检索结果-内蒙古大学图书馆

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 231-239页

作者： Yahui Liu Bin Tian Yisheng Lv Lingxi Li Fei-Yue Wang the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190 IEEE the Transportation and Autonomous Systems Institute(TASI)and the Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University Indianapolis(IUPUI)Indianapolis 46202 USA

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://***/yahuiliu99/PointC onT.

关键词： Content-based Transformer deep learning feature aggregator local attention point cloud classification

来源：评论

学校读者我要写书评

暂无评论

The Journey/DAO/TAO of Embodied Intelligence: From Large Models to Foundation Intelligence and Parallel Intelligence

引用

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1313-1316页

作者： Tianyu Shen Jinlin Sun Shihan Kong Yutong Wang Juanjuan Li Xuan Li Fei-Yue Wang College of Information Science and Technology Beijing University of Chemical TechnologyBeijing 100029China School of Electrical and Information Engineering Jiangsu UniversityZhenjiang 212013China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and RoboticsCollege of EngineeringPeking UniversityBeijing 100871China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Peng Cheng Laboratory Shenzhen 518000China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China IEEE

THE tremendous impact of large models represented by ChatGPT[1]-[3]makes it necessary to con-sider the practical applications of such models[4].However,for an artificial intelligence(AI)to truly evolve,it needs to possess a physical“body”to transition from the virtual world to the real world and evolve through interaction with the real *** this context,“embodied intelligence”has sparked a new wave of research and technology,leading AI beyond the digital realm into a new paradigm that can actively act and perceive in a physical environment through tangible entities such as robots and automated devices[5].

关键词： Intelligence DAO TAO

来源：评论

学校读者我要写书评

暂无评论

VistaScenario: Interaction Scenario Engineering for Vehicles with Intelligent systems for Transport Automation

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-17页

作者： Chang, Cheng Zhang, Jiawei Ge, Jingwei Zhang, Zuo Wei, Junqing Li, Li Wang, Fei-Yue Department of Automation Tsinghua University Beijing China DiDi Autonomous Driving Company Beijing China Department of Automation BNRist Tsinghua University Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Intelligent vehicles and autonomous driving systems rely on scenario engineering for intelligence and index (I&I), calibration and certification (C&C), and verification and validation (V&V). To extract and index scenarios, various vehicle interactions are worthy of much attention, and deserve refined descriptions and labels. However, existing methods cannot cope well with the problem of scenario classification and labeling with vehicle interactions as the core. In this paper, we propose VistaScenario framework to conduct interaction scenario engineering for vehicles with intelligent systems for transport automation. Based on the summarized basic types of vehicle interactions, we slice scenario data stream into a series of segments via spatiotemporal scenario evolution tree. We also propose the scenario metric Graph-DTW based on Graph Computation Tree and Dynamic Time Warping to conduct refined scenario comparison and labeling. The extreme interaction scenarios and corner cases can be efficiently filtered and extracted. Moreover, with naturalistic scenario datasets, testing examples on trajectory prediction model demonstrate the effectiveness and advantages of our framework. VistaScenario can provide solid support for the usage and indexing of scenario data, further promote the development of intelligent vehicles and transport automation. IEEE

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Data-driven finite-time adaptive attitude tracking control for spacecraft

引用

Advances in Space Research 2025年第12期75卷 8780-8791页

作者： Wang, Jianhui He, Guangping Bian, Guibin Geng, Shixiong College of Mechanical & Energy Engineering Beijing University Of Technology Beijing100124 China Department of Mechanical and Electrical Engineering North China University of Technology Beijing100144 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

This paper proposes a novel data-driven finite-time adaptive control method for the spacecraft attitude tracking control problem with inertial uncertainty. Based on the dynamic regression extension technique, the disturbance unit matrix is introduced, and the parameter estimation law in the form of algebraic equations is presented, which realizes the arbitrarily small convergence of parameter estimation error. The convergence of parameter estimation errors is verified through stability analysis. Globally non-singular fast terminal sliding mode control is designed to achieve finite-time arrival of the sliding surface and convergence of the system state error. The stability analysis of the closed-loop system demonstrates the effectiveness of the proposed method. Furthermore, the effectiveness and superiority of the proposed method are verified through numerical simulations of spacecraft attitude tracking control. © 2025 COSPAR

关键词： Attitude control

来源：评论

学校读者我要写书评

暂无评论

Conservative-Progressive Collaborative Learning for Semi-Supervised Semantic Segmentation

引用

IEEE Transactions on Image Processing 2023年 32卷 6183-6194页

作者： Fan, Siqi Zhu, Fenghua Feng, Zunlei Lv, Yisheng Song, Mingli Wang, Fei-Yue Institute of Automation State Key Laboratory of Management and Control of Complex Systems Chinese Academy of Sciences Beijing100190 China Tsinghua University Beijing100190 China Zhejiang University College of Computer Science and Technology Hangzhou310027 China

Pseudo supervision is regarded as the core idea in semi-supervised learning for semantic segmentation, and there is always a tradeoff between utilizing only the high-quality pseudo labels and leveraging all the pseudo labels. Addressing that, we propose a novel learning approach, called Conservative-Progressive Collaborative Learning (CPCL), among which two predictive networks are trained in parallel, and the pseudo supervision is implemented based on both the agreement and disagreement of the two predictions. One network seeks common ground via intersection supervision and is supervised by the high-quality labels to ensure a more reliable supervision, while the other network reserves differences via union supervision and is supervised by all the pseudo labels to keep exploring with curiosity. Thus, the collaboration of conservative evolution and progressive exploration can be achieved. To reduce the influences of the suspicious pseudo labels, the loss is dynamic re-weighted according to the prediction confidence. Extensive experiments demonstrate that CPCL achieves state-of-the-art performance for semi-supervised semantic segmentation. © 1992-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Implicit Scene Context-aware Interactive Trajectory Prediction for Autonomous Driving

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年第9期9卷 1-17页

作者： Lan, Wenxing Li, Dachuan Hao, Qi Zhao, Dezong Tian, Bin Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China James Watt School of Engineering University of Glasgow Glasgow U.K State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China

The accurate prediction of behaviors of surrounding traffic participants is critical for autonomous vehicles (AV). How to fully encode both explicit (e.g., map structure and road geometry) and implicit scene context information (e.g., traffic rules) within complex scenarios is still challenging. In this work, we propose an implicit scene context-aware trajectory prediction framework (the PRISC-Net, Prediction with Implicit Scene Context) for accurate and interactive behavior forecasting. The novelty of the proposed approach includes: 1) development of a behavior prediction framework that takes advantage of both model- and learning-based approaches to fully encode scene context information while modeling complex interactions;2) development of a candidate path target predictor that utilizes explicit and implicit scene context information for candidate path target prediction, along with a motion planning-based generator that generates kinematic feasible candidate trajectories;3) integration of the proposed target predictor and trajectory generator with a learning-based evaluator to capture complex agent-agent and agent-scene interactions and output accurate predictions. Experiment results based on vehicle behavior datasets and real-world road tests show that the proposed approaches outperform state-of-the-art methods in terms of prediction accuracy and scene context compliance. IEEE

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Development and control of Underwater Gliding Robots:A Review

引用

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1543-1560页

作者： Jian Wang Zhengxing Wu Huijie Dong Min Tan Junzhi Yu the State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China the State Key Laboratory for Turbulence and Complex System Department of Mechanics and Engineering ScienceBIC-ESATCollege of EngineeringPeking UniversityBeijing 100871China

As one of the most effective vehicles for ocean development and exploration,underwater gliding robots(UGRs)have the unique characteristics of low energy consumption and strong ***,by borrowing the motion principles of current underwater robots,a variety of novel UGRs have emerged with improving their maneuverability,concealment,and environmental friendliness,which significantly broadens the ocean *** this paper,we provide a comprehensive review of underwater gliding robots,including prototype design and their key *** the perspective of motion characteristics,we categorize the underwater gliding robots in terms of traditional underwater gliders(UGs),hybrid-driven UGs,bio-inspired UGs,thermal UGs,and ***,their buoyancy driven system,dynamic and energy model,and motion control are concluded with detailed ***,we have discussed the current critical issues and future *** review offers valuable insight into the development of next-generation underwater robots well-suited for various oceanic applications,and aims to gain more attention of researchers and engineers to this growing field.

关键词： Buoyancy driven motion control oceanic applications system development underwater gliding robots

来源：评论

学校读者我要写书评

暂无评论

A Novel Attention-based Global and Local Information Fusion Neural Network for Group Recommendation

引用

Machine Intelligence Research 2022年第4期19卷 331-346页

作者： Song Zhang Nan Zheng Dan-Li Wang State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China

Due to the popularity of group activities in social media,group recommendation becomes increasingly *** aims to pursue a list of preferred items for a target *** deep learning-based methods on group recommendation have focused on learning group representations from single interaction between groups and ***,these methods may suffer from data sparsity *** for the interaction between groups and users,there also exist other interactions that may enrich group representation,such as the interaction between groups and *** interactions,which take place in the range of a group,form a local view of a certain *** addition to local information,groups with common interests may also show similar tastes on ***,group representation can be conducted according to the similarity among groups,which forms a global view of a certain *** this paper,we propose a novel global and local information fusion neural network(GLIF)model for group *** GLIF,an attentive neural network(ANN)activates rich interactions among groups,users and items with respect to forming a group′s local ***,our model also leverages ANN to obtain a group′s global representation based on the similarity among different ***,it fuses global and local representations based on attention mechanism to form a group′s comprehensive ***,group recommendation is conducted under neural collaborative filtering(NCF)*** experiments on three public datasets demonstrate its superiority over the state-of-the-art methods for group recommendation.

关键词： Group recommendation attentive neural network(ANN) global information local information recommender system

来源：评论

学校读者我要写书评

暂无评论

A PREA and OODA Computing Framework of Unmanned systems to Perform complex Tasks

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-18页

作者： Yang, Dongsheng Yu, Lei Zhang, Yi Zhu, Fenghua Li, Qiang Cui, Huachao Ma, Qiongmin Fan, Lili Tian, Yonglin Jinan University Guangzhou China Intelligent Science & Technology Academy Limited of CASIC Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China 28th Research Institute of China Electronics Technology Group Corporation Nanjing China National Key Laboratory for Complex Systems Simulation National University of Defense Technology Changsha China School of Information and Electronics Beijing Institute of Technology Beijing China

A C2 computing framework for unmanned systems to perform complex tasks is proposed using methods of system of systems engineering, which is formed by combining the macro-scale command and control (C2) process mechanism model (PREA loop) and micro-scale C2 process mechanism model (OODA loop). Guided by PREA loop and OODA loop, the computing framework is divided into four steps and three kinds of transformations. The four steps are design, construction, operation monitoring, and assessment. The three transformations are tactical feedback, campaign feedback, and strategic feedback. A C2 organization model of joint landing combat force is established against the background of a typical complex task of joint landing operation, and the C2 computing framework based on the PREA &OODA is used to implement the C2 activities of the joint landing combat force. The influence of the computing framework on the performance of unmanned systems under different task conditions is verified, including task coordination load, task efficiency and sensitivity of unmanned systems response. Authors

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

The Prospects of Multi-modal Pre-trained Models in Epidemic Forecasting 9th

The Prospects of Multi-modal Pre-trained Models in Epidemi...

引用

9th China National Conference on Big Data and Social Computing, BDSC 2024

作者： Fei, Jiaqiang Zhao, Pengfei Luo, Tianyi Wang, Jiaojiao Cao, Zhidong The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9789819758029

Accurate epidemic forecasting is imperative in light of the increasing global threat posed by epidemic diseases. Presently, researchers predominantly approach this challenge as a time-series prediction task and have proposed a variety of effective methodologies. However, two critical issues deserve thorough consideration. Firstly, the transmission of infectious diseases is a profoundly intricate process influenced by a multitude of factors, encompassing complex dynamics and propagation mechanisms. In contrast to the multifaceted nature of real-world scenarios, prevailing modeling approaches often exhibit undue simplification, resulting in imprecision and a deficit of interpretability. Secondly, existing methodologies excessively rely on data and require substantial adaptation for new infectious disease scenarios. The endeavor to conduct rapid and precise simulations and predictions during the early stages of transmission is challenging due to limited data availability. Thus, we aim to explore the feasibility and effective strategies of leveraging multi-modal pre-trained technology for epidemic forecasting. This approach offers the potential to comprehensively grasp the transmission process from multi-view perspectives and acquire richer representations by integrating multi-modal data. Moreover, through pre-trained, this methodology captures overarching patterns and principles of infectious disease transmission, facilitating swift and accurate predictions via fine-tuning, particularly in scenarios of sparse early-stage transmission data. We discuss the prospects of multi-modal pre-trained models in epidemic forecasting and provide feasible strategies for constructing the model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Forecasting

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：