检索结果-内蒙古大学图书馆

第三十九届中国控制会议

作者： Lele Xi Zhihong Peng Lei Jiao School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System

In this paper, we present a trajectory generation method for quadrotor while tracking a moving target with relative pattern. Compared to existing methods, safe flying zone, vehicle’s physical limits and smoothness are considered to ensure obstacles avoidance and real tracking flight. To tackle with the cluttered environment, a parallel Particle Swarm Optimization algorithm is applied to calculate the safe feasible waypoints for quadrotor with consideration of target’s predicted state and the realistic tracking pattern, as well as safety. Then, a multiple waypoints constraints motion planning method is applied and embed into a cost function for solving the problem of trajectories generation and robust tracking for quadrotor via convex optimization approach, ensuring the real-time planning, with the geometrical constraint of safe flight corridor for quadrotor. The effectiveness of proposed method is verified by numerical simulation experiments.

关键词： Target tracking Trajectory generation Waypoints constraint Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Simulation Research on Coordination of Electrical and Structural Parameters in Composite Insulator with Field Grading Materials

Simulation Research on Coordination of Electrical and Struct...

引用

Conference on Electrical Insulation and Dielectric Phenomena, (CEIDP)

作者： Yangzhi Gong Jiale Wu Xupeng Song Wei Yang Kun Wang Xingming Bian State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources North China Electric Power University Beijing P.R.China State Key Laboratory of Advanced Power Transmission Technology Global Energy Interconnection Research Institute Co. Ltd. Beijing P.R.China

Local overstress in composite insulators is a critical problem that affects insulation performance of high voltage transmission system. In addition to traditional methods, applying field grading materials (FGMs) with nonlinear electrical properties is also a promising method. To self-adaptively optimize the electric field strength distribution, electrical and structural parameters of FGMs need to be coordinated. Using finite element modeling, we examine the influence of FGMs with different electrical and structural parameters on field strength distribution of a 220kV AC transmission line epoxy composite insulator. The results indicate that the increase of non-linear coefficient has saturation effect on the reduction of local concentrated electric field strength. Non-linear coefficient of 10-20 is efficient for field grading. The coordination of threshold field strength and length of FGM layers is essential for the improvement of field strength distribution. And the increase of thickness of FGM layers also benefits field grading.

关键词： Power transmission lines Conferences Fitting High-voltage techniques Insulators Structural engineering Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Network for Image Deblurring Using Content Constraint Loss

Generative Adversarial Network for Image Deblurring Using Co...

引用

第32届中国控制与决策会议

作者： Ye Ji Yaping Dai Junjie Ma Kaixin Zhao Yanyan Cheng School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System

The research of image deblurring plays an important role in the digital image *** order to reduce image blurring problems,a content constraint loss（CCL） function in the generative adversarial network（GAN）is *** SSIM loss and the perceptual loss constitute the CCL function,which makes the trained generative model *** CCL function as the content constraint loss component and the adversarial loss component constitute the total *** total loss is optimized by the iterative training to further improve the stability of the network model,and the image blurring will be *** the test experiment of the open source image dataset MNIST,CIFAR10/100 and CELEBA,the CCL function is used as the content constraint loss component of the generative adversarial network,the effect of image deblurring has obvious promotion in the structural similarity measure and visual appearance.

关键词： Image deblurring Generative adversarial network Content constraint loss Adversarial loss

来源：评论

学校读者我要写书评

暂无评论

An Approach for Multi-Objective Obstacle Avoidance Using Dynamic Occupancy Grid Map 17

An Approach for Multi-Objective Obstacle Avoidance Using Dyn...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Liu, Yanjie Chen, Jiao Bai, Xinyu Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin Heilongjiang Province China Sinopec International Business Co. Ltd. No. 22 North Chaoyang Gate Street Chaoyang District Beijing China

ISBN: (纸本)9781728164151

Path planning in dynamic environments is an important guarantee for mobile robots to complete navigation tasks safely. However, human motion is unpredictable, changing its speed or direction arbitrarily, and traditional dynamic obstacle avoidance strategies based on object detection require massive computing resources in the prediction step, which reduces the real time characteristics of the system. To address this question, we propose a dynamic obstacle avoidance framework. It defines the environment as a random dynamic system by using dynamic grid maps, and obtains the velocity of multiple objects with low delay under GPU parallel acceleration calculations. Naturally, we introduce the relative velocity into the artificial potential field function. By expanding the data structure of costmaps, the dynamic grid map is effectively connected with the local obstacle avoidance algorithm. Our approach reduces the detour time of the robot and improves the system security. © 2020 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Closed-form integration of IMU error state covariance for optimization-based Visual-Inertial state Estimator

Closed-form integration of IMU error state covariance for op...

引用

第三十九届中国控制会议

作者： Xingbo Wang Zhihong Peng Lele Xi School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System

In this paper, we propose a closed-form IMU error state covariance integration method for optimization-based visualinertial state estimator. We derive a closed-form solutions of the IMU error state covariance propagation in pre-integration process, yielding improved accuracy of IMU residual information matrix. Our visual-inertial state estimator is based on a tightly-coupled, sliding-window optimization framework, which jointly estimate the IMU states and landmarks and performing marginalization to limit the computational cost. Finally, the system are validated in park environment dataset, the result shows our proposed method is effective.

关键词： visual-inertial state estimator pre-integration

来源：评论

学校读者我要写书评

暂无评论

Advancing energy absorption in additively manufactured meta-plates through machine learning-driven inverse design

引用

Thin-Walled Structures 2025年 215卷

作者： Qingyuan Liu Liang Mou Lan Zhang Shuai Yuan Haiyang Peng Jinguo Ge Yunze Yang Yuhong Long Hualin Fan Guangxi Key Laboratory of Manufacturing System & Advanced Manufacturing Technology School of Mechanical and Electrical Engineering Guilin University of Electronic Technology Jinji road Guilin Guangxi 541004 China Research Center of Lightweight Structures and Intelligent Manufacturing State Key Laboratory of Mechanics and Control of Mechanical Structures Nanjing University of Aeronautics and Astronautics Nanjing 210016 China

Transportation safety systems (e.g., automotive crash boxes, train front-end energy absorption structures) require energy absorbers to simultaneously control energy absorption ( EA ), peak crushing force or stress ( PCF , PCS ), mean crushing force or stress ( MCF , MCS ), and undulation of load carrying ( ULC ). This study proposed meta-plates, characterized by stacking layers, twisting angles, and wall thicknesses. An additive manufacturing constrained machine learning and genetic algorithm (ML-GA) co-design framework was designed to optimize the crashworthiness performances. Finite element (FE) simulations incorporating nonlinear material models and contact algorithms, combined with Latin hypercube sampling, efficiently explored 10.7% of the design space, capturing nonlinear large deformations under quasi-static compression up to 50% strain. 600 independent samples were calculated to evaluate the performance of the ML model, which achieved 96.0% prediction accuracy ( R 2 score). At a given target relative density ( ρ ∗ ) ranging from 4% to 14%, the optimized meta-plates demonstrated 80%–200% higher MCS compared to benchmark shell/plate lattices at equivalent ρ ∗ . The meta-plates also exhibited directional crushing behavior with crushing force efficiency ( CFE ) around 1.0. Experimental validations show < 6% deviation from predictions also witnessed the high MCS , low PCS , and nearly free from stress fluctuation for meta-plates with 8%, 10%, and 14% ρ ∗ values. This methodology enables rapid design of lightweight energy absorbers with tunable deformation modes and extremely high material efficiency, providing a paradigm shift from trial-and-error approaches to intelligent crashworthy structure development.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Study on particle size distribution of debris in electrical discharge machining of deep narrow slots

Study on particle size distribution of debris in electrical ...

引用

20th CIRP Conference on Electro Physical and Chemical Machining, ISEM 2020

作者： Zhang, Rui-Xue Chen, Mo Xi, Xue-Cheng Yan, Xiao-Shen Zhao, Wan-Sheng State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University 800 Dongchuan RD Shanghai200240 China Department of Production Engineering KTH Royal Institute of Technology Stockholm10044 Sweden

Deep narrow slot (DNS) structures can be used in heat-dissipating fins of die-casting molds, grooves in flexible joints of gyros, and slots for inserts in tire molds. However, debris accumulation in the gap makes EDM process unstable and time-consuming, resulting in that slots with high aspect ratio are difficult to achieve. Various methods, such as flushing and electrode jumping, have been used to help evacuate debris and have achieved good results. Nevertheless, these methods treat debris with no distinction under the fact that some debris can naturally leave the gap with bubbles and fluid while the others cannot. This study aims to find out the difference between the easy-to-leave debris and the difficult-to-leave debris from the perspective of the particle size distribution of debris. Factors including currents, machining depths and electrode thicknesses, are studied on their influences on the particle size distribution of debris. In this paper, a laser particle analyzer (LPA) is used to obtain the statistical particle size distribution of debris, while a scanning electronic microscopy is used to observe and record the particle morphology and measure the particle diameters of partial debris. The knowledge of the difference in debris may help seek targeted ways to expel easy-to-leave debris and difficult-to-leave debris. © 2020 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/) Peer-review under responsibility of the scientific committee of the ISEM 2020

关键词： Particle size analysis

来源：评论

学校读者我要写书评

暂无评论

A Path Planning Algorithm of Spray Robot based on 3D Point Cloud

A Path Planning Algorithm of Spray Robot based on 3D Point C...

引用

International Conference on Communications, Information system and Computer Engineering (CISCE)

作者： Jubo Yang Minxiu Kong Rundong Wang School of Mechatronics Engineering Harbin Institute of Technology State Key Laboratory of Robotics and System Harbin China

The following topics are dealt with: learning (artificial intelligence); feature extraction; neural nets; diseases; convolutional neural nets; computer aided instruction; power engineering computing; teaching; educati... 详细信息

ISBN: (数字)9781728197616

ISBN: (纸本)9781728197623

关键词： Three-dimensional displays Spraying Robot sensing systems Robots Robot kinematics Covariance matrices Gravity

来源：评论

学校读者我要写书评

暂无评论

Target Assignment Optimization of Heterogeneous Sensor Networks in Urban Environment

Target Assignment Optimization of Heterogeneous Sensor Netwo...

引用

第三十九届中国控制会议

作者： Chen Chen Cheng Zihao Xu Wei School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex System

Preventing and controlling Low-Slow-Small(LSS) targets are problems to be solved due to their good concealment in urban environment. Consequently, the problem of target assignment is studied in this paper. Firstly, a target assignment model based on heterogeneous sensor networks is proposed. The characteristics of LSS targets and the influence of environmental factors such as climate and terrain are considered on this model. At the same time, the detection capabilities of different detection nodes and collaborative tracking capabilities are also considered. Secondly, an intelligent optimization algorithm GSAPSO based on PSO is proposed to maximize tracking effect of the sensors. Finally, the simulations are used to compare the GSAPSO algorithm with the traditional PSO and GAPSO algorithms. The results demonstrate that the proposed algorithm has better tracking effect.

关键词： Target assignment Urban environment Heterogeneous sensor networks PSO

来源：评论

学校读者我要写书评

暂无评论

UniMSF: A Unified Multi-Sensor Fusion Framework for Intelligent Transportation system Global Localization

arXiv

引用

arXiv 2024年

作者： Liu, Wei Zhu, Jiaqi Zhuo, Guirong Fu, Wufei Meng, Zonglin Lu, Yishi Hua, Min Qiao, Feng Li, You He, Yi Xiong, Lu School of Automotive Studies Tongji University Shanghai201804 China Department of Civil and Environmental Engineering University of California Los Angeles Los AngelesCA United States Shanghai Gongji Technology Co. Ltd Shanghai201804 China Department of Mechanical Engineering The University of Birmingham B15 2TT United Kingdom RWTH Aachen University Aachen52062 Germany State Key Laboratory of Surveying Mapping and Remote Sensing Wuhan University Wuhan China Intelligent Transportation System Research Center Wuhan University of Technology Wuhan China

Intelligent transportation systems (ITS) localization is of significant importance as it provides fundamental position and orientation for autonomous operations like intelligent vehicles. Integrating diverse and complementary sensors such as global navigation satellite system (GNSS) and 4D-radar can provide scalable and reliable global localization. Nevertheless, multi-sensor fusion encounters challenges including heterogeneity and time-varying uncertainty in measurements. Consequently, developing a reliable and unified multi-sensor framework remains challenging. In this paper, we introduce UniMSF, a comprehensive multi-sensor fusion localization framework for ITS, utilizing factor graphs. By integrating a multi-sensor fusion front-end, alongside outlier detection&noise model estimation, and a factor graph optimization back-end, this framework accomplishes efficient fusion and ensures accurate localization for ITS. Specifically, in the multi-sensor fusion front-end module, we tackle the measurement heterogeneity among different modality sensors and establish effective measurement models. Reliable outlier detection and data-driven online noise estimation methods ensure that back-end optimization is immune to interference from outlier measurements. In addition, integrating multi-sensor observations via factor graph optimization offers the advantage of "plug and play". Notably, our framework features high modularity and is seamlessly adapted to various sensor configurations. We demonstrate the effectiveness of the proposed framework through real vehicle tests by tightly integrating GNSS pseudorange and carrier phase information with IMU, and 4D-radar. © 2024, CC BY.

关键词： Global positioning system

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：