检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liu, Zhiyu Han, Zhi Tang, Yandong Zhang, Hai Tang, Shaojie Wang, Yao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Department of Statistics Northwest University Xi’an710000 China Department of Management Science and Systems State University of New York Buffalo United States Center for Intelligent Decision-making and Machine Learning School of Management Xi’an Jiaotong University Xi’an710049 China

We consider the noisy matrix sensing problem in the over-parameterization setting, where the estimated rank r is larger than the true rank r★. Specifically, our main objective is to recover a matrix X★ ∈ Rn1×n2 with rank r★ from noisy measurements using an over-parameterized factorized form LRT, where L ∈ n1×r, R ∈ n2×r and min{n1, n2} ≥ r > r★, with the true rank r★ being unknown. Recently, preconditioning methods have been proposed to accelerate the convergence of matrix sensing problem compared to vanilla gradient descent, incorporating preconditioning terms (LTL + λI)−1 and (RTR + λI)−1 into the original gradient. However, these methods require careful tuning of the damping parameter λ and are sensitive to initial points and step size. To address these limitations, we propose the alternating preconditioned gradient descent (APGD) algorithm, which alternately updates the two factor matrices, eliminating the need for the damping parameter and enabling faster convergence with larger step sizes. We theoretically prove that APGD achieves near-optimal error convergence at a linear rate, starting from arbitrary random initializations. Through extensive experiments, we validate our theoretical results and demonstrate that APGD outperforms other methods, achieving the fastest convergence rate. Notably, both our theoretical analysis and experimental results illustrate that APGD does not rely on the initialization procedure, making it more practical and versatile. Copyright © 2025, The Authors. All rights reserved.

关键词： Damping

来源：评论

学校读者我要写书评

暂无评论

Development of an on-board single-frequency GNSS RTK system for MAVs 34

Development of an on-board single-frequency GNSS RTK system ...

引用

第三十四届中国控制会议

作者： LUO Bing MENG Qing-Hao XU Fei WANG Jia-Ying SUN Biao Institute of Robotics and Autonomous Systems School of Electrical Engineering and AutomationTianjin University

ISBN: (纸本)9781467374439

This paper describes the implementation and experimental results of an on-board real-time kinematic global navigation satellite system(GNSS) for micro air vehicles(MAVs). In this study, a local NTRIP system is constructed, and a base station and a rover station are designed. The RTKLIB source code is modified and ported to single-board computers, forming the stream server of the base station and the position solver of the rover station. To demonstrate and verify the performance of this positioning system, field tests are conducted. Results show that this positioning system is suitable for MAV applications which require economical exact 3D positioning service.

关键词： RTK,GNSS,GPS,MAV,UAV,NTRIP Caster,RTKLIB

来源：评论

学校读者我要写书评

暂无评论

An Improved Object Detection Algorithm for Assembly Line Garbage Sorting 41

An Improved Object Detection Algorithm for Assembly Line Gar...

引用

第41届中国控制会议

作者： Ming Zeng Jiazhe Liu Xiangzhe Lu Zhijing Wang Yuanhao Li Siying Li Institute of Robotics and Automation Systems School of Electrical and Information EngineeringTianjin University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Garbage object detection is of central importance to achieve accurate garbage *** this work,we propose an improved object detection algorithm for sorting complex garbage objects on the assembly *** algorithm utilizes the Faster RCNN as the baseline and improves its performance with several tips,including deformable convolution,PAFPN,mixup,cutout,color jitter,multi-scale training and ImageNet transfer *** the lack of public datasets for the garbage object detection task,we synthesize a highly realistic multi-object garbage detection dataset,M-GarbageNet,with 20000 training images,5000 validation images and 5000 test ***,we evaluate our algorithm than Faster RCNN,and obtain a 8.2%relative improvement on the M-GarbageNet dataset.

关键词： Garbage object detection Improved Faster RCNN M-GarbageNet Image augmentation

来源：评论

学校读者我要写书评

暂无评论

Temporal-spatial cross-correlation analysis of non-stationary near-surface wind speed time series

引用

Journal of Central South University 2017年第3期24卷 692-698页

作者： ZENG Ming LI Jing-hai MENG Qing-hao ZHANG Xiao-nei Institute of Robotics and Autonomous Systems Tianjin Key Laboratory of Process Measurement and Control （School of Electrical Automation and Information Engineering Tianjin University） Tianjin 300072 China

Temporal-spatial cross-correlation analysis of non-stationary wind speed time series plays a crucial role in wind field reconstruction as well as in wind pattern ***,the near-surface wind speed time series recorded at different locations are studied using the detrended fluctuation analysis(DFA),and the corresponding scaling exponents are larger than *** indicates that all these wind speed time series have non-stationary ***,concerning this special feature( i.e.,non-stationarity)of wind signals,a cross-correlation analysis method,namely detrended cross-correlation analysis(DCCA) coefficient,is employed to evaluate the temporal-spatial cross-correlations between non-stationary time series of different anemometer ***,experiments on ten wind speed data synchronously collected by the ten anemometers with equidistant arrangement illustrate that the method of DCCA cross-correlation coefficient can accurately analyze full-scale temporal-spatial cross-correlation between non-stationary time series and also can easily identify the seasonal component,while three traditional cross-correlation techniques(i.e.,Pearson coefficient,cross-correlation function,and DCCA method) cannot give us these information directly.

关键词： temporal-spatial cross-correlation near-surface wind speed time series detrended cross-correlation analysis （DCCA） cross-correlation coefficient Pearson coefficient cross-correlation function

来源：评论

学校读者我要写书评

暂无评论

Riemannian Online Optimistic Algorithms with Dynamic Regret

引用

IEEE Transactions on Automatic Control 2025年

作者： Wang, Xi Yuan, Deming Hong, Yiguang Hu, Zihao Wang, Lei Shi, Guodong University of New South Wales School of Electrical Engineering & Telecommunications SydneyNSW2052 Australia Nanjing University of Science and Technology School of Automation Nanjing210094 China Tongji University Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China Hong Kong University of Science and Technology Department of Mathematics Hong Kong Zhejiang University College of Control Science and Engineering Zhejiang 310058 China The University of Sydney Australian Center for Robotics School of Aerospace Mechanical and Mechatronic Engineering NSW2006 Australia

In this paper, we consider Riemannian online convex optimization with dynamic regret, which involves minimizing the cumulative loss difference between a learner's decisions and a sequence of adaptive decisions across dynamic environments over time on Riemannian manifolds. First, we propose Riemannian Online Optimistic Gradient Descent (R-OOGD), which extends the classical optimistic algorithms to Riemannian manifolds, requiring one gradient inquiry per round. We then propose Riemannian Adaptive Online Optimistic Gradient Descent (R-AOOGD) by incorporating the meta-expert framework into R-OOGD. We analyze the dynamic regret of R-OOGD and R-AOOGD in terms of the regularity of the sequence of cost functions and comparators. The dynamic regret bound matches the results in Euclidean space and with a scale adjustment of O(1+κ D2/√1-KD2) related to the sectional curvature lower bound κ, sectional curvature upper bound and feasible set diameter. Finally, we provide numerical experiments to illustrate the performance of the proposed algorithms. © 1963-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Towards a MRI-Compatible Meso-Scale SMA-Actuated Robot using PWM Control

Towards a MRI-Compatible Meso-Scale SMA-Actuated Robot using...

引用

3rd IEEE RAS and EMBS International Conference on Biomedical robotics and Biomechatronics

作者： Ho, Mingyen Desai, Jaydev P. Robotics Automation and Medical Systems (RAMS) Laboratory Maryland Robotics Center Institute for Systems Research at University of Maryland College Park 20742 USA

ISBN: (纸本)9781424477098

In this paper, we present our work towards the development of a SMA-actuated meso-scale robot for neurosurgery, which can be operated under MRI guidance. In this robot, we use two antagonistic SMA wires as actuators for each joint, so that each joint can be actuated independently. Due to the size scale of the robot, it is impossible to have individual position sensors at each joint and hence we rely primarily on temperature feedback to control the robot. We thus designed and developed an experimental setup to characterize the SMA wires. The goal of SMA characterization was to develop systematic experiments whereby the dependence of the joint motion on the temperature (and hence the SMA phase transition) can be experimentally determined. We also developed a theoretical model based on Tanaka's model and the geometry of the robot to characterize the joint motion with the change in SMA wire temperature. The results demonstrated that the SMA wire temperature can be used reliably to predict the joint motion of the robot. We then developed a Pulse Width Modulation (PWM) scheme to control the temperature of SMA wires (and hence the joint motion). By using PWM control and switching circuits, we can actuate multiple SMA wires simultaneously and independently using only one power supply. Experimental results from our current prototype of a 2-DOF robot show that we can actuate the SMA wires reliably and hence observe joint motion in a gelatin medium as well as in MRI.

关键词： MRI-compatible mesoscale SMA-actuated robot PWM Control Tanaka model actuators biocontrol biomedical MRI gelatin medium joint motion medical robotics mobile robots neurophysiology neurosurgery phase transition pulse width modulation pulse width modulation shape memory effect shape memory effects surgery switching circuits switching circuits

来源：评论

学校读者我要写书评

暂无评论

EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training

arXiv

引用

arXiv 2025年

作者： Tian, Qingyao Liao, Huai Huang, Xinyan Yang, Bingyu Lei, Dongdong Ourselin, Sebastien Liu, Hongbin State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Dept. of Radiology The First Affiliated Hospital Sun Yat-sen University Guangzhou China Centre for Artificial Intelligence and Robotics Chinese Academy of Sciences Hong Kong School of Engineering and Imaging Sciences King’s College London United Kingdom

Endoscopic video-based tasks, such as visual navigation and surgical phase recognition, play a crucial role in minimally invasive surgeries by providing real-time assistance. While recent video foundation models have shown promise, their applications are hindered by (1) computational inefficiencies and (2) suboptimal performance caused by limited data for pre-training in endoscopy. To address these issues, we present EndoMamba, a foundation model designed for real-time inference while learning generalized spatiotemporal representations. First, to mitigate computational inefficiencies, we propose the EndoMamba backbone, optimized for real-time inference. Inspired by recent advancements in state space models, EndoMamba integrates Bidirectional Mamba blocks for spatial modeling within individual frames and vanilla Mamba blocks for past-to-present reasoning across the temporal domain. This design enables both strong spatiotemporal modeling and efficient inference in online video streams. Second, we propose a self-supervised hierarchical pre-training diagram to enhance EndoMamba’s representation learning using endoscopic videos and incorporating general video domain knowledge. Specifically, our approach combines masked reconstruction with auxiliary supervision, leveraging low-level reconstruction to capture spatial-temporal structures and high-level alignment to transfer broader knowledge from a pretrained general-video domain foundation model. Extensive experiments on four downstream tasks—classification, segmentation, surgical phase recognition, and localization—demonstrate that EndoMamba outperforms existing foundation models and task-specific methods while maintaining real-time inference speed. The source code will be released upon acceptance. Copyright © 2025, The Authors. All rights reserved.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Enhanced Autonomous Exploration and Mapping of an Unknown Environment with the Fusion of Dual RGB-D Sensors

引用

Engineering 2019年第1期5卷 164-172页

作者： Ningbo Yu Shirong Wang Institute of Robotics and Automatic Information Systems Nankai University Tianjin 300353 China Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin 300353 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang 110016 China

The autonomous exploration and mapping of an unknown environment is useful in a wide range of applications and thus holds great significance. Existing methods mostly use range sensors to generate twodimensional (2D) grid maps. Red/green/blue-depth (RGB-D) sensors provide both color and depth information on the environment, thereby enabling the generation of a three-dimensional (3D) point cloud map that is intuitive for human perception. In this paper, we present a systematic approach with dual RGB-D sensors to achieve the autonomous exploration and mapping of an unknown indoor environment. With the synchronized and processed RGB-D data, location points were generated and a 3D point cloud map and 2D grid map were incrementally built. Next, the exploration was modeled as a partially observable Markov decision process. Partial map simulation and global frontier search methods were combined for autonomous exploration, and dynamic action constraints were utilized in motion control. In this way, the local optimum can be avoided and the exploration efficacy can be ensured. Experiments with single connected and multi-branched regions demonstrated the high robustness, efficiency, and superiority of the developed system and methods.

关键词： Autonomous exploration Red/green/blue-depth Sensor fusion Point cloud Partial map simulation Global frontier search

来源：评论

学校读者我要写书评

暂无评论

JADFER: Exploring Spatial-Contextual Interaction with Joint Attention Dropping for Facial Expression Recognition

引用

IEEE Transactions on Affective Computing 2024年第02期16卷 655-668页

作者： Gao, Yu Ren, Weihong Jiang, Weibo Dong, Qian Nie, Wei Wu, Wenhao Liu, Honghai Harbin Institute of Technology State Key Lab of Robotics and Systems School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen518055 China

Facial Expression Recognition (FER) aims to categorize emotional expressions depicted on a human face, and is a challenging task under unconstrained conditions, such as face occlusions and pose variations. Recent methods usually adopt self attention or cross attention to explore global or local relationships among different level features. However, these methods are inclined to focus on the redundant facial regions, causing model overfitting. To address this problem, we propose a new FER model named JADFER, which drops the joint attention in the weight matrix to adaptively enhance facial expression representations. Specifically, our JADFER model consists of three components: Spatial Branch (SB), Contextual Branch (CB), and Spatial-Contextual Interaction (SCI). Firstly, SB runs N paths in parallel, where a Variety loss is designed to guide the paths of SB to focus on different discriminative regions. Meanwhile, CB abstracts the contextual facial representations using self attention with Joint Attention Dropping (JAD). Then, the SCI adopts the spatial features from SB to query the contextual representations from CB through cross attention with JAD, which regulates the attention weights by dropping the similar activations to further enhance the facial embeddings. Experimental results demonstrate that the proposed model outperforms the state-of-the-art methods on several FER benchmarks. © 2010-2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Machine-learning-driven prediction of flow curves and development of processing maps for hot-deformed Ni–Cu–Co–Ti–Ta alloy

引用

Journal of Materials Research and Technology 2025年 36卷 7447-7456页

作者： Reliance Jain Sandeep Jain Sheetal Kumar Dewangan M.R. Rahul Sumanta Samal Eunhyo Song Younggeon Lee Yongho Jeon Krishanu Biswas Gandham Phanikumar Byungmin Ahn Department of Materials Science and Engineering Ajou University Suwon 16499 Republic of Korea Department of Mechanical Engineering Ajou University Suwon 16499 Republic of Korea Department of Automation & Robotics Engineering Prestige Institute of Engineering Management and Research Indore 452010 India School of Materials Science and Engineering Yeungnam University Gyeongsan 38541 Republic of Korea Department of Fuel Minerals and Metallurgical Engineering Indian Institute of Technology (ISM) Dhanbad 826004 India Department of Metallurgy Engineering and Materials Science Indian Institute of Technology Indore Indore 453552 India Department of Energy Systems Research Ajou University Suwon 16499 Republic of Korea Department of Materials Science and Engineering Indian Institute of Technology Kanpur Kanpur 208016 India Department of Metallurgical and Materials Engineering Indian Institute of Technology Madras Chennai 600036 India

Optimizing hot deformation conditions is critical for achieving efficient thermo-mechanical processing of advanced alloy systems. In this study, a multicomponent Ni 48 Cu 10 Co 2 Ti 38 Ta 2 alloy was developed, exhibiting a refined eutectic microstructure composed of NiTi and Ni 3 Ti phases, along with coarse Ti 2 Ni and NiTi dendritic phases. High-temperature compression tests were performed using a Gleeble® thermo-mechanical simulator over a temperature range of 973–1273 K and strain rates from 10 −2 to 10 s −1 to investigate the alloy flow behavior. To reduce experimental efforts and enhance prediction accuracy, five machine learning (ML) models random Forest (RF), XGBoost (XGB), decision tree (DT), K-Nearest neighbor (KNN), and gradient boosting (GB) were applied to predict the flow stress–strain response and construct processing maps. Among these, the RF model demonstrated superior predictive performance, particularly at a strain rate of 0.1 s −1 , with R 2 = 0.97, RMSE = 10.1 %, and MAE = 8.9 %. The flow curves predicted by the RF model were used to develop precise processing maps, identifying optimal and safe deformation conditions. The resulting processing maps were validated through experiments, confirming that the alloy can be safely deformed within the temperature range of 1173–1273 K and strain rates between 10 −0.8 and 10 −2 s −1 . This integrated experimental–computational approach offers a reliable and efficient strategy for determining hot working conditions, reducing material and energy consumption. It also presents a robust framework for advancing the development of high-temperature alloy systems through the combination of ML techniques and experimental validation.

关键词： Ni–Ti-Based alloy Hot deformation Kinetic analysis Processing map Machine learning

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：