检索结果-内蒙古大学图书馆

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Danping Zeng Yaonan Wang Yiming Jiang Haoran Tan Zhiqiang Miao Yun Feng School of Robotics and the National Engineering Research Center for Robot Visual Perception and Control Technology Hunan University Changsha China College of Electrical and Information Engineering and the National Engineering Research Center for Robot Visual Perception and Control Technology Hunan University Changsha China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

A number of robotic tasks exist, such as manipulating heavy and oversized objects, where a single manipulator is not enough and multiple mobile manipulators need to be used. When uncertainty exists, a compliant control strategy is expected to be applied for such a tightly coordinated multiple mobile manipulator system. An adaptive impedance control law that enables adaptive updating of impedance parameters is developed in this work. The proposed method ensures that all closed-loop systems boundedly and asymptotically realize the desired adaptive impedance dynamics. Furthermore, to ensure the passivity of the adaptive impedance system, the impedance system of each mobile manipulator is interconnected with a virtual energy tank, and the update of the impedance system parameters is guided according to the level of the energy to ensure that the adaptive impedance system is passive, thus realizing the adaptive trade-off between compliance and operational accuracy. Finally, a simulation for four mobile manipulators collaborating to carry an unknown object is provided to validate the effectiveness of the proposed one.

关键词： Adaptive systems Uncertainty Mechatronics robot kinematics Cooperative systems Stability analysis Trajectory Impedance Closed loop systems Manipulator dynamics

来源：评论

学校读者我要写书评

暂无评论

An Improved SCA-BP Delay Prediction Method for Networked control Systems

An Improved SCA-BP Delay Prediction Method for Networked Con...

引用

2023 China Automation Congress, CAC 2023

作者： Xie, Jiayin Wang, Yaonan Tan, Haoran Wu, You Zhou, Bowen College of Electrical and Information Engineering Hunan University National Engineering Research Center for Robot Visual Perception and Control Changsha China Hunan Retoo Intelligent Technology Co. Ltd. Changsha China

ISBN: (纸本)9798350303759

A networked control system is a system that uses communication networks to connect the various parts. However, network delay affects the performance and stability of the networked control system. In order to eliminate the impact of network delay on the control system, an improved SCA-BP delay prediction method is proposed in this paper. The proposed method optimizes the initial weights and biases of the BP neural network, and further optimizes them through backpropagation gradient descent, obtaining the final prediction model. The proposed method introduces a random perturbation factor in the sine and cosine functions, which increases the explorability and diversity of the method. And they are sorted and grouped according to the fitness values of the candidate solutions. At the same time, different update strategies are adopted based on the different groups, enabling the method to perform global and local search simultaneously. In the update strategy, a linear function is also introduced in addition to the sine and cosine functions, enabling the method to maintain the direction of the current optimal solution to a certain extent. Finally, the superiority and effectiveness of the method compared with traditional methods are verified through some comparative simulations, indicating that the method has a strong delay prediction ability. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

LanCOPE: Language-Guided Category-Level Object Pose Estimation from a Single RGB Image

引用

IEEE robotics and Automation Letters 2025年第7期10卷 7555-7562页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Dai, Zhenqi Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha 410082 China Central South University School of Architecture and Art Changsha 410082 China The University of Western Australia Department of Computer Science and Software Engineering 6009 WA Australia

Monocular RGB-based category-level object pose estimation is more practical and cost-effective for robotics. However, existing methods do not fully exploit the rich semantic and contextual information in multimodal data (e.g. language) that provides additional object attributes to guide the model in extracting category features more reliably. We propose a language-guided category-level object pose estimation method (LanCOPE), taking a single RGB image as input. Our method uses DINOv2 to recover depth from a single RGB image and converts it into point cloud to perceive the object's geometry. We then introduce language descriptions for the RGB image, estimated point cloud and overall scene to better guide the point cloud encoder and image encoder in learning category features. We develop a cross-modal differential perception feature fusion network to fuse multimodal features. This network employs a differential perception module to eliminate redundant information across different modalities, highlighting signifcant semantic differences and similarities. Furthermore, it uses a cross-attention mechanism to fuse the semantic information of the language and vision features, improving the overall perception. Finally, we design a denoising network based on the skip fusion transformer to recover the object pose accurately. Extensive experiments on REAL275 and Wild6D datasets show that LanCOPE achieves state-of-the-art performance. Our code is available at LanCOPE. © 2016 IEEE.

关键词： category-level object pose estimation languag RGB image

来源：评论

学校读者我要写书评

暂无评论

Current Status,Challenges,and Prospects for New Types of Aerial robots

引用

engineering 2024年第10期41卷 19-34页

作者： Xidong Zhou Hang Zhong Hui Zhang Wei He Hean Hua Yaonan Wang College of Robotics Hunan UniversityChangsha 410082China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan UniversityChangsha 410082China School of Intelligence Science and Technology Beijing University of Science and TechnologyBeijing 100083China

New types of aerial robots(NTARs)have found extensive applications in the military,civilian contexts,scientific research,disaster management,and various other *** with traditional aerial robots,NTARs exhibit a broader range of morphological diversity,locomotion capabilities,and enhanced operational ***,this study defines aerial robots with the four characteristics of morphability,biomimicry,multi-modal locomotion,and manipulator attachment as ***,this paper discusses the latest research progress in the materials and manufacturing technology,actuation technology,and perception and control technology of ***,the research status of NTAR systems is summarized,focusing on the frontier development and application cases of flapping-wing microair vehicles,perching aerial robots,amphibious robots,and operational aerial ***,the main challenges presented by NTARs in terms of energy,materials,and perception are analyzed,and the future development trends of NTARs are summarized in terms of size and endurance,mechatronics,and complex scenarios,providing a reference direction for the follow-up exploration of NTARs.

关键词： Aerial robot Morphability Biomimicry Perch Amphibious

来源：评论

学校读者我要写书评

暂无评论

NCV-PWM Method for the Phase Current Reconstruction With DC Link Single Sensor

NCV-PWM Method for the Phase Current Reconstruction With DC ...

引用

作者： Shen, Yongpeng Wu, Kexuan Yuan, Xiaofang Wu, Chengzhong Liang, Weihua Chen, Zhiwei The College of Electric and Information Engineering Zhengzhou University of Light Industry Zhengzhou450002 China The Department of Electric and Information Engineering Hunan University Changsha410082 China The National Engineering Laboratory for Robot Visual Perception and Control Technology Hunan University Changsha410082 China

The DC link current sampling with a single sensor is a promising solution in the electric drive field due to its low cost and small volume. However, limited by the minimum sampling time, the current reconstruction unobservable area is the most intractable challenge in the traditional single sensor reconstruction method, especially in sector boundary areas, where the phase current cannot be reconstructed completely. In this article, a new non-zero compensation vector pulse width modulation (NCV-PWM) method is proposed to eliminate the current unobservable area. Firstly, by introducing the definition of minimum sampling time, the voltage space vector plane is accurately divided into different modulation areas. Then, by applying non-zero compensation vector in the sector boundary, the current sampling window is extended, and the sampling time requirement for the DC link current is satisfied. Finally, the practicability and accuracy of the NCV-PWM method are verified by experiments, and results show that the current reconstruction error is less than 2.86%, which provides accurate current feedback for high-performance motor control. © 2023 IEEE.

关键词： Electric drives

来源：评论

学校读者我要写书评

暂无评论

Towards Consistent Object Detection via LiDAR-Camera Synergy

Towards Consistent Object Detection via LiDAR-Camera Synergy

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Luo, Kai Wu, Hao Yi, Kefu Yang, Kailun Hao, Wei Hu, Rongdong College of Automotive and Mechanical Engineering Changsha University of Science and Technology China School of Traffic and Transportation Engineering Changsha University of Science and Technology China School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China Changsha Intelligent Driving Institute China

ISBN: (纸本)9781665410205

As human-machine interaction continues to evolve, the capacity for environmental perception is becoming increasingly crucial. Integrating the two most common types of sensory data, images, and point clouds, can enhance detection accuracy. Currently, there is no existing model capable of detecting an object's position in both point clouds and images while also determining their corresponding relationship. This information is invaluable for human-machine interactions, offering new possibilities for their enhancement. In light of this, this paper introduces an end-to-end Consistency Object Detection (COD) algorithm framework that requires only a single forward inference to simultaneously obtain an object's position in both point clouds and images and establish their correlation. Furthermore, to assess the accuracy of the object correlation between point clouds and images, this paper proposes a new evaluation metric, Consistency Precision (CP). To verify the effectiveness of the proposed framework, an extensive set of experiments has been conducted on the KITTI and DAIR-V2X datasets. The study also explored how the proposed consistency detection method performs on images when the calibration parameters between images and point clouds are disturbed, compared to existing post-processing methods. The experimental results demonstrate that the proposed method exhibits ex-cellent detection performance and robustness, achieving end-to-end consistency detection. The source code will be made publicly available at https://***/xifen523/COD. © 2024 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Frequency shift-based 3D shape measurement in the presence of strong inter-reflection

Frequency shift-based 3D shape measurement in the presence o...

引用

2024 International Conference on Optical and Photonic engineering, icOPEN 2024

作者： Miao, Huisi Liu, Wan Yan, Ziyu Xu, Weidong Zhang, Dongbo Zhang, Hui School of Automation and Electronic Information Xiangtan University Xiangtan411105 China Xiangtan Electric Manufacturing Co..Ltd. Xiangtan411105 China National Engineering Research Center of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410082 China

ISBN: (数字)9781510688117

ISBN: (纸本)9781510688100

Traditional fringe projection profilometry (FPP) struggles with robust imaging and high-precision three-dimensional (3D) reconstruction in complex lighting environments with strong inter-reflection. This paper proposes a method combining frequency-shifted fringe projection and epipolar constraint to achieve high-precision 3D profilometry in such scenarios. First, environmental light interference is mitigated and the maximum fringe frequency is reduced through window function analysis (WFA) and a four-step phase-shifting (PS). Then, direct and indirect illumination are separated in the Fourier domain. Direct illumination positions are identified using threshold segmentation and epipolar geometry constraint, enhancing imaging robustness in strong inter-reflection contexts. Experimental results demonstrate that the method constructs direct and indirect illumination feature models, accurately obtaining direct illumination information and eliminating multi-path interference. Additionally, in tests with complex geometrical surfaces, imaging efficiency and robustness significantly improve, with effective point cloud data increasing by over 30% and planar accuracy improving by 50%. © 2025 SPIE.

关键词： Light interference

来源：评论

学校读者我要写书评

暂无评论

A Graph-Based SLAM Method Assisted by visual Marker in the Degenerate Scenes 8

A Graph-Based SLAM Method Assisted by Visual Marker in the D...

引用

8th IEEE International Conference on Advanced robotics and Mechatronics, ICARM 2023

作者： Zhang, Jieqingxin Zhang, Hui Zhou, Xidong Chen, Bo Wang, Xiangchuan Xu, Tao College of Electrical and Information Engineering Changsha University of Science and Technology Hunan China College of Robotics Robot Visual Perception and Control Technology National Engineering Research Center Hunan University Hunan China College of Electrical and Information Engineering Hunan University Hunan China

ISBN: (纸本)9798350300178

In the post-COVID-19 pandemic era, hospitals and other places have an urgent need for mobile robots with autonomous disinfection ability, and robots need to complete SLAM tasks to realize autonomous navigation. Lidar is widely used for indoor SLAM. However, due to the lack of geometric structure in the indoor environment, two-dimensional lidar information degrades, rendering the robot unable to obtain effective positioning. Therefore, we leverage the easy identification and high robustness of ARTag to fuse vision and range sensor information. We introduce ARTag as visual marker to assist positioning, establish observation window to screen the acquired ARTag pose. We employ the pose graph optimization method to optimize the visual markers and laser scanning results in the back end. This reduces the positioning errors caused by the degradation of lidar information and reduces the frequency of optimization by improving the back end optimization strategy. This method is applied in a UltraViolet C (UVC) Disinfection robot experiment. Experimental results show that our method effectively improves the positioning accuracy and robustness of the robot in the environments with degraded laser information. © 2023 IEEE.

关键词： Disinfection

来源：评论

学校读者我要写书评

暂无评论

DDH-Net:A Dual Dynamic Head Network for Transmission Line Inspection

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Yu, Junlong Mao, Jianxu Wang, Yaonan He, Zhenyu Yi, Junfei Tao, Ziming Zhang, Hui Wang, Shaoyuan Hunan University College of Electrical and Information Engineering Hunan Changsha410012 China Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Robotics Hunan Changsha410082 China

Transmission lines are a critical component of an electrical grid, and ensuring their effective detection is of utmost importance. However, problems such as fine-grained identification, target occlusion, and background complexity in aerial transmission line images challenge existing transmission line detection methods. This paper presents a dual dynamic head network (DDH-Net) to address the aforementioned issues. This network incorporates a dual dynamic head (DDH) composed of a multifeature fusion module (MFFM) and deformable convolution. DDH leverages deformable convolution to enhance the network's focus on the target of interest. Subsequently, the MFFM enhances the feature representation capabilities for individual targets, leading to discriminative feature extraction and improving the network's accuracy in detecting similar targets. Furthermore, we introduce the wise area intersection over union (WAIoU) loss, which reduces the network's attention on detection boxes that contain only partial target content through the adaptive allocation of loss weights to anchor boxes to mitigate occlusion-induced interference. Additionally, we incorporate area as a constraint to further enhance the network's localization accuracy. Finally, extensive experiments were conducted on a power transmission line dataset. The results demonstrated the superiority of the proposed module over other state-of-the-art (SOTA) methods. © 1963-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

One-Shot Affordance Grounding of Deformable Objects in Egocentric Organizing Scenes

arXiv

引用

arXiv 2025年

作者： Jia, Wanjun Yang, Fan Duan, Mengfei Chen, Xianchi Wang, Yinxi Jiang, Yiming Chen, Wenrui Yang, Kailun Li, Zhiyong School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

Deformable object manipulation in robotics presents significant challenges due to uncertainties in component properties, diverse configurations, visual interference, and ambiguous prompts. These factors complicate both perception and control tasks. To address these challenges, we propose a novel method for One-Shot Affordance Grounding of Deformable Objects (OS-AGDO) in egocentric organizing scenes, enabling robots to recognize previously unseen deformable objects with varying colors and shapes using minimal samples. Specifically, we first introduce the Deformable Object Semantic Enhancement Module (DefoSEM), which enhances hierarchical understanding of the internal structure and improves the ability to accurately identify local features, even under conditions of weak component information. Next, we propose the ORB-Enhanced Keypoint Fusion Module (OEKFM), which optimizes feature extraction of key components by leveraging geometric constraints and improves adaptability to diversity and visual interference. Additionally, we propose an instance-conditional prompt based on image data and task context, effectively mitigates the issue of region ambiguity caused by prompt words. To validate these methods, we construct a diverse real-world dataset, AGDDO15, which includes 15 common types of deformable objects and their associated organizational actions. Experimental results demonstrate that our approach significantly outperforms state-of-the-art methods, achieving improvements of 6.2%, 3.2%, and 2.9% in KLD, SIM, and NSS metrics, respectively, while exhibiting high generalization performance. Source code and benchmark dataset will be publicly available at https://***/Dikay1/OS-AGDO. Copyright © 2025, The Authors. All rights reserved.

关键词： Image enhancement

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

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

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：