy is proposed to endow the gripper with tactile-feedback grasp stability-maintaining ability. We install the gripper on our robot platform and conduct various grasp experiments by utilizing proposed control methods. Experimental results verify the reliability of the GelStereo gripper and also prove the effectiveness of the proposed strategy for experimental objects with different features.

关键词： Shape Pose estimation Force Tactile sensors Grasping Robot sensing systems Sensors

来源：评论

学校读者我要写书评

暂无评论

A Biofuel Risk management Model for Biomass-Based Heat Sources Considering Supply-Demand-Side Uncertainties 12

A Biofuel Risk Management Model for Biomass-Based Heat Sourc...

引用

12th International Conference on Quality, Reliability, Risk, Maintenance, and Safety Engineering, QR2MSE 2022

作者： Fu, Dianzheng Zhou, Tingting Yang, Tianji Zhang, Tao Dong, Jingya Key Laboratory of Networked Control Systems Institutes for Robotics and Intelligent Manufacturing Digital Factory Department Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Technical Management Division Guodian Technology & Environment Group Co Ltd Beijing China Digital Factory Department Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781839538360

Biofuel-based heat sources are gradually penetrated into heating systems in Northern China in the background of carbon neutrality. It is essential to conduct biofuel risk management study, not only for enhancing the ability of continuous heat supply for heating systems, but also improving the ability of effective cost control. A biofuel risk management model is thus proposed innovatively for biomass-based heat sources considering supply-demand-side uncertainties. The developed model integrates Chance-constrained programming, Two-stage stochastic programming and the traditional linear programming into a general framework. After that, the developed model is applied in to a real heat-source case of biofuel risk management under uncertainties and the corresponding solutions on biofuel risk management are generated. The beneficial results of biofuel allocation pattern can be obtained for decision-makers to provide the fuel management support under different risk levels. Besides, a trade-off analysis between the constraint-violation risk and the system cost can also be provided to conduct in-depth analysis. © 2022 IEEE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Context-aware Emotion Recognition Based on Vision-Language Pre-trained Model

Context-aware Emotion Recognition Based on Vision-Language P...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： XingLin Li Xinde Li Chuanfei Hu Huaping Liu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Nanjing Center for Applied Mathematics Nanjing China Southeast University Shenzhen Research Institute Shenzhen China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Given the difficulty of recognizing ambiguous emotions in facial expression recognition tasks, we propose a visual-language model named CAER-CLIP to address this challenge. The proposed CAER-CLIP standed for Context-Aware Emotion Recognition (CAER), and were incorporated structure of the Contrastive Language–Image Pre-training (CLIP) model as promising alternative to classifier. There are two parts in CAER-CLIP model. In the visual part, facial expressions and contextual information of the image are simultaneously extracted to obtain the final feature embeddings, which are then used as a learnable “class” token for text-image pairing with desired module. In the textual part, we use text labels for emotion recognition classes as input. The outputs were merged to participate the comparative study to generated parameters of the model. The experiments demonstrate the effectiveness of the proposed method and show that our CAER-CLIP outperforms the state-of-the-art results on the CAER benchmark. The ablation experiment verified the effectiveness of both the classifier-based and text-based (ours without classifier) models, demonstrating that our method with the CAER-CLIP structure performed better, and the incorporation of a text encoder in the deep network model architecture effectively enhancing recognition accuracy.

关键词： Training Emotion recognition Visualization Accuracy Text recognition Face recognition Benchmark testing Feature extraction Data mining Context modeling

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：