检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xin, Jinghao Liang, Zhichao Zhang, Zihuan Wang, Peng Li, Ning Department of Automation Shanghai Jiao Tong University Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China

Deep Reinforcement Learning (DRL) has demonstrated potential in addressing robotic local planning problems, yet its efficacy remains constrained in highly unstructured and dynamic environments. To address these challenges, this study proposes the ColorDynamic framework. First, an end-to-end DRL formulation is established, which maps raw sensor data directly to control commands, thereby ensuring compatibility with unstructured environments. Under this formulation, a novel network, Transqer, is introduced. The Transqer enables online DRL learning from temporal transitions, substantially enhancing decision-making in dynamic scenarios. To facilitate scalable training of Transqer with diverse data, an efficient simulation platform E-Sparrow, along with a data augmentation technique leveraging symmetric invariance, are developed. Comparative evaluations against state-of-the-art methods, alongside assessments of generalizability, scalability, and real-time performance, were conducted to validate the effectiveness of ColorDynamic. Results indicate that our approach achieves a success rate exceeding 90% while exhibiting real-time capacity (1.2–1.3 ms per planning). Additionally, ablation studies were performed to corroborate the contributions of individual components. Building on this, the OkayPlan-ColorDynamic (OPCD) navigation system is presented, with simulated and real-world experiments demonstrating its superiority and applicability in complex scenarios. The codebase and experimental demonstrations have been open-sourced on our website1 to facilitate reproducibility and further research. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Leader-Following Entrapping control of AUVs Using Bearing Measurements in Local Coordinate Frames

引用

Guidance, Navigation and control 2022年第4期2卷 85-121页

作者： Yingbo Fu Ziwen Yang Shanying Zhu Cailian Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240P.R.China Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai 200240P.R.China Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240P.R.China

In this paper,the entrapping control problem of discrete-time AUVs with local coordinate frames is *** achieve entrapment in arbitrarily shaped orbits and formations,we design a bearingbased leader-following framework fully in the discrete-time domain with four parts:the orientation estimation unit,estimator unit,controller unit and parameters tuning *** bearing measurements and communication information,the orientation estimation unit can estimate orientations of local coordinate frames infinite time,and the estimator unit can achieve local *** on estimation,the controller unit can drive each AUV to track the desired orbit or formation with an arbitrary *** present su±cient conditions under which stability of the overall system is proved using the theorem offinite-time stability and LaSalle's theorem for the discrete-time ***,the parameters tuning unit can calculate optimal parameters to improve overall ***,we extend our schemes to nonholonomic AUVs with unicycle ***,simulation results demonstrate the effectiveness of the proposed scheme.

关键词： Entrapping control discrete-time AUVs bearing measurements local coordinate frames

来源：评论

学校读者我要写书评

暂无评论

Designing Cluster Consensus on Higher-Order Interaction Networks

Designing Cluster Consensus on Higher-Order Interaction Netw...

引用

IEEE Conference on Decision and control

作者： Haoyu Wei Lulu Pan Haibin Shao Dewei Li Wenbin Yu Shibei Xue Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China

This paper examines the cluster consensus design problem on higher-order interaction networks. Specifically, the higher-order interaction mechanism is captured by matrix-weighted networks that allow the interdependency across the dimensions of the agents' states, and the matrix-valued weight matrices $A_{ij}\in \mathbb{R}^{d\times d}$ associated with specific edges are further assumed to share the same nullspace for design purposes. Under mild assumptions on network connectivity, we first examine the case that the nullspace of positive semi-definite edges is spanned by a nonzero vector $\boldsymbol{\xi}\in \mathbb{R}^{d}$ and show that the predictable cluster consensus can be achieved, which is eventually located in the 1-dimensional linear space determined by span $\{\boldsymbol{\xi}\}$ and the average of agents' initial states. Moreover, the transient state of agents in each cluster can also be explicitly characterized. Namely, the derivative of the average state of agents in each cluster is perpendicular to span $\{\boldsymbol{\xi}\}$ . To generalize the above results, we proceed to examine the case that the nullspace of positive semi-definite edges is spanned by more than one linearly independent $d$ -dimensional vector, in which case, analogous results can be obtained, and the explicit geometric interpretation is also provided.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent Backflow Prevention system

Design of Intelligent Backflow Prevention System

引用

Chinese control Conference (CCC)

作者： Jiale Chen Tao Dong Shiyun Wang Guili Jiao Rongrong Zhang Xincheng Tian Center for Robotics Engineering Research Center of Intelligent Unmanned System Ministry of Education School of Control Science and Engineering Shandong University Jinan China Jinan China Shandong Tianyong Intelligent Technology Co. Ltd Jinan China Shandong Hydrology Center Jinan China

With the advent of the rainy season, the chances of urban flooding are increasing, to avoid the risk of flooding people and underground garages, this paper explains our reliance on video surveillance technology and 5G cloud data technology to collect the data of anti-backflow door equipment deployed in various parts of the city, and remote control and command in the management center, which can quickly give flood control measures and early warning to protect the personnel and property of underground garages, and reduced losses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Flight Test of a Compact and Rapidly-Deployable Air-Launched Inflatable-Winged Aircraft

Design and Flight Test of a Compact and Rapidly-Deployable A...

引用

AIAA Science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Ge, Hang Xu, Yixiang Sun, Donglei Chen, Xinmin Chen, Boyang School of Aerospace Faculty of Science and Engineering University of Nottingham Ningbo China Zhejiang Ningbo315100 China Department of Mechanical Materials and Manufacturing Engineering UNNC-NFTZ Blockchain Laboratory University of Nottingham Ningbo China Zhejiang Ningbo315100 China Advanced Intelligent Manufacturing Research Group Control System Lab University of Nottingham Ningbo China Zhejiang Ningbo315100 China Zhejiang Provincial Engineering Research Center of Special Aircraft Ningbo Institute of Materials Technology & Engineering Chinese Academy of Sciences Zhejiang Ningbo315100 China

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

In this research, a high-altitude, compact and rapidly deployable, air-launched, inflatablewinged aircraft is designed, developed, and flight-tested to investigate the flight characteristics of inflatable-winged aircraft as well as the in-flight inflation and dynamic deployment properties when launched from various carriers. To start with, two types of inflatable wings employing different materials have been designed, fabricated, and tested, the tests including structural characteristics tests, inflation properties tests, and low-Reynolds-number wind-tunnel tests. A full-scale 30-kilogram prototype unmanned aerial vehicle with inflatable wings was then designed, assembled and tested with some basic low-altitude flights to verify the feasibility of the aerodynamic layout and the trim and stability and control characteristics. Finally, low- and high-altitude in-flight launches will be conducted to study the dynamic deployment properties and high-altitude flight characteristics of this design. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Wind tunnels

来源：评论

学校读者我要写书评

暂无评论

Anti-Disturbance Formation control of Quadrotor UAVs Based on Terminal Sliding Mode control

Anti-Disturbance Formation Control of Quadrotor UAVs Based o...

引用

Chinese Automation Congress (CAC)

作者： Ying Xin Hao Ni Zihao Huang Yongning He Sigang Xia Intelligent Flight Control Technology Research and Development Center Shanghai Aerospace Control Technology Institute Shanghai China Electrical system laboratory Shanghai Institute of Mechanical and Electrical Engineering Shanghai China

In this paper, the anti-disturbance formation flight control of quadrotor UAVs system is realized based on terminal sliding mode control. The generalized error state is designed for each quad-rotor UA V, based on which the formation control target is proposed. In order to achieve the goal of anti-disturbance formation control, a formation controller based on terminal sliding mode control is designed. Finally, the general error states of all quadrotor UAVs converge to zero to achieve the desired formation. Finally, a simulation example is given to verify the effectiveness of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distributed Neighbor Selection on Matrix-weighted Networks

Distributed Neighbor Selection on Matrix-weighted Networks

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Haoyu Wei Lulu Pan Haibin Shao Dewei Li Department of Automation and Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China

This paper explores distributed neighbor selection in matrix-weighted networks, where a matrix-valued weight captures the interdependencies among agents’ states. We demonstrate the feasibility of preserving and, in certain cases, improving the convergence rate of matrix-weighted networks by having agents exclusively engage with a subset of their neighbors. Leveraging the inherent monotonicity of Laplacian matrix eigenvectors, we introduce a novel neighbor selection criterion that reduces network connections while enhancing convergence rates. Existing neighbor selection strategies often require acquiring information from all nodes before making decisions. In order to propose a distributed neighbor selection strategy for matrix-weighted networks, we establish a numerical relationship between Laplacian eigenvectors and a locally measurable metric. In essence, this paper extends prior findings from scalar-weighted networks to matrix-weighted networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task Order Filing Generation Algorithm Based on Multidimensional Association Rules and Similarity Matching

Task Order Filing Generation Algorithm Based on Multidimensi...

引用

2024 International Conference Optoelectronic Information and Optical engineering, OIOE 2024

作者： Zhang, Xinyue Lv, Weimin Wei, Dingjiang Yang, Dongsheng Yang, Lin Naval Aviation University Yantai China No. 91593 of PLA Sanya China The Laboratory for Military-Civilian Integration Emergency Command and Control Jinan University Guangzhou China School of Public Management/Emergency Management Jinan University Guangzhou China Key Laboratory of Information System Engineering National University of Defense Technology Changsha China School of Information and Intelligent Engineering University of Sanya Academician Guoliang Chen Team Innovation Center University of Sanya Sanya China

ISBN: (数字)9781510688209

ISBN: (纸本)9781510688193

This paper examines the potential for leveraging the order dispatch algorithm in the commercial domain to enhance the intelligent allocation of military combat tasks, thereby improving the speed and accuracy of command decision-making in the context of intelligent warfare. The study proposes an "order-based" command and control model, which aims to overcome the efficiency bottleneck and information lag problem in traditional combat task allocation. The algorithmic design incorporates multi-dimensional association rules and similarity matching algorithms to guarantee the optimal matching of combat tasks and resources, thereby achieving the objectives of rapid response, efficient resource utilization, and enhanced combat effectiveness. This paper focuses on the challenges and advantages of this model in the context of naval warfare. It highlights the strategic value of order-based command and control in non-direct confrontation missions, such as reconnaissance, patrol, and intelligence gathering. The utilization of the "combat cloud," artificial intelligence, and a highly integrated command network enables the precise allocation of resources and the rapid execution of tasks. This, in turn, enhances the ISR capability, network-centered warfare effectiveness, and cross-domain synergistic warfare capability in naval warfare. The study also delineates the specific implementation process of the algorithm, which includes multi-dimensional association rule mining and similarity matching based on historical cases, with the objective of generating optimal combat scenarios and ensuring the effective execution of task orders. © 2025 SPIE.

关键词： Naval warfare

来源：评论

学校读者我要写书评

暂无评论

Exploration and Practice of Blended Teaching in the Course of engineering Drawing Empowered by Knowledge Graph

Exploration and Practice of Blended Teaching in the Course o...

引用

International Conference on Educational and Information Technology (ICEIT)

作者： Yahong Xue Haozhi Mu Lijun Xue Tianjin Key Laboratory of the Design and Intelligent Control of the Advanced Mechatronical System National Demonstration Center for Experimental Mechanical and Electrical Engineering Education (Tianjin University of Technology) Tianjin University of Technology Tianjin China

ISBN: (数字)9798350372663

ISBN: (纸本)9798350372670

Under the current blended learning mode, students' ability to process, organize, and integrate knowledge is insufficient, and the ability to construct a complete knowledge system for autonomous learning is slightly weak. Taking the national first-class undergraduate course “engineering Drawing” at Tianjin University of Technology as an example, this study explores and practices the teaching of online and offline hybrid courses based on knowledge graphs, and conducts a comprehensive effectiveness analysis. Practice has proven that the hybrid teaching empowered by knowledge graphs enables visualization of knowledge points and analysis of learning situations, allows for planned learning paths, intelligent resource recommendations, and can achieve targeted integration of data and teaching of key and difficult issues. It has reference significance for the construction of an open, personalized, and precise intelligent education system.

关键词： Federated learning engineering drawings Education Knowledge based systems Data visualization Knowledge graphs Hybrid learning

来源：评论

学校读者我要写书评

暂无评论

Acoustically Driven Micropipette for Hydrodynamic Manipulation of Mouse Oocytes

Acoustically Driven Micropipette for Hydrodynamic Manipulati...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Zhaofeng Zuo Xiaoming Liu Zhuo Chen Yuyang Li Xiaoqing Tang Dan Liu Qiang Huang Tatsuo Arai Beijing Advanced Innovation Center for Intelligent Robots and Systems and School of Mechatronical Engineering Key Laboratory of Biomimetic Robots and Systems Ministry of Education State Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China Center for Neuroscience and Biomedical Engineering The University of Electro-Communications Tokyo Japan

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Micromanipulation techniques that can achieve controlled fine operations at the micro scale play an important role in biomedical fields including embryo engineering, gene engineering, drug screening, and cell analysis. However, micromanipulation of biological micro-objects, such as cells and micro tissues, suffers from mechanical damage and low efficiency. Several techniques have been introduced to manipulate cells more easily, but most of them are restricted by expensive devices, limited work area, and potential damage to cellular structure. Here we develop a hydrodynamic manipulation method to rotate and transport mouse oocytes, which utilizes acoustic waves and micropipette to generate acoustic radiation force and excite microstreaming. This method can accomplish rotational and translational operations precisely and controllably. We tested the process of trapping, rotation, and transportation of the mouse oocytes, and measured rotational and translational speed with a range of applied voltage. The method was able to shorten the cost time of delivery and posture adjustment before oocyte injection. Our study provides an easy-to-use technique for oocyte manipulation without contact, and it has the potential to be universally applied in many cellular studies.

关键词： Visualization Voltage measurement Three-dimensional displays Force Transportation Hydrodynamics Biology

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：