检索结果-内蒙古大学图书馆

2022 Chinese automation Congress, CAC 2022

作者： Si, Zeze Zhao, Hongxia Tang, Haina Zhu, Fenghua Lv, Yisheng Lu, Hao Institute of Autamation Chinese Academy of Sciences State Key Laboratory for Management and Control of Complex Systems Beijing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Qingdao Academy of Intelligent Industries Qingdao266000 China

ISBN: (纸本)9781665465335

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. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Lane-changing Decision-making for Deep Reinforcement Learning 21

Benchmarking Lane-changing Decision-making for Deep Reinforc...

引用

Proceedings of the 7th International Conference on Robotics and Artificial Intelligence

作者： Junjie Wang Qichao Zhang Dongbin Zhao The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences China and College of Artificial Intelligence University of Chinese Academy of Sciences China

ISBN: (纸本)9781450385855

The development of autonomous driving has attracted extensive attention in recent years, and it is essential to evaluate the performance of autonomous driving. However, testing on the road is expensive and inefficient. Virtual testing is the primary way to validate and verify self-driving cars, and the basis of virtual testing is to build simulation scenarios. In this paper, we propose a training, testing, and evaluation pipeline for the lane-changing task from the perspective of deep reinforcement learning. First, we design lane change scenarios for training and testing, where the test scenarios include stochastic and deterministic parts. Then, we deploy a set of benchmarks consisting of learning and non-learning approaches. We train several state-of-the-art deep reinforcement learning methods in the designed training scenarios and provide the benchmark metrics evaluation results of the trained models in the test scenarios. The designed lane-changing scenarios and benchmarks are both opened to provide a consistent experimental environment for the lane-changing task1 .

关键词： Autonomous driving Reinforcement learning Lane change scenarios

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

Discrete-time Linear Tracking control Based on Parallel System Theory

引用

Applied Mathematics and Nonlinear Sciences 2024年第1期9卷

作者： Gao, Junjie Chen, Mingliang Wei, Qinglai The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment China Nuclear Power Engineering Co. Ltd Guangdong Shenzhen518172 China

Inspired by parallel system theory, a novel parallel tracking controller is presented for discrete-time linear systems in this paper. The core point is to model the time derivative of system control, which makes the control system and the control law completely equivalent in mathematical form. First, the architecture of discrete-time linear parallel tracking control is introduced. Then, in the sight of the reachability of control systems, the pole assignment theorems are given. The merits of this presented method comparing with traditional feedback control are analyzed. Eventually, the efficiency of this method is proved through numerical results. © 2024 Gao, J., Chen, M. & Wei, Q.

关键词： Discrete time control systems

来源：评论

学校读者我要写书评

暂无评论

Short-term wind power forecast with turning weather based on DBSCAN-RFE-LightGBM

引用

Renewable Energy 2025年 251卷

作者： Wu, Zhenlong Fan, Xinyu Bian, Guibin Liu, Yanhong Zhang, Xiaoke Chen, YangQuan School of Electrical and Information Engineering Zhengzhou University Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Zhengzhou University Luoyang471000 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Electric Power Research Institute of State Grid Henan Electric Power Company Zhengzhou450052 China Lab Department of Mechanical Engineering School of Engineering University of California MercedCA95343 United States

At present, the wind power prediction technology is becoming more and more mature, however, the turning weather brings a decrease in prediction accuracy due to its suddenness and instability. In this paper, a wind power prediction method considering the turning period and non-turning period respectively is proposed to weaken the adverse effects caused by turning weather. Firstly, the prediction effects of multiple models are compared, density-based spatial clustering of applications with noise (DBSCAN) is selected as the outlier processing method, recursive feature elimination (RFE) is used as the feature selection method, and Light gradient boosting machine (LightGBM) is used for prediction. The combined prediction method based on DBSCAN-RFE-LightGBM can reduce the influence of abnormal data and redundant features and improve the prediction effect. Then, the sliding window is set to detect the turning period. Considering that the turning weather is an emergency and does not happen frequently, the amount of data is small, which leads to the inability to train the model well. Generative adversarial networks (GAN) are applied to expand the turning period data. The LightGBM is trained and predicted by using the expended turning period data. Finally, the time-division prediction results are merged. Using the data collected from wind farms for short-term power prediction experiments, the time-segment prediction method proposed in this paper with GAN reduces MAE by 1.913 and RMSE by 3.351 on a single unit compared with the non-differentiated period. © 2025 Elsevier Ltd

关键词： Merging

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

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

Cyber-physical -social systems for smart cities: An overview 1

Cyber-physical -social systems for smart cities: An overview

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Anwar, Noreen Xiong, Gang Lu, Wanze Ye, Peijun Zhao, Hongxia Wei, Qinglai Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation The Cloud Computing Center Chinese Academy of Sciences China School of Artificial Intelligence and Automation Beijing University of Technology Beijing100124 China

ISBN: (纸本)9781665433372

Cyber-physical social systems (CPSS) include cyberspace, physical space, and social space. Since the introduction of CPSS, human relationships with machinery and the physical world have altered as a new paradigm. Recent estimates indicate that approximately 60 percent of the world's population will live in cities by 2030. Large, dense cities can be highly productive, innovative, and very green per capita, hence ideal for our future. However, the huge influx of new people poses enormous challenges to their administrations. Smart cities are becoming a reality, therefore, to achieve higher efficiency, optimum use of resources, management and to strengthen several features of modern towns, several elements of modern cities are automated and integrated into Information and Communications Technology (ICT). Cities and infrastructure are growing all over the world, in providing end-users with increased performance, comfort, visibility and convenience, the Smart Cities concept is critical. This paper will discuss smart cities and the CPSS concept intensively with some of its key technologies, challenges, and further development by using CPSS. © 2021 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Line-of-sight based three-dimensional path following control for an underactuated robotic dolphin

引用

Science China(Information Sciences) 2021年第1期64卷 215-226页

作者： Jincun LIU Zhenna LIU Junzhi YU State Key Laboratory for Turbulence and Complex System Department of Mechanics and Engineering ScienceBIC-ESATCollege of EngineeringPeking University Department of Electrical and Automation Shandong Labor Vocational and Technical College State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

This paper investigates the three-dimensional(3-D) path following control problem for an underactuated robotic dolphin. With a comprehensive consideration of the mechanical constraint and swimming principle of the robotic dolphin, a decoupling motion strategy is proposed to produce yaw and pitch maneuvers simultaneously. Then, kinematics and dynamics models for 3-D dolphin-like swimming are established,followed by simulations of the path following control. Furthermore, a novel lookahead based 3-D line-ofsight(LOS) guidance law is developed and implemented to obtain desired attitude angles with its simplicity,intuitiveness, and small computational footprint. Finally, simulation results illustrate the feasibility and effectiveness of the proposed path following control methods.

关键词： robotic dolphin path following 3-D LOS guidance law decoupling motion

来源：评论

学校读者我要写书评

暂无评论

Temperature control System of Thermoelectric Cooler Based on Improved ADRC

Temperature Control System of Thermoelectric Cooler Based on...

引用

Chinese control and Decision Conference, CCDC

作者： Xiyuan Shan Tao Cai Zhicheng Zong Hongbo Mu School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing China

ISBN: (纸本)9781665478977

Aiming at the problems containing complex working conditions, modeling difficulties and long-time delay of thermoelectric cooler temperature control system, an improved ADRC control method combining ADRC and Smith predictor is proposed in this paper. ADRC deals with the disturbances and uncertain dynamics in the system, SP compensates the time delay to improve the control performance. Compared with the traditional PID controller, the proposed control method has faster response speed and stronger anti-disturbance ability, meanwhile, overcomes the dependence of Smith predictor on object parameters to a certain extent. Through simulation and experimental verification, a good control effect is obtained, which provides a positive guidance of the related application of thermoelectric cooler.

关键词： Robust control Employee welfare Delay effects Simulation Perturbation methods Predictive models control systems

来源：评论

学校读者我要写书评

暂无评论

An Improved Active Disturbance Rejection control Method for Crane System

An Improved Active Disturbance Rejection Control Method for ...

引用

Chinese control and Decision Conference, CCDC

作者： Yubo Sun Xiyuan Shan Zhicheng Zong School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing China

ISBN: (纸本)9781665478977

In order to improve the dynamic performance of the underdriven crane system, an improved linear active disturbance rejection controller (LADRC) based on the new error was proposed. The improved LADRC takes the error value between the disturbance and its observed value multiplied by a coefficient as the basis for adjusting the linear extended state observer (LESO). The improved method has two advantages. Firstly, the new error can prevent the traditional LESO from choosing larger parameter adjustment disturbances, which will limit the performance of the observer. Secondly, the pole can be configured by adjusting the coefficient to obtain better dynamic characteristics. Finally, the effectiveness of the proposed method is verified by simulation and experiment. The proposed method can effectively restrain the swing of the payload and it is robust to system parameters perturbation as well.

关键词： Robust control Couplings Adaptation models Cranes Uncertainty Perturbation methods Bandwidth

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：