检索结果-内蒙古大学图书馆

第40届中国控制会议

作者： LI Bin WANG Shoukun WANG Shuai WANG Junzheng LIU Shangfei State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Key Laboratory of Servo Motion System Drive and Control Ministry of Industry and Information Technology Beijing Institute of Technology

In order to meet the demand for high-precision operation of the vibroseis vehicle in the case of unmanned driving, an unmanned operation system that meets the working characteristics of the vibroseis vehicle is designed, and the key technical problems are studied, so that the vibroseis vehicle can operate in the complex environment of the field and improve the efficiency of geological exploration greatly. Firstly, the coordinate system and the kinematic model without sideslip of the articulated vehicle are established successively. Secondly, in order to improve the path tracking accuracy of the vibroseis vehicle, a model predictive control algorithm based on the kinematic model is designed for vehicle path tracking. In order to improve the positioning accuracy of the working point, a compensation algorithm for positioning error is proposed to reduce the positioning error caused by terrain factors. Finally, the unmanned operation platform is built and the path tracking algorithm and the compensation algorithm for positioning error are verified on the platform. The real vehicle test data shows that the path tracking algorithm proposed in this paper can control the average lateral error of the path tracking of the vibroseis vehicle within 22 *** with the PID control method, its path tracking accuracy can be improved by 59%. The average positioning error of working point is controlled within about 15 cm by adopting the compensation algorithm for positioning error.

关键词： Vibroseis vehicle Unmanned operation Path tracking Positioning compensation

来源：评论

学校读者我要写书评

暂无评论

A Novel Agricultural Data Sharing Mode Based on Rice Disease Identification

引用

Plant Diseases and Pests 2024年第2期15卷 9-16页

作者： Mengmeng ZHANG Xiujuan WANG Mengzhen KANG Jing HUA Haoyu WANG Feiyue WANG State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of AutomationChinese Academy of SciencesBeijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China State Key Laboratory for Management and Control of Complex System Institute of AutomationChinese Academy of SciencesBeijing 100190China

In this paper,a variety of classical convolutional neural networks are trained on two different datasets using transfer learning *** demonstrated that the training dataset has a significant impact on the training results,in addition to the optimization achieved through the model ***,the lack of open-source agricultural data,combined with the absence of a comprehensive open-source data sharing platform,remains a substantial *** issue is closely related to the difficulty and high cost of obtaining high-quality agricultural data,the low level of education of most employees,underdeveloped distributed training systems and unsecured data *** address these challenges,this paper proposes a novel idea of constructing an agricultural data sharing platform based on a federated learning(FL)framework,aiming to overcome the deficiency of high-quality data in agricultural field training.

关键词： Rice disease and pest identification Convolutional neural networks Distributed training Federated learning(FL) Open-source data sharing platform

来源：评论

学校读者我要写书评

暂无评论

System Dynamics-Based Analysis on Factors Influencing Comprehensive Competence of Primary and Secondary School Students

System Dynamics-Based Analysis on Factors Influencing Compre...

引用

Chinese Automation Congress (CAC)

作者： Sifeng Jing Xiwei Liu Xiaoyan Gong Hongxia Zhao The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Institute of Automation Beijing China Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Qingdao China

With rapid progress of artificial intelligence (AI) , it is urgent to promote educational reform to improve comprehensive competence level of primary and secondary school students (CCLPSSS). However, educational reform is a system engineering involving multiple and intertwined factors. In this research, a system dynamics-based model of education reform is developed. Then, based on this model, a series of simulation experiments are carried out to find main factors affecting improvement of CCLPSSS. Results show that: 1) this model could simulate trends of CCLPSSS under different educational reform measures; 2) Measures including teaching mode reform, development and application of AI-based new teaching method, implementation of Double Reduction in compulsory education, implementation of deepening education evaluation reform policy, and development and application of AI-based education evaluation technology could play significant roles in promoting CCLPSSS and further strengthening cultivation of AI compound talents.

关键词： Analytical models Text analysis System dynamics Education decision making Predictive models Market research

来源：评论

学校读者我要写书评

暂无评论

Optimization of Robot End-Effector Load Gravity Compensation for Unmanned Live Work in Electric Power Distribution Networks Based on Improved PSO Algorithm

Optimization of Robot End-Effector Load Gravity Compensation...

引用

2023 China Automation Congress, CAC 2023

作者： Chen, Jinge Chen, Xin Hu, Chenyu Huang, Guangxian Sun, Shu Jian, Xu School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering-Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China State Grid Hubei Electric Power Co. Ltd. Xianning Power Supply Company Distribution Department Xianning437000 China State Grid Hubei Electric Power Co. Ltd. Electric Power Science Research Institute Equipment Technology Center Wuhan430077 China

ISBN: (纸本)9798350303759

In the field of electric power distribution network operation, most tasks involve contact operations. A key technology to enable the flexible operation of robots in live distribution network tasks is the installation of six-dimensional force sensors on the robot's end flange. These sensors allow the robot to perceive external environmental contact forces. However, the presence of the end load interferes with the accurate perception of external forces. Aiming at the gravity compensation of robot end load, an optimization algorithm of gravity compensation based on particle swarm optimization is proposed. In this method, the optimal solution model is established with the objective of minimum sum of squared errors, and the particle swarm optimization algorithm is used to estimate the mounting declination angle of the force sensor and improve the precision of gravity compensation. The experiments show that the proposed method can effectively reduce the maximum gravity compensation error and the average gravity compensation error in each direction after optimization, in which the maximum gravity compensation error of the resultant force is reduced by 9.11% and the average gravity compensation error of the resultant force is reduced by 12.34%. © 2023 IEEE.

关键词： Error compensation

来源：评论

学校读者我要写书评

暂无评论

CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition

arXiv

引用

arXiv 2024年

作者： Zheng, Jinzhi Ji, Ruyi Zhang, Libo Wu, Yanjun Zhao, Chen Intelligent Software Research Center Institute of Software Chinese Academy of Sciences Beijing100190 China The Laboratory of Cognition and Decision Intelligence for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing100190 China

Scene text recognition, as a cross-modal task involving vision and text, is an important research topic in computer vision. Most existing methods use language models to extract semantic information for optimizing visual recognition. However, the guidance of visual cues is ignored in the process of semantic mining, which limits the performance of the algorithm in recognizing irregular scene text. To tackle this issue, we propose a novel cross-modal fusion network (CMFN) for irregular scene text recognition, which incorporates visual cues into the semantic mining process. Specifically, CMFN consists of a position self-enhanced encoder, a visual recognition branch and an iterative semantic recognition branch. The position self-enhanced encoder provides character sequence position encoding for both the visual recognition branch and the iterative semantic recognition branch. The visual recognition branch carries out visual recognition based on the visual features extracted by CNN and the position encoding information provided by the position self-enhanced encoder. The iterative semantic recognition branch, which consists of a language recognition module and a cross-modal fusion gate, simulates the way that human recognizes scene text and integrates cross-modal visual cues for text recognition. The experiments demonstrate that the proposed CMFN algorithm achieves comparable performance to stateof- the-art algorithms, indicating its effectiveness. © 2024, CC BY.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

An Immersive Learning System with Multimodal Cognitive Processes Inference

An Immersive Learning System with Multimodal Cognitive Proce...

引用

Chinese Automation Congress (CAC)

作者： Siyu Bian Xiwei Liu Hongxia Zhao Xiaoyan Gong Sifeng Jing The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Qingdao Academy of Intelligent Industries Institute of Smart Education Systems Qingdao China

Using multimodal technology to infer learners’ cognitive processes is an important means to support personalized learning. Previous cognitive process analysis is more about subjective reasoning, and less about combining physiological signals. With the rapid development of virtual reality technology, new requirements and more immersive schemes for learner’s cognitive process inferring have been proposed. Based on this, this paper proposes an immersive learning system with multimodal cognitive processes inference, which is composed of macro, mesoscopic and micro environments. The system analyzes learner’s actions, emotions and attention to infer learner’s cognitive process through more comprehensive and objective multimodal data. The system also combines eye movement, brainwaves and other data, and proposes a multimodal data acquisition and analysis scheme using HMD-based VR. This paper also provides an immersive learning cognitive processes inference scheme for individual online learning, offline classroom learning scenarios.

关键词： Learning systems Automation Cognitive processes Data acquisition Virtual reality Physiology

来源：评论

学校读者我要写书评

暂无评论

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

引用

Frontiers of Information Technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning

来源：评论

学校读者我要写书评

暂无评论

Research on intelligent methods in virtual reality games

Research on intelligent methods in virtual reality games

引用

Chinese Automation Congress (CAC)

作者： JiaWei Wang Xiwei Liu Xiaoyan Gong The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Smart Education Systems Qingdao Academy of Intelligent Industries Qingdao China

Introduction of virtual reality technology enriches the expression of traditional games and greatly improves the sense of substitution and interactive experience of users. Realization of virtual reality is inseparable from artificial intelligence technology. In order to improve immersion and interactivity of virtual reality games, it is necessary to propose more intelligent solutions to existing technologies. This paper aims to discuss some intelligent methods of virtual reality games. Firstly, it discusses artificial intelligence means to enhance the virtual reality experience, which can improve the tracking and force / tactile interaction system of existing virtual reality games from software and hardware aspects; Then it proposes the concept of human-machine hybrid enhanced intelligence: by introducing human cognitive model to improve perception and decision-making ability of virtual reality games, so as to make interaction of virtual reality games more friendly and more real.

关键词： Solid modeling Human intelligence Force Virtual reality Games Reinforcement learning Software

来源：评论

学校读者我要写书评

暂无评论

Collaborative Scheduling of Computing Tasks for Edge Computing

Collaborative Scheduling of Computing Tasks for Edge Computi...

引用

2021 China Automation Congress, CAC 2021

作者： Liu, Yue Xiong, Gang Zhu, Fenghua Chen, Shichao Zhang, Liguo Liu, Xudong School of Artificial Intelligence and Automation Beijing University of Technology The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation The Cloud Computing Center Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Qingdao Academy of Intelligent Industries Chinese Academy of Sciences Beijing China Faculty of Information and Technology Beijing University of Technology Beijing China

ISBN: (纸本)9781665426473

In the face of the rapid development of the IoT, the traditional cloud computing, while providing services for mobile intelligent devices, also brings problems such as network bandwidth occupation and communication delay. Edge computing can solve these problems to some extent. But too many offloaded tasks may result in an edge server becoming overloaded and execution delay of tasks increasing, the computing resources of idle edge devices are also not fully utilized. In order to make full use of the computing resources of idle edge devices in the local network and reduce the execution delay for computing tasks, this paper takes the average delay time for all end devices as the optimization objective and proposes an end-edge cooperative scheduling (EECS) model to schedule tasks for edge computing. The scheduling algorithm used in EECS model is improved based on MCT algorithm. We use the EdgeCloudSim to verify the EECS model and scheduling algorithm. The simulation results show that the average completion time of computing tasks in EECS model, compared with only single edge server (SEE) task computing model, can be reduced by up to three times. In addition, the system load can be balanced to a certain extent in local network. © 2021 IEEE

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Pedestrian Trajectory Prediction by Modeling the Interactions using Social LSTM Extensions

Pedestrian Trajectory Prediction by Modeling the Interaction...

引用

Chinese Automation Congress (CAC)

作者： Zeze Si Hongxia Zhao Haina Tang Fenghua Zhu Yisheng Lv Hao Lu State Key Laboratory for Management and Control of Complex Systems Institute of Autamation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academic of Sciences Beijing China Qingdao Academy of Intelligent Industries Qingdao China

In many driving situations, human mobility is an important topic in trajectory prediction. Considering the pedestrian trajectory as a sequence generative task, a prediction algorithm based on Social Long Short-Term Memory (Social LSTM) is implemented. In order to simulate the social interaction between pedestrians, Social Pooling (S-Pooling) is used to aggregate the hidden state of pedestrians, while the attention mechanism is utilized to aggregate information differently according to the importance of surrounding pedestrians. Furthermore, Convolutional Neural Networks (CNN) is introduced into Social LSTM model to consider both the interaction between people and the characteristic of scene scale in the prediction process. Experiments are carried out against baseline methods, and the results demonstrated that combining Social LSTM with attention mechanism or CNN can improve the performance of pedestrian trajectory prediction.

关键词： Automation Aggregates Predictive models Prediction algorithms Trajectory Convolutional neural networks Task analysis

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：