检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kienle, Claudius Alt, Benjamin Schneider, Finn Pertlwieser, Tobias Jäkel, Rainer Rayyes, Rania ArtiMinds Robotics Karlsruhe Germany IAS Lab Computer Science Department TU Darmstadt Germany AICOR Institute for Artificial Intelligence University of Bremen Germany Karlsruhe Germany

Despite the widespread adoption of industrial robots in automotive assembly, wire harness installation remains a largely manual process, as it requires precise and flexible manipulation. To address this challenge, we design a novel AI-based framework that automates cable connector mating by integrating force control with deep visuotactile learning. Our system optimizes search-and-insertion strategies using first-order optimization over a multimodal transformer architecture trained on visual, tactile, and proprioceptive data. Additionally, we design a novel automated data collection and optimization pipeline that minimizes the need for machine learning expertise. The framework optimizes robot programs that run natively on standard industrial controllers, permitting human experts to audit and certify them. Experimental validations on a center console assembly task demonstrate significant improvements in cycle times and robustness compared to conventional robot programming approaches. Videos are available under https: //***/*** Codes 68T40 © 2025, CC BY.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

A Review on On Device Privacy and Machine Learning Training 2

A Review on On Device Privacy and Machine Learning Training

引用

2nd IEEE International Conference on artificial intelligence in Everything, AIE 2022

作者： Tonga, Paul Audu Ameen, Zubaida Said Mubarak, Auwalu Saleh Al-Turjman, Fadi Ai and Robotics Institute Near East University Research Center for Ai and IoT Artificial Intelligence Dept Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Cyprus

ISBN: (数字)9781665474009

ISBN: (纸本)9781665474009

On device machine learning has in recent times attracted growing attention and applications, ranging from advanced OCR and handwriting recognition, smart sleep tracking in Apple iOS, mobile virtual assistants and Image recognition, text translation in android;and more. As a result, there is increasing demand for user privacy and security in machine learning applications. Federated Learning (FL), a new method, allows users to cooperatively train a global model while keeping the data local, thereby resolving the issue of data privacy protection through the encryption mechanism. The server aggregates models until convergence while the clients train their local models. In this procedure, the server employs a reward system to persuade users to provide huge amounts of high-quality data in order to enhance the overall model. This paper explores a few FL techniques that can be applied alongside on-device learning, in order to achieve better privacy and security. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Human Action Recognition with Noisy Labels

Skeleton-Based Human Action Recognition with Noisy Labels

引用

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

作者： Yi Xu Kunyu Peng Di Wen Ruiping Liu Junwei Zheng Yufan Chen Jiaming Zhang Alina Roitberg Kailun Yang Rainer Stiefelhagen Anthropomatics and Robotics Karlsruhe Institute of Technology Germany Institute for Artificial Intelligence University of Stuttgart Germany School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Understanding human actions from body poses is critical for assistive robots sharing space with humans in order to make informed and safe decisions about the next interaction. However, precise temporal localization and annotation of activity sequences is time-consuming and the resulting labels are often noisy. If not effectively addressed, label noise negatively affects the model’s training, resulting in lower recognition quality. Despite its importance, addressing label noise for skeleton-based action recognition has been overlooked so far. In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark. Observations reveal that these baselines yield only marginal performance when dealing with sparse skeleton data. Consequently, we introduce a novel methodology, NoiseEraSAR, which integrates global sample selection, co-teaching, and Cross-Modal Mixture-of-Experts (CM-MOE) strategies, aimed at mitigating the adverse impacts of label noise. Our proposed approach demonstrates better performance on the established benchmark, setting new state-of-the-art standards. The source code for this study will be made accessible at https://***/xuyizdby/NoiseEraSAR.

关键词： Training Source coding Noise Training data Benchmark testing Skeleton Noise measurement Human activity recognition Streams Standards

来源：评论

学校读者我要写书评

暂无评论

Optimizing Medication Compliance through Machine Learning and IoT for Personalized Health Management 9

Optimizing Medication Compliance through Machine Learning an...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Balaji, P. Mohitha, I.K. Prashanthini, K. Sivaprakash, K. Rithick, P. Kasthuri, S. Sri Ramakrishna Engineering College Department of Electronics and Instrumentation Engineering Coimbatore India KGiSL Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Sri Ramakrishna Engineering College Department of Robotics and Automation Engineering Coimbatore India Sns College of Engineering Department of Artificial Intelligence and Data Science Coimbatore India

ISBN: (纸本)9798350377972

Machine learning (ML) and Internet of Things (IoT) technologies have revolutionized the healthcare industry, particularly in the field of medication administration. Inadequate adherence to medication is a serious worldwide issue that can result in poor health and higher medical expenses. Through continuous monitoring and analysis of patient-specific parameters, such as vital signs, medication history, and lifestyle factors, the system dynamically adjusts medication schedules and dosages to optimize therapeutic efficacy while minimizing adverse effects. The system tracks medicine usage, vital signs, and ambient variables using data gathered from Internet of Things (IoT) devices like wearable devices and smart pill bottles. An ML model, trained to anticipate potential adherence problems, is then provided with this preprocessed data. Personalized interventions, like medicine reminders, educational content, and progress reports, are delivered by the Intelligent Medication Compliance System (IMAC) based on these predictions. The integration of IoT-enabled smart sensors and connectivity allows for smooth communication between patients, healthcare professionals, and medicine dispensers, permitting prompt interventions, prescription reminders, and remote monitoring. Additionally, the system makes it easier for patients and medical professionals to communicate, allowing for prompt modifications to treatment programs. Serving as an anticipatory system, the IMAC provides personalized interventions. Predicting possible adherence problems, such as missing doses or inadvertent drug interactions, is done by the model through data analysis. The proposed IMAS seeks to empower patients, personalized medication management, and eventually improve medication adherence by fusing real-time IoT data with ML-driven insights. © 2024 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

On the O(√d/T1/4) Convergence Rate of RMSProp and Its Momentum Extension Measured by 1 Norm

arXiv

引用

arXiv 2024年

作者： Li, Huan Lin, Zhouchen Institute of Robotics and Automatic Information Systems College of Artificial Intelligence Nankai University Tianjin China National Key Lab of General AI School of Intelligence Science and Technology Peking University Beijing China

Although adaptive gradient methods have been extensively used in deep learning, their convergence rates proved in the literature are all slower than that of SGD, particularly with respect to their dependence on the dimension. This paper considers the classical RMSProp and its momentum extension and establishes the convergence rate of (Equation presented) measured by 1 norm without the bounded gradient assumption, where d is the dimension of the optimization variable, T is the iteration number, and C is a constant identical to that appeared in the optimal convergence rate of SGD. Our convergence rate matches the lower bound with respect to all the coefficients except the dimension d. Since x2 x1 ≤ √dx2 for problems with extremely large d, our convergence rate can be considered to be analogous to the (Equation presented) rate of SGD in the ideal case of ∇f(x)1 = Θ(√d∇f(x)2). © 2024, CC BY.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Optimal scheduling of islanded microgrid based on improved MOSSA 43

Optimal scheduling of islanded microgrid based on improved M...

引用

43rd Chinese Control Conference, CCC 2024

作者： Huanhuan, Lai Qingqi, Pei Meiqin, Liu Shanling, Dong Zhiyun, Xie Jian, Zheng Hezuo, Qu Senlin, Zhang Wenzhou Branch of State Grid Wenzhou325028 China Zhejiang University College of Electrical Engineering Hangzhou310027 China Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou310027 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Xi'an710049 China Jinhua Research Institute of Zhejiang University Jinhua321036 China

ISBN: (纸本)9789887581581

Microgrid systems are widely used in various scenarios. However, there is great uncertainty in the output of wind and solar units. How to maximize both the economic and environmental benefits of microgrid is an important issue. To achieve this, considering consumption of renewable energy and total cost, a multi-objective optimization model for islanded microgrid is established. The classical optimization algorithm has insufficient ability to approach the optimal solution in each dimension when facing multi-objective optimization. Thus, this paper introduces the fuzzy clustering mechanism and the non-dominated sorting method to obtain the improved multi-objective sparrow search algorithm (MOSSA). Taking data of renewable energy units and loads from a certain microgrid as test case, the Pareto frontier is searched by improved MOSSA. The experimental results show that the proposed method can effectively reduce the economic cost and improve the absorption capacity of wind power and photovoltaic energy. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： improved MOSSA microgrid multi-objective optimization Pareto frontier

来源：评论

学校读者我要写书评

暂无评论

OpenSatMap: a fine-grained high-resolution satellite dataset for large-scale map construction 24

OpenSatMap: a fine-grained high-resolution satellite dataset...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Hongbo Zhao Lue Fan Yuntao Chen Haochen Wang Yuran Yang Xiaojuan Jin Yixin Zhang Gaofeng Meng Zhaoxiang Zhang Institute of Automation Chinese Academy of Sciences (CASIA) and University of Chinese Academy of Sciences (UCAS) Centre for Artificial Intelligence and Robotics HKISI CAS Tencent Maps Tencent and Beijing University of Posts and Telecommunications Institute of Automation Chinese Academy of Sciences (CASIA) Tencent Maps Tencent Institute of Automation Chinese Academy of Sciences (CASIA) and Centre for Artificial Intelligence and Robotics HKISI CAS and University of Chinese Academy of Sciences (UCAS)

ISBN: (纸本)9798331314385

In this paper, we propose OpenSatMap, a fine-grained, high-resolution satellite dataset for large-scale map construction. Map construction is one of the foundations of the transportation industry, such as navigation and autonomous driving. Extracting road structures from satellite images is an efficient way to construct large-scale maps. However, existing satellite datasets provide only coarse semantic-level labels with a relatively low resolution (up to level 19), impeding the advancement of this field. In contrast, the proposed OpenSatMap (1) has fine-grained instance-level annotations; (2) consists of high-resolution images (level 20); (3) is currently the largest one of its kind; (4) collects data with high diversity. Moreover, OpenSatMap covers and aligns with the popular nuScenes dataset and Argoverse 2 dataset to potentially advance autonomous driving technologies. By publishing and main taining the dataset, we provide a high-quality benchmark for satellite-based map construction and downstream tasks like autonomous driving.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Dense Object Detector with Scale Balanced Sample Assignment and Refinement

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Dong, Jinpeng Yao, Dingyi Hu, Yufeng Zhou, Sanping Zheng, Nanning Xi’an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an710049 China Xi’an Jiaotong University Shaanxi Xi’an710049 China

Scale variation of objects remains one of the crucial challenges in object detection. Currently, conventional dense detectors with fixed receptive fields and label weights are not conducive to the detection of multi-scale objects. However, the design limitations of unbalanced label weights and fixed refinement for multi-scale objects and multi-tasks in these studies make it difficult to achieve better detection performance. In this paper, we propose a novel dense detector named Balanced FCOS which consists of two components: Balanced Label Assignment (BLA) and Flexible Shape-based Refinement (FSR). The BLA implements scale-balanced sample assignment by introducing reweighting factors consisting of localization and classification scores into the label assignment. Low-quality but high-weight samples can be weakened by the BLA. Furthermore, we design a cross-reweighting mechanism in the BLA to ensure score consistency between classification and localization. The FSR implements scale-balanced sample refinement by learning flexible sample points’ offsets for multi-scale objects and multi-tasks based on objects’ coarse features to get more discriminative features with appropriate receptive field. In addition, better features obtained by FSR are beneficial to get better classification and localization scores, which can be used by BLA to produce accurate label weights. Only equipped with the BLA, we can achieve 41.7/46.6 AP under R50/R101-FCOS without any additional parameters. When combining the BLA with the FSR, our Balanced FCOS achieves SOTA results among dense detectors on the COCO test-dev set. Experiments conducted on other heads (T-Head, DyHead), detectors (DINO), and datasets (AI-TOD) further demonstrate the effectiveness of our method. (Figure presented) © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

CaKDP: Category-Aware Knowledge Distillation and Pruning Framework for Lightweight 3D Object Detection

CaKDP: Category-Aware Knowledge Distillation and Pruning Fra...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Haonan Zhang Longjun Liu Yuqi Huang Zhao Yang Xinyu Lei Bihan Wen National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Nanyang Technological University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Knowledge distillation (KD) possesses immense potential to accelerate the deep neural networks (DNNs) for LiDAR-based 3D detection. However, in most of prevailing approaches, the suboptimal teacher models and insufficient student architecture investigations limit the performance gains. To address these issues, we propose a simple yet effective Category-aware Knowledge Distillation and Pruning (CaKDP) framework for compressing 3D detectors. Firstly, CaKDP transfers the knowledge of two-stage detector to one-stage student one, mitigating the impact of inadequate teacher models. To bridge the gap between the heterogeneous detectors, we investigate their differences, and then introduce the student-motivated category-aware KD to align the category prediction between distillation pairs. Secondly, we propose a category-aware pruning scheme to obtain the customizable architecture of compact student model. The method calculates the category prediction gap before and after removing each filter to evaluate the importance of filters, and retains the important filters. Finally, to further improve the student performance, a modified IOU-aware refinement module with negligible computations is leveraged to remove the redundant false positive predictions. Experiments demonstrate that CaKDP achieves the compact detector with high performance. For example, on WOD, CaKDP accelerates CenterPoint by half while boosting L2 mAPH by 1.61%. The code is available at https://***/zhnxjtu/CaKDP.

关键词： Knowledge engineering Computer vision Three-dimensional displays Computational modeling Detectors Computer architecture Object detection

来源：评论

学校读者我要写书评

暂无评论

Robust Noisy Label Learning via Two-Stream Sample Distillation

arXiv

引用

arXiv 2024年

作者： Bai, Sihan Zhou, Sanping Qin, Zheng Wang, Le Zheng, Nanning The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Shaanxi 710049 China

Noisy label learning aims to learn robust networks under the supervision of noisy labels, which plays a critical role in deep learning. Existing work either conducts s ample selection or label correction to deal with noisy labels during the model training process. In this paper, we design a simple yet effective sample selection framework, termed Two-Stream Sample Distillation (TSSD), for noisy label learning, which can extract more high-quality samples with clean labels to improve the robustness of network training. Firstly, a novel Parallel Sample Division (PSD) module is designed to generate a certain training set with sufficient reliable positive and negative samples by jointly considering the sample structure in feature space and the human prior in loss space. Secondly, a novel Meta Sample Purification (MSP) module is further designed to mine adequate semi-hard samples from the remaining uncertain training set by learning a strong meta classifier with extra golden data. As a result, more and more high-quality samples will be distilled from the noisy training set to train networks robustly in every iteration. Extensive experiments on four benchmark datasets, including CIFAR-10, CIFAR-100, Tiny-ImageNet, and Clothing-1M, show that our method has achieved state-of-the-art results over its competitors. Copyright © 2024, The Authors. All rights reserved.

关键词： Image classification

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：