检索结果-内蒙古大学图书馆

Domain generalization for vision-based driving trajectory generation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wang, Yunkai Zhang, Dongkun Cui, Yuxiang Chen, Zexi Jing, Wei Chen, Junbo Xiong, Rong Wang, Yue State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China Department of Autonomous Driving Lab Alibaba DAMO Academy Hangzhou China

One of the challenges in vision-based driving trajectory generation is dealing with out-of-distribution scenarios. In this paper, we propose a domain generalization method for vision-based driving trajectory generation for autonomous vehicles in urban environments, which can be seen as a solution to extend the Invariant Risk Minimization (IRM) method in complex problems. We leverage an adversarial learning approach to train a trajectory generator as the decoder. Based on the pre-trained decoder, we infer the latent variables corresponding to the trajectories, and pre-train the encoder by regressing the inferred latent variable. Finally, we fix the decoder but fine-tune the encoder with the final trajectory loss. We compare our proposed method with the state-of-the-art trajectory generation method and some recent domain generalization methods on both datasets and simulation, demonstrating that our method has better generalization ability. Our project is available at https://***/view/dg-traj-gen. Copyright © 2021, The Authors. All rights reserved.

关键词： Signal encoding

Improving the initialization speed for long-range NRTK in network solution mode

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2020年第5期63卷 866-873页

作者： ZHANG Ming LÜJinHu BAI ZhengDong LIU Hui FAN ChengCheng Key Laboratory of Systems and Control Institute of Systems ScienceAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Automation Science and Electrical Engineering Beihang UniversityBeijing 100191China Institute of Geomatics Tsinghua UniversityBeijing 100084China GNSS Research Center Wuhan UniversityWuhan 430079China Guangxi Zhuang Autonomous Region Remote Sensing Information Surveying and Mapping Institute Nanning 530023China

Initialization speed is one of the most important factors in network real time kinematic(NRTK)*** to the low correlation among the error sources of reference stations,it is difficult to fix reference station ambiguities of long-range NRTK *** traditional reference stations ambiguity resolution(AR)methods,baselines are usually solved independently which is called baseline solution(BS)mode in this *** the correlations among baselines are not taken into consideration in ambiguities estimation,the AR speed is ***,tens of minutes or longer time is required to *** propose a network solution(NS)mode approach,in which the correlations among the double-difference ambiguities(DDAs)as well as double-difference ionospheric delays(DDIDs)of different baselines are considered in estimating float ambiguity *** results show that the float ambiguity solutions obtained are more accurate with an improved ***,initialization speed is significantly increased by 18%in NS mode.

关键词： initialization speed network real time kinematic(NRTK) reference station ambiguity resolution(AR) network solution(NS)mode baseline solution(BS)mode

Toward Consistent drift-free visual inertial localization on keyframe based map

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, Zhuqing Jiao, Yanmei Huang, Shoudong Wang, Yue Xiong, Rong State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang China Centre for Autonomous Systems Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

Global localization is essential for robots to perform further tasks like navigation. In this paper, we propose a new framework to perform global localization based on a filter-based visual-inertial odometry framework MSCKF. To reduce the computation and memory consumption, we only maintain the keyframe poses of the map and employ Schmidt-EKF to update the state. This global localization framework is shown to be able to maintain the consistency of the state estimator. Furthermore, we introduce a re-linearization mechanism during the updating phase. This mechanism could ease the linearization error of observation function to make the state estimation more precise. The experiments show that this mechanism is crucial for large and challenging scenes. Simulations and experiments demonstrate the effectiveness and consistency of our global localization framework. Copyright © 2021, The Authors. All rights reserved.

关键词： State estimation

HEART: Achieving Timely Multi-Model Training for Vehicle-Edge-Cloud-Integrated Hierarchical Federated Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Yang, Xiaohong Liwang, Minghui Wang, Xianbin Cheng, Zhipeng Hosseinalipour, Seyyedali Dai, Huaiyu Jiao, Zhenzhen School of Informatics Xiamen University Fujian China Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems Japan Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai China Department of Electrical and Computer Engineering Western University ON Canada School of Future Science and Engineering Soochow University Suzhou China Department of Electrical Engineering University at Buffalo-SUNY BuffaloNY United States Department of Electrical and Computer Engineering NC State University RaleighNC United States iF-Labs Beijing Teleinfo Technology Company Ltd. CAICT Beijing China

The rapid growth of AI-enabled Internet of Vehicles (IoV) calls for efficient machine learning (ML) solutions that can handle high vehicular mobility and decentralized data. This has motivated the emergence of Hierarchical Federated Learning over vehicle-edge-cloud architectures (VEC-HFL). Nevertheless, one aspect which is underexplored in the literature on VEC-HFL is that vehicles often need to execute multiple ML tasks simultaneously, where this multi-model training environment introduces crucial challenges. First, improper aggregation rules can lead to model obsolescence and prolonged training times. Second, vehicular mobility may result in inefficient data utilization by preventing the vehicles from returning their models to the network edge. Third, achieving a balanced resource allocation across diverse tasks becomes of paramount importance as it majorly affects the effectiveness of collaborative training. We take one of the first steps towards addressing these challenges via proposing a framework for multi-model training in dynamic VEC-HFL with the goal of minimizing global training latency while ensuring balanced training across various tasks—a problem that turns out to be NP-hard. To facilitate timely model training, we introduce a hybrid synchronous-asynchronous aggregation rule. Building on this, we present a novel method called Hybrid Evolutionary And gReedy allocaTion (HEART). The framework operates in two stages: first, it achieves balanced task scheduling through a hybrid heuristic approach that combines improved Particle Swarm Optimization (PSO) and Genetic Algorithms (GA);second, it employs a low-complexity greedy algorithm to determine the training priority of assigned tasks on vehicles. Experiments on real-world datasets demonstrate the superiority of HEART over existing methods. © 2025, CC BY-NC-ND.

关键词： Federated learning

Towards Integrated Traffic control with Operating Decentralized autonomous Organization

学校读者我要写书评

暂无评论

Towards Integrated Traffic Control with Operating Decentrali...

International Conference on Intelligent Transportation

作者： Shengyue Yao Jingru Yu Yi Yu Jia Xu Xingyuan Dai Honghai Li Fei-Yue Wang Yilun Lin Urban Computing Shanghai AI Lab Shanghai China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Research and Development Center of Transport Industry of Autonomous Driving Technology RIOH High and Technology Group Institute of Automation Chinese Academy of Sciences Beijing China Macau Institute of Systems Engineering Macau University of Science and Technology Macau China

With a growing complexity of the intelligent traffic system (ITS), an integrated control of ITS that is capable of considering plentiful heterogeneous intelligent agents is desired. However, existing control methods based on the centralized or the decentralized scheme have not presented their competencies in considering the optimality and the scalability simultaneously. To address this issue, we propose an integrated control method based on the framework of Decentralized autonomous Organization (DAO). The proposed method achieves a global consensus on energy consumption efficiency (ECE), meanwhile to optimize the local objectives of all involved intelligent agents, through a consensus and incentive mechanism. Furthermore, an operation algorithm is proposed regarding the issue of structural rigidity in DAO. Specifically, the proposed operation approach identifies critical agents to execute the smart contract in DAO, which ultimately extends the capability of DAO-based control. In addition, a numerical experiment is designed to examine the performance of the proposed method. The experiment results indicate that the controlled agents can achieve a consensus faster on the global objective with improved local objectives by the proposed method, compare to existing decentralized control methods. In general, the proposed method shows a great potential in developing an integrated control system in the ITS.

关键词：

Prescriptive Manufacturing in Society 5.0: Human autonomous Organizations and “On-Demand” Smart Services

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2024年第3期58卷 139-144页

作者： Xiao Wang Jun Huang Jing Yang Xiaoxing Wang Fei-Yue Wang Engineering Research Center of Autonomous Unmanned System Technology Ministry of Education Anhui University Hefei 230601 China Macau University of Science and Technology Macau 999078 China School of artificial Intelligence University of Chinese Academy of Sciences Beijing 100049 China Beijing SANBODY Technology Company Ltd Beijing 214000 China Qingdao Academy of Intelligent Industries Qingdao 266109 China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

Society 5.0 addresses human behaviors and their consequences in social management, while emphasizing the integration of Cyber-Physical-Social Spaces to achieve a highly connected and circulated society. Prompted by the various social needs expressed on social media platforms, Prescriptive Manufacturing (PM) emerges as a proactive pre-manufacturing paradigm. This paper delves into PM within the context of Society 5.0. It highlights the development of Human autonomous Organizations (HAOs) and the delivery of “on-demand” smart services, which are customized to meet both individual and broader societal demands. The social sensing framework of social needs across different social media platforms that enables the identification and anticipation of consumer demands in real-time is illustrated. This data-driven insight leverages artificial intelligence and robotics to facilitate customized design and on-demand production, aligning product creation with real user requirements. Furthermore, we discuss the implementation of human-centered smart services in PM, such as virtual try-on, virtual fitting, personalized retrofit, user-friendly scheduling, and proximity logistics, which not only enhance consumer experience but also optimize resource efficiency By examining the symbiosis between technological advancements and social need fulfillment, this study sheds light on how PM and HAOs can foster a more responsive, sustainable, and inclusive economy in society, ultimately contributing to a higher quality of life and sustainable development goals of Society 5.0.

关键词： Social Needs Sensing Human autonomous Organization Customized Design personalized fine-tuning prescriptive manufacturing Human-Centric Smart Services

Super-resolution reconstruction method of face image based on attention mechanism

学校读者我要写书评

暂无评论

IEEE Access 2021年

作者： Yu, Chenglin Pei, Hailong Key Laboratory of Autonomous Systems and Networked Control Ministry of EducationUnmanned Aerial Vehicle Systems Engineering Technology Research Center of GuangdongSchool of Automation Scinece and EngineeringSouth China University of TechnologyGuangzhou510640China.

In recent years, convolutional neural network in Single image super-resolution field show good results. Deep networks can establish complex mapping between low-resolution and high-resolution images, making the reconstructed images quality a great progress over traditional methods. In order to be able to generate face images with rich texture details, the algorithm proposed in this paper captures implicit weight information in channel and space domains through dual attention modules, so as to allocate computing resources more effectively and speed up the network convergence. Fusion of global features through residual connections in this network not only focus on learning the high frequency information of images that has been lost, but also accelerate the network convergence through effective feature supervision. In order to alleviate the defects of MAE loss function, a special Huber loss function is introduced in the algorithm. The experimental results on benchmark show that the proposed algorithm has a significant improvement in image reconstruction accuracy compared with existed SISR methods. CCBY

关键词： Convolution

Towards Integrated Traffic control with Operating Decentralized autonomous Organization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yao, Shengyue Yu, Jingru Yu, Yi Xu, Jia Dai, Xingyuan Li, Honghai Wang, Fei-Yue Lin, Yilun Urban Computing Shanghai AI Lab Shanghai China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The Research and Development Center of Transport Industry of Autonomous Driving Technology RIOH High and Technology Group The Institute of Automation Chinese Academy of Sciences Beijing China The Macau Institute of Systems Engineering Macau University of Science and Technology China

关键词： Integrated control

Cross-heterogeneous Domain Authentication Scheme Based on Blockchain

学校读者我要写书评

暂无评论

Journal of Artificial Intelligence and Technology 2021年第2期1卷 92-100页

作者： Jing Liu Yixin Liu Yingxu Lai Rongchen Li Siyu Wu Sami Mian College of Computer Science Faculty of Information TechnologyBeijing University of TechnologyBeijing 100124China Shaanxi Key Laboratory of Network and System Security Xi’an 710071China Science and Technology on Information Assurance Laboratory Beijing 100072China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of EducationBeijing 100124China Fan Gongxiu Honors College Beijing University of TechnologyBeijing 100124China University of Pittsburgh PittsburghPA 15260USA

With the rising popularity of the Internet and the development of big data technology,an increasing number of organizations are opting to cooperate across domains to maximize their *** organizations use public key infrastructure to ensure security in accessing their data and ***,with the continuous development of identity-based encryption(IBE)technology,small-and medium-sized enterprises are increasingly using IBE to deploy internal authentication *** solve the problems that arise when crossing heterogeneous authentication domains and to guarantee the security of the certification process,we propose using blockchain technology to establish a reliable cross-domain authentication *** the distributed and tamper-resistant characteristics of the blockchain,we design a cross-domain authentication model based on blockchain to guarantee the security of the heterogeneous authentication process and present a cross-domain authentication protocol based on *** model does not change the internal trust structure of each authentication domain and is highly ***,on the premise of ensuring security,the process of verifying the signature of the root certificate in the traditional cross-domain authentication protocol is improved to verify the hash value of the root certificate,thereby improving the authentication *** developed prototype exhibits generality and simplicity compared to previous methods.

关键词： public key infrastructure identity-based encryption cross-domain authentication blockchain