检索结果-内蒙古大学图书馆

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Pengxin Yang Dongliang Cui Xuewu Dai Yisheng Lv Hairong Dong Xinghao Wang Ruiguang Liu State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China

The railway system is a complex system because of many constraints, randomness and high security requirements, so it is difficult to establish an accurate mathematical model for it, which brings great challenges to railway scheduling. Parallel intelligence theory can effectively solve the modeling, analysis and control of complex systems, so it has a wide range of applications in the field of intelligent transportation. In this paper, we build an artificial system according to the actual system, and use the surrogate modelling to carry out the calculation experiments, and proposed a parallel scheduling system based on the parallel intelligence method. Select a case to design scenario and perform computational experiment, the scheduling strategy is given and the scheduling strategy is analyzed.

关键词： Data analysis Processor scheduling Transportation Prediction algorithms Rail transportation Scheduling Mathematical models

来源：评论

学校读者我要写书评

暂无评论

A Novel Two-Stage Framework for 2D/3D Registration in Neurological Interventions

A Novel Two-Stage Framework for 2D/3D Registration in Neurol...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Huang, De-Xing Zhou, Xiao-Hu Xie, Xiao-Liang Liu, Shi-Qi Feng, Zhen-Qiu Hao, Jian-Long Hou, Zeng-Guang Ma, Ning Yan, Long The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China The School of Information Shanxi University of Finance and Economics Taiyuan030006 China The CAS Center for Excellence in Brain Science and Intelligence Technology Beijing100190 China The Joint Laboratory of Intelligence Science and Technology Institute of Systems Engineering Macau University of Science and Technology Taipa China The Department of Interventional Neuroradiology Beijing Tiantan Hospital Capital Medical University Beijing100070 China

ISBN: (纸本)9781665481090

2D/3D medical image registration of pre-operative volumes and intra-operative images plays an important role in neurological interventions. However, vast space of transformation parameters makes this task incredibly challenging. In this paper, a novel two-stage framework for 2D/3D registration is proposed. It consists of two basic modules: CNN regression for preliminarily estimating transformation parameters, and centroid alignment for further reducing estimation errors to get refined images. Experimental results on two patients show the proposed framework can achieve superior performances to baseline methods with an inference rate of 22 FPS, satisfying real-time requirements (612 FPS) in clinical practice. Extensive ablation studies prove the effectiveness of centroid alignment in significantly improving registration accuracies. These promising results indicate the framework has the potential to be integrated into navigation frameworks for neurological interventions, facilitating treatments of physicians. © 2022 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Conditional Goal-oriented Trajectory Prediction for Interacting Vehicles with Vectorized Representation

arXiv

引用

arXiv 2022年

作者： Li, Ding Zhang, Qichao Lu, Shuai Pan, Yifeng Zhao, Dongbin School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Baidu Inc. Beijing100085 China

Predicting joint future trajectories of two interacting vehicles faces great challenges, due to the high degree of multimodality and uncertainty in the future interaction process. For the traditional joint prediction models, each vehicle is treated as an individual agent, and its multimodal future modes can be learned from an efficient Goal-oriented Trajectory Prediction (GTP) method. However, such marginal methods produce multimodal self-consistent trajectories over individual agents without considering their future interactions. Motivated by this, this paper aims to tackle the interactive behavior prediction task, and proposes a novel Conditional Goal-oriented Trajectory Prediction (CGTP) framework to jointly generate scene-compliant trajectories of two interacting agents. Our CGTP framework is an end-to-end and interpretable model, including three main stages: context encoding, goal interactive prediction and trajectory interactive prediction. First, a Goals-of-Interest Network (GoINet) is designed to extract the interactive features between agent-to-agent and agent-to-goals using a graph-based vectorized representation. Further, the Conditional Goal Prediction Network (CGPNet) focuses on goal interactive prediction via a combined form of marginal and conditional goal predictors. Finally, the Goal-oriented Trajectory Forecasting Network (GTFNet) is proposed to implement trajectory interactive prediction via the conditional goal-oriented predictors, with the predicted future states of the other interacting agent taken as inputs. In addition, a new goal interactive loss is developed to better learn the joint probability distribution over goal candidates between two interacting agents. In the end, the proposed method is conducted on Argoverse motion forecasting dataset, In-house cut-in dataset, and Waymo open motion dataset. The comparative results demonstrate the superior performance of our proposed CGTP model than the mainstream prediction methods. Copyright © 202

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic

arXiv

引用

arXiv 2022年

作者： Liu, Yuqi Gao, Yinfeng Zhang, Qichao Ding, Dawei Zhao, Dongbin The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China College of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing1000839 China

Multi-task intersection navigation including the unprotected turning left, turning right, and going straight in dense traffic is still a challenging task for autonomous driving. For the human driver, the negotiation skill with other interactive vehicles is the key to guarantee safety and efficiency. However, it is hard to balance the safety and efficiency of the autonomous vehicle for multi-task intersection navigation. In this paper, we formulate a multi-task safe reinforcement learning with social attention to improve the safety and efficiency when interacting with other traffic participants. Specifically, the social attention module is used to focus on the states of negotiation vehicles. In addition, a safety layer is added to the multi-task reinforcement learning framework to guarantee safe negotiation. We compare the experiments in the simulator SUMO with abundant traffic flows and CARLA with high-fidelity vehicle models, which both show that the proposed algorithm can improve safety with consistent traffic efficiency for multi-task intersection navigation. Copyright © 2022, 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

Novel PIO Algorithm with Multiple Selection Strategies for Many-Objective Optimization Problems

引用

complex System Modeling and Simulation 2021年第4期1卷 291-307页

作者： Zhihua Cui Lihong Zhao Youqian Zeng Yeqing Ren Wensheng Zhang Xiao-Zhi Gao School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030024China School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Intelligent Control and Management of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Computing University of Eastern FinlandKuopioFI-70211Finland

With the increase of problem dimensions,most solutions of existing many-objective optimization algorithms are ***,the selection of individuals and the retention of elite individuals are *** algorithms cannot provide sufficient solution precision and guarantee the diversity and convergence of solution sets when solving practical many-objective industrial ***,this work proposes an improved many-objective pigeon-inspired optimization(ImMAPIO)algorithm with multiple selection strategies to solve many-objective optimization *** selection strategies integrating hypervolume,knee point,and vector angles are utilized to increase selection pressure to the true Pareto ***,the accuracy,convergence,and diversity of solutions are *** is applied to the DTLZ and WFG test functions with four to fifteen objectives and compared against NSGA-III,GrEA,MOEA/D,RVEA,and many-objective Pigeon-inspired optimization *** results indicate the superiority of ImMAPIO on these test functions.

关键词： pigeon-inspired optimization algorithm many-objective optimization problem multiple selection strategy elite individual retention

来源：评论

学校读者我要写书评

暂无评论

Backstepping-Based Parallel control for Cascaded Nonlinear systems

Backstepping-Based Parallel Control for Cascaded Nonlinear S...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Jingwei Lu Qinglai Wei Tianmin Zhou Liyuan Han Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Beijing China

In this study, a novel nonlinear parallel control method is proposed for cascaded nonlinear systems using the backstepping technique. Unlike the existing state feedback control methods, the control input is taken into the feedback system. First, an augmented system is constructed to facilitate the constructing the Lyapunov function. Then, the backstepping technique can be applied to obtain the nonlinear parallel control law, and the stability analysis is shown using the Lyapunov theory. Finally, a simulation is conducted to demonstrate the effectiveness of the proposed parallel control method.

关键词： state feedback Backstepping Simulation Digital twin Conferences control systems Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Parallel control-Based Event-Triggered Optimal control for Constrained Discrete-Time Nonlinear systems

Parallel Control-Based Event-Triggered Optimal Control for C...

引用

Chinese automation Congress (CAC)

作者： Jingwei Lu Tianxiang Bai Qinglai Wei Tianmin Zhou Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Beijing China

ISBN: (纸本)9781665426480

This study proposes a new event-triggered optimal control (ETOC) method for discrete-time (DT) constrained nonlinear systems. First, a new triggering condition is proposed. We show the asymptotic stability of the closed-loop system using the proposed triggering condition and analyze the degeneration degree of the real performance index. Second, to perform the proposed ETOC method effectively, parallel control (PC) combined with adaptive dynamic programming (ADP) is applied. Finally, the validity of the ETOC method is validated by a simulation.

关键词： Degradation Asymptotic stability Adaptation models Stability criteria Optimal control Performance analysis Trajectory

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Generalization of 3D Detectors with Hybrid Point Clouds

Evaluating the Generalization of 3D Detectors with Hybrid Po...

引用

Computer Science and management Technology (ICCSMT), International Conference on

作者： Yonglin Tian Xiao Wang University of Science and Technology of China Hefei China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665420648

With the development of LiDAR technologies and deep learning algorithms, tremendous methods have been proposed for 3D detection in intelligent transportation. However, the generalization of 3D detectors under different environments is not fully evaluated due to the lack of diverse testing datasets. Two of the main obstacles in building testing benchmark of point clouds are the huge cost of the annotation of point clouds and the low flexibility in data collection. In this paper, we propose to use hybrid point clouds to evaluate the generalization of multiple 3D detectors when they are transferred from real data to hybrid data. Compared with evaluating 3D detectors with real point clouds dataset, our approach is much more flexible and demands less human labor.

关键词： Point cloud compression Cloud computing Three-dimensional displays Laser radar Costs Pipelines Transportation

来源：评论

学校读者我要写书评

暂无评论

Design of a curled hyper-redundant manipulator and the motion control with tip-following algorithm

Design of a curled hyper-redundant manipulator and the motio...

引用

Chinese control and Decision Conference, CCDC

作者： Aoshun Zhang En Li Feng Zhang Rui Guo Mingrui Luo Yuwei Zhang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Engineering Laboratory for Intelligent Industrial Vision CAS Beijing China State Grid Intelligent Technology Co. Ltd. Shandong China State Grid Shandong Electric Power Company Jinan Power Supply Company Shandong China

In order to meet the operational needs in some narrow environments, the hyper-redundant snake-shaped manipulator has received extensive attention and has been widely studied due to its compact shape and multiple degrees of freedom. At present, the research of hyper-redundant manipulator mainly focuses on the straight push platform. Considering the limitation of working space, this paper designed a hyper-redundant manipulator delivered by a curled turntable. According to the characteristics of turntable delivery, a tip-following algorithm based on curve fitting and a tip-following strategy based on terminal posture record are proposed. Finally, with the algorithm applied to the physical robot we made, we successfully realized the tip-following motion control of the hyper-redundant manipulator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mechanical Design Paradigm based on ACP Method in Parallel Manufacturing

Mechanical Design Paradigm based on ACP Method in Parallel M...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Shimeng Li Yutong Wang Xiao Wang Feiyue Wang 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 Qingdao China

Parallel Manufacturing is a new manufacturing paradigm in industry, deeply integrating informalization, automation, and artificial intelligence. In this paper we propose a new mechanical design paradigm in Parallel Manufacturing based on ACP method. The key is to regard the design procedure based on artificial design and emulation method as two independent procedures, which can be modeled as a parallel system. The design procedure based on ACP method does not include a real system, which is an inventive extension of the traditional parallel system. This method can be implemented with social information by introducing the definition of SDV, SDM, and Intelligent Design Manager, making it highly adaptive for social manufacturing and Parallel Manufacturing.

关键词： Industries Adaptation models automation Digital twin Design methodology Conferences Emulation

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：