检索结果-内蒙古大学图书馆

International Conference on Biomimetic Intelligence and robotics & Medical robotics Forum, ICBIR+MRF 2024

作者： Xi, Rui-Dong Ma, Tie-Nan Xia, Bingyi Zhang, Xue Yuan, Yixuan Wang, Jiankun Meng, Max Q.-H. Shenzhen Key Laboratory of Robotics Perception and Intelligence The Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen518055 China Department of Electromechanical Engineering Faculty of Science and Technology University of Macau Taipa999078 China Jiaxing Research Institute Southern University of Science and Technology Jiaxing314000 China Department of Electronic Engineering Chinese University of Hong Kong Hong Kong

Trajectory tracking control of autonomous trolley collection robots (ATCR) is a challenging task due to the complex environment, significant noise, and external disturbances. To address these challenges, this work investigates a control scheme for ATCRs subject to severe environmental interference. A fast-convergent, kinematics model-based adaptive sliding mode disturbance observer (ASMDOB) is first proposed to estimate lumped disturbances. Building upon this, a robust controller with prescribed performance is designed using the backstepping technique, improving transient performance and guaranteeing fast convergence. Simulation results have been given to illustrate the effectiveness of the proposed control scheme. © 2024 The Authors.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Human-Like Robot Impedance Regulation Skill Learning from Human-Human Demonstrations

arXiv

引用

arXiv 2025年

作者： Li, Chenzui Wu, Xi Liu, Junjia Teng, Tao Chen, Yiming Calinon, Sylvain Caldwell, Darwin Chen, Fei Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong Idiap Research Institute Martigny Switzerland Department of Advanced Robotics Istituto Italiano di Tecnologia Genoa16163 Italy

Humans are experts in collaborating with others physically by regulating compliance behaviors based on the perception of their partners’ states and the task requirements. Enabling robots to develop proficiency in human collaboration skills can facilitate more efficient human-robot collaboration (HRC). This paper introduces an innovative impedance regulation skill learning framework for achieving HRC in multiple physical collaborative tasks. The framework is designed to adjust the robot compliance to the human partner’s states while adhering to reference trajectories provided by human-human demonstrations. Specifically, electromyography (EMG) signals from human muscles are collected and analyzed to extract limb impedance, representing compliance behaviors during demonstrations. Human endpoint motions are captured and represented using a probabilistic learning method to create reference trajectories and corresponding impedance profiles. Meanwhile, an LSTM-based module is implemented to develop task-oriented impedance regulation policies by mapping the muscle synergistic contributions between two demonstrators. Finally, we propose a whole-body impedance controller for a human-like robot, coordinating joint outputs to achieve the desired impedance and reference trajectory during task execution. Experimental validation was conducted through a collaborative transportation task and two interactive Tai Chi pushing hands tasks, demonstrating superior performance from the perspective of interactive forces compared to a constant impedance control method. Copyright © 2025, The Authors. All rights reserved.

关键词： Electromyography

来源：评论

学校读者我要写书评

暂无评论

Knowledge-guided temperature correction method for soluble solids content detection of watermelon based on Vis/NIR spectroscopy

Artificial Intelligence in Agriculture

引用

Artificial Intelligence in Agriculture 2025年第1期15卷 88-97页

作者： Zhizhong Sun Jie Yang Yang Yao Dong Hu Yibin Ying Junxian Guo Lijuan Xie College of Biosystems Engineering and Food Science Zhejiang UniversityHangzhou 310058PR China College of Chemistry and Materials Engineering Zhejiang A&F UniversityHangzhou 311300PR China Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province Hangzhou 310058PR China The National Key Laboratory of Agricultural Equipment Technology Beijing 100083PR China Department of Bioproducts and Biosystems Engineering University of MinnesotaSaint PaulMN 55108USA Zhejiang University School of Medicine Division of Scientific Research(ZJU-QILU joint research institute)Hangzhou 310058PR China College of Optical Mechanical and Electrical EngineeringZhejiang A&F UniversityHangzhou 311300PR China College of Mechanical and Electrical Engineering Xinjiang Agricultural UniversityUrumqi 830052PR China

Visible/near-infrared(Vis/NIR)spectroscopy technology has been extensively utilized for the determination of soluble solids content(SSC)in ***,the spectral distortion resulting from temperature variations in the sample leads to a decrease in detection *** mitigate the influence of temperature fluctuations on the accuracy of SSC detection in fruits,using watermelon as an example,this study presents a knowledge-guided temperature correction method utilizing one-dimensional convolutional neural networks(1D-CNN).This method consists of two stages:the first stage involves utilizing 1D-CNN models and gradient-weighted class activation mapping(Grad-CAM)method to acquire gradient-weighted features correlating with *** second stage involves mapping these features and integrating them with the original Vis/NIR spectrum,and then train and test the partial least squares(PLS)*** knowledge-guided method can identify wavelength bands with high temperature correlation in the Vis/NIR spectra,offering valuable guidance for spectral data *** performance of the PLS model constructed using the 15℃ spectrum guided by this method is superior to that of the global model,and can reduce the root mean square error of the prediction set(RMSEP)to 0.324°Brix,which is 32.5%lower than the RMSEP of the global model(0.480°Brix).The method proposed in this study has superior temperature correction effects than slope and bias correction,piecewise direct standardization,and external parameter orthogonalization correction *** results indicate that the knowledge-guided temperature correction method based on deep learning can significantly enhance the detection accuracy of SSC in watermelon,providing valuable reference for the development of PLS calibration methods.

关键词： Visible/near-infrared spectroscopy Temperature correction Watermelon Knowledge-guided Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Robust Optimization Under Decision Dependent Uncertainty

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1295-1306页

作者： Yunfan Zhang Feng Liu Yifan Su Yue Chen Zhaojian Wang João P.S.Catalão State Key Laboratory of Power System and Generation Equipment the Department of Electrical EngineeringTsinghua UniversityBeijing 100084China Department of Mechanical and Automation Engineering the Chinese University of Hong KongHong Kong SARChina Ministry of Education Key Laboratory of System Control and Information Processing the Department of AutomationShanghai Jiao Tong Universityand also with Shanghai Engineering Research Center of Intelligent Control and ManagementShanghai 200240China Faculty of Engineering of the University of Porto and Institute for Systems and Computer Engineering Technology and Science(INESC TEC)Porto 4200-465Portugal IEEE

In the conventional robust optimization(RO)context,the uncertainty is regarded as residing in a predetermined and fixed uncertainty *** many applications,however,uncertainties are affected by decisions,making the current RO framework *** paper investigates a class of two-stage RO problems that involve decision-dependent *** introduce a class of polyhedral uncertainty sets whose right-hand-side vector has a dependency on the here-and-now decisions and seek to derive the exact optimal wait-and-see decisions for the second-stage problem.A novel iterative algorithm based on the Benders dual decomposition is proposed where advanced optimality cuts and feasibility cuts are designed to incorporate the uncertainty-decision *** computational tractability,robust feasibility and optimality,and convergence performance of the proposed algorithm are guaranteed with theoretical *** motivating application examples that feature the decision-dependent uncertainties are ***,the proposed solution methodology is verified by conducting case studies on the pre-disaster highway investment problem.

关键词： Benders decomposition decision-dependent uncertainty endogenous uncertainty robust optimization(RO)

来源：评论

学校读者我要写书评

暂无评论

Renderable Street View Map-Based Localization: Leveraging 3D Gaussian Splatting for Street-Level Positioning

Renderable Street View Map-Based Localization: Leveraging 3D...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Howoong Jun Hyeonwoo Yu Songhwai Oh Artificial Intelligence (IPAI) Seoul National University and Automation and Systems Research Institute (ASRI) and Sequor Robotics Inc. Seoul Korea Republic of Department of Intelligent Robotics & Mechanical Engineering Sungkyunkwan University (SKKU) Suwon-si Korea Republic of Department of Electrical and Computer Engineering (ECE) & Interdisciplinary Program in Artificial Intelligence (IPAI) Seoul National University and Automation and Systems Research Institute (ASRI) and Sequor Robotics Inc. Seoul Korea Republic of

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In this paper, we introduce a new method that first utilizes 3D Gaussian splatting in street-level localization problem. Robust localization with street-level real-world images such as street view is a major issue for autonomous vehicle, augmented reality (AR) navigation, and outdoor mobile robots. The objective is to determine the position and orientation of a query image that matches a street view database composed of RGB images. However, given the limited information available in the street view images, accurately determining the location solely based on this data presents a significant challenge. To address this challenge, we propose a novel method called renderable street view map-based localization (RSM-Loc). This approach enhances the localization process by augmenting 2D street view images into a renderable 3D map using 3D Gaussian splatting, to resolve street-level localization problems. Upon receiving a query RGB image without geometry information, the proposed method renders 2D images from a pre-made renderable map and compares image pose similarities between the rendered images and the query image. Through iterations of this process, the proposed method eventually estimates the pose of the given query image. The experimental results demonstrate that RSM-Loc outperforms the baselines with neural-field-based localization. Additionally, we conduct deep analysis on the proposed method to show that our method can serve as a new concept for the street-level localization problem.

关键词： Location awareness Visualization Matched filters Three-dimensional displays Image resolution Navigation Noise measurement Mobile robots Intelligent robots Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

An Evaluation Method for Statistical Index of New-type Power System Based on Hierarchical Evidential Reasoning 9

An Evaluation Method for Statistical Index of New-type Power...

引用

9th Asia Conference on Power and electrical engineering, ACPEE 2024

作者： Wu, Xiangyu Xun, Chao Fu, Li Jiang, Xiaofu Zhuang, Pengwei Xu, Xun Jiang, Changxu Shao, Zhenguo Power Research Institute Development Department Fujian Power Co. Ltd. Electric Fuzhou China State Grid Fujian Electric Power Co. Ltd Development Department Fuzhou China Fuzhou University College of Electrical Engineering and Automation Fuzhou China

ISBN: (纸本)9798350309638

In the background of carbon neutrality and carbon peaking, provinces are actively promoting the construction of new-type power system. However, there is currently a lack of quantitative methods for evaluating the construction of new-type power system. In response to this issue, this paper proposes an evaluation method for statistical index of new-type power system based on hierarchical evidential reasoning. Firstly, the subjective and objective weights for the indicators are obtained through analytic hierarchy process and entropy weight method, and the combined weight is obtained through game theory as the final weight of the indicators. Then, the evaluation of each indicator is fused through hierarchical evidential reasoning. Subsequently, using the constructed statistical index system and indicator data of the new-type power system, simulation verification is conducted to quantitatively assess the construction status of the new-type power system in each province. Finally, by comparing and analyzing the construction of new-type power system in Zhejiang, Qinghai, and Fujian provinces, the future development directions of new-type power system construction in Fujian province are suggested. © 2024 IEEE.

关键词： Analytic hierarchy process

来源：评论

学校读者我要写书评

暂无评论

Compact 3D Gaussian Splatting for Dense Visual SLAM

arXiv

引用

arXiv 2024年

作者： Deng, Tianchen Chen, Yaohui Zhang, Leyan Yang, Jianfei Yuan, Shenghai Liu, Jiuming Wang, Danwei Wang, Hesheng Chen, Weidong Institute of Medical Robotics Department of Automation Shanghai Jiao Tong University Shanghai200240 China School of Electrical and Electronic Engineering Nanyang Technological University Singapore

Recent work has shown that 3D Gaussian-based SLAM enables high-quality reconstruction, accurate pose estimation, and real-time rendering of scenes. However, when we revisit the existing GS-based SLAM systems, we observe that the redundancy of the Gaussian ellipsoids created by SLAM systems is significantly superior to those of the original 3D Gaussian Splatting methods. We further quantitatively demonstrate the geometric similarity and the redundancy of 3D Gaussian scene representation, leading to high memory and storage costs. To address this limitation, we propose a compact 3D Gaussian Splatting SLAM system that reduces the number and the parameter size of Gaussian ellipsoids. A sliding window-based masking strategy is first proposed to reduce the redundant ellipsoids. Then, a novel geometry codebook-based quantization method is proposed to further compress 3D Gaussian geometric attributes. Robust and accurate pose estimation is achieved by a local-to-global bundle adjustment method with reprojection loss. Extensive experiments demonstrate that our method achieves faster training, rendering speed (226% increase), and low memory usage (2.21× compression) while maintaining the state-of-the-art (SOTA) quality of the scene representation. https://***/dtc111111/CompactGSSLAM Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Bilateral-Head Region-Based Convolutional Neural Networks: A Unified Approach for Incremental Few-Shot Object Detection

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4376-4390页

作者： Li, Yiting Zhu, Haiyue Tian, Sichao Ma, Jun Xiang, Cheng Vadakkepat, Prahlad National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore Singapore Institute of Manufacturing Technology Agency for Science Technology and Research 138634 Singapore Peking Union Medical College Institute of Medicinal Plant Development Chinese Academy of Medical Sciences Beijing100193 China Robotics and Autonomous Systems Thrust Guangzhou511453 China The Hong Kong University of Science and Technology Division of Emerging Interdisciplinary Areas Hong Kong SAR Hong Kong Hkust Shenzhen-Hong Kong Collaborative Innovation Research Institute Shenzhen Futian518045 China

Practical object detection systems are highly desired to be open-ended for learning on frequently evolved datasets. Moreover, learning with little supervision further adds flexibility for real-world applications such as autonomous driving and robotics, where large-scale datasets could be prohibitive or expensive to obtain. However, continual adaption with small training examples often results in catastrophic forgetting and dramatic overfitting. To address such issues, a compositional learning system is proposed to enable effective incremental object detection from nonstationary and few-shot data streams. First of all, a novel bilateral-head framework is proposed to decouple the representation learning of base (pretrained) and novel (few-shot) classes into separate embedding spaces, which takes care of novel concept integration and base knowledge retention simultaneously. Moreover, to enhance learning stability, a robust parameter updating rule, i.e., recall and progress mechanism, is carried out to constrain the optimization trajectory of sequential model adaption. Beyond that, to enforce intertask class discrimination with little memory burden, we present a between-class regularization method that expands the decision space of few-shot classes for constructing unbiased feature representation. Final, we deeply investigate the incomplete annotation issue considering the realistic scenario of incremental few-shot object detection (iFSOD) and propose a semisupervised object labeling mechanism to accurately recover the missing annotations for previously encountered classes, which further enhances the robustness of the target detector to counteract catastrophic forgetting. Extensive experiments conducted on both Pascal visual object classes dataset (VOC) and microsoft common objects in context dataset (MS-COCO) datasets demonstrate the effectiveness of our method. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Development of Three Phase High Power Smart Meter for Energy Management Monitoring System in UniKL MSI 2

Development of Three Phase High Power Smart Meter for Energy...

引用

2nd International Conference on Power, electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Abd Rahman, Fikri Izuddin Yaakop, Nurazlin M. Ibrahim, Nor Haslina Sohan, Moshiur Rahman Shaffiee, Nor Syafiqa Mohamed Hossain, Md Liton Universiti Kuala Lumpur Malaysian Spanish Institute Mechatronic Engineering Kulim Malaysia Universiti Kuala Lumpur Malaysian Spanish Institute Electrical Electronic & Automation Kulim Malaysia University of Liberal Arts Bangladesh Department of Electrical and Electronic Engineering Dhaka Bangladesh Universiti Kuala Lumpur Malaysian Spanish Institute Student Development Kulim Malaysia Federation University Australia Centre for New Energy Transition Research Melbourne Australia

ISBN: (纸本)9798331517984

Energy efficiency is defined as using energy in the most efficient way to provide the same service that could have been provided less efficiently. Low energy efficiency will increase greenhouse gas emissions, demand for energy import, and high costs for electrical bills and economy-wide levels. This paper discusses the development of a 3-phase high-power smart energy meter using the Internet of Things (IoT). This meter was designed using a NodeMCU ESP8266 as the main controller device. Three PZEM-004T modules and Split Coil Current Transformer (CT) were the main sensors used in this project. The NodeMCU with the built-in Wi-Fi module allows this system to communicate wirelessly with the cloud server and mobile application. The accuracy of power data measurements proposed by the Smart Energy Monitoring System (SEMS) was tested by experimenting in a laboratory. The result shows all the data measurements of power usage proposed by SEMS had less than 10% error compared with the Power Analyzer. This demonstrated that SEMS had high accuracy and was equivalent to existing measurement devices on the market. © 2024 IEEE.

关键词： Strain measurement

来源：评论

学校读者我要写书评

暂无评论

Optimization of Crop Yields in Sustainable Agriculture: Application of Big Data Analytics and Artificial Intelligence

引用

Remote Sensing in Earth Systems Sciences 2025年第2期8卷 375-386页

作者： Nimma, Divya Dhanke, Jyoti A. Murthy, G.S.N. Khandekar, Sachin Dadu Hymavathi, J. Jangir, Pradeep Singh, Mahesh Department of Computational Science University of Southern Mississippi Hattiesburg 39406 MS United States Department of Engineering Science (Mathematics) Bharati Vidyapeeth’s College of Engineering Lavale Maharashtra Pune India Department of CSE Aditya University Surampalem India Department of Civil Engineering Sinhgad College of Engineering Maharashtra Pune India Department of CSE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan Department of Robotics and Automation Symbiosis Institute of Technology Pune Campus Symbiosis International (Deemed University) Pune India

Making informed economic decisions based on agricultural data is challenging without proper crop management. Data has become the single most important part of modern farming, and its rapid evolution is a major contributor to the rise of “smart farming.” Using sensors to gather objective data with the end aim of increasing productivity and sustainability has several advantages. Information that might boost productivity while decreasing resource waste and pollution levels is essential for managed farms. The cornerstone of future sustainable farming will be data-driven agriculture using robotic solutions based on AI-based techniques. This paper examines the current state of advanced farm management systems, discussing topics like data acquisition in crop fields and variable rate applications, to assist farmers in saving money, protecting the environment, and transforming food production so that it can sustainably keep up with the expected increase in population. The advent of machine learning, big data technologies, and high-performance computers has opened up new avenues for data-intensive research in the interdisciplinary subject of agro technology. These avenues of exploration have been aided by the development of more capable computers. A comprehensive literature review on the issue of the applications of machine learning in agricultural manufacturing is provided in this research. Machine learning has shown its utility in agriculture via two applications: filtering and categorizing products. The use of machine learning on sensor data is transforming conventional farm management systems into AI-enabled programs. These services provide farmers instantaneous, complete access to ideas and insights that may guide their decisions. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Artificial intelligence Big data analytics Optimize crop yields Sustainable agriculture

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：