检索结果-内蒙古大学图书馆

3D Printing Strategy in Manufacturing of Health Monitoring Devices

Macromolecular Symposia 2024年第3期413卷 2300205-2300205页

作者： Ulmeanu, Mihaela-Elena Doicin, Cristian-Vasile Lamanna, Giuseppe Opran, Constantin Nițuică, Pavel-Mihai Faculty of Industrial Engineering and Robotics National University of Science and Technology POLITEHNICA Bucharest Splaiul Independentei 313 Bucharest Romania University of Campania "Luigi Vanvitelli" Via Roma 9 CE Aversa81031 Italy

The paper proposes a study regarding the influence of support structure parameters on customer targets for 3D printed bespoke health monitoring devices, specifically a wrist casing. The evolution of additive manufacturing for personalized medical devices needs a comprehensive understanding of the support structure parameters in respect to the anthropomorphic designs of these products. This study investigates how these specific parameters influence vital customer targets, which include time efficiency, cost optimization, surface roughness, fit, and overall patient compliance. Diverse configurations of the support parameters are analyzed, employing a methodology based on experimental evaluations. Overhang angle is found to directly correlate with print time and surface roughness, while support density exhibits a marked influence on cost implications and dimensional accuracy. Notably, variations in support pattern demonstrated discernible differences in the overall quality and cost-efficiency of the printed devices. © 2024 Wiley-VCH GmbH.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Improving Trust Estimation in Human-Robot Collaboration Using Beta Reputation at Fine-grained Timescales

arXiv

引用

arXiv 2024年

作者： Dagdanov, Resul Andrejević, Milan Liu, Dikai Lin, Chin-Teng The Robotics Institute Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia The Psychology Discipline Graduate School of Health Faculty of Health University of Technology Sydney UltimoNSW2007 Australia The Australian Artificial Intelligence Institute School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney UltimoNSW2007 Australia

When interacting with each other, humans adjust their behavior based on perceived trust. However, to achieve similar adaptability, robots must accurately estimate human trust at sufficiently granular timescales during the human-robot collaboration task. A beta reputation is a popular way to formalize a mathematical estimation of human trust. However, it relies on binary performance, which updates trust estimations only after each task concludes. Additionally, manually crafting a reward function is the usual method of building a performance indicator, which is labor-intensive and time-consuming. These limitations prevent efficiently capturing continuous changes in trust at more granular timescales throughout the collaboration task. Therefore, this paper presents a new framework for the estimation of human trust using a beta reputation at fine-grained timescales. To achieve granularity in beta reputation, we utilize continuous reward values to update trust estimations at each timestep of a task. We construct a continuous reward function using maximum entropy optimization to eliminate the need for the laborious specification of a performance indicator. The proposed framework improves trust estimations by increasing accuracy, eliminating the need for manually crafting a reward function, and advancing toward developing more intelligent robots. The source code is publicly available. © 2024, CC BY.

关键词： Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Self Decoupling-Reconstruction Network for Facial Expression Recognition

Self Decoupling-Reconstruction Network for Facial Expression...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Linhuang Wang Xin Kang Fei Ding Hai-Tao Yu Yunong Wu Kazuyuki Matsumoto Satoshi Nakagawa Fuji Ren Graduate School of Advanced Technology and Science Tokushima University Tokushima Japan Faculty of Library Information and Media Science University of Tsukuba Tsukuba Japan Dataa Robotics Chengdu China Graduate School of Information Science & Technology The University of Tokyo Tokyo Japan School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Facial Expression Recognition (FER) poses significant challenges due to various imaging conditions, including diverse head poses, lighting conditions, resolutions, and occlusions. Additionally, different personal attributes such as age, gender, and racial background further contribute to the complexity of FER. To accurately extract meaningful expression features amidst these interfering factors to enhance recognition accuracy and the model’s generalization, we propose a Self Decoupling-Reconstruction Network (SDRNet). Specifically, our approach involves two learning processes. In the first phase, the network is trained to decouple facial images with expressions into expression and neutral components. This process involves reconstructing neutral facial images and the original input, ensuring the preservation of meaningful expression components devoid of interference in the decoupling process. In the second learning phase, we employ simple convolutional neural networks (CNNs) to recognize the extracted expression components. Our method has achieved state-of-the-art results across multiple widely used datasets, providing substantial evidence of its effectiveness. Additionally, we demonstrate the robust generalization performance of our approach through cross-database evaluations.

关键词： Image resolution Image recognition Head Face recognition Neural networks Lighting Imaging

来源：评论

学校读者我要写书评

暂无评论

Nussbaum Function Based PID Approach for Tracking Control of Robot Manipulators

Nussbaum Function Based PID Approach for Tracking Control of...

引用

Mediterranean Conference on Control and Automation (MED)

作者： Hamed Rahimi Nohooji Holger Voos Interdisciplinary Centre for Security Reliability and Trust (SnT) Automation Robotics Research Group University of Luxembourg Department of Engineering Interdisciplinary Centre for Security Reliability and Trust (SnT) Automation Robotics Research Group Faculty of Science Technology and Medicine (FSTM) University of Luxembourg

ISBN: (数字)9798350395440

ISBN: (纸本)9798350395457

This paper introduces a novel Nussbaum function-based PID control for robotic manipulators. The integration of the Nussbaum function into the PID frame-work provides a solution with a simple structure that effectively tackles the challenge of unknown control di-rections. Stability is achieved through a combination of neural network-based estimation and Lyapunov analysis, facilitating automatic gain adjustment without the need for system dynamics. Our approach offers a gain determination with minimum parameter requirements, significantly reducing the complexity and enhancing the efficiency of robotic manipulator control. The paper guarantees that all signals within the closed-loop system remain bounded. Lastly, numerical simulations validate the theoretical framework, confirming the effectiveness of the proposed control strategy in enhancing robotic manipulator control.

关键词： Technological innovation PI control Estimation Stability analysis Trajectory Complexity theory PD control

来源：评论

学校读者我要写书评

暂无评论

HISTOHDR-NET: HISTOGRAM EQUALIZATION FOR SINGLE LDR TO HDR IMAGE TRANSLATION

arXiv

引用

arXiv 2024年

作者： Barua, Hrishav Bakul Krishnasamy, Ganesh Wong, KokSheik Dhall, Abhinav Stefanov, Kalin School of Information Technology Monash University Malaysia Malaysia Robotics and Autonomous Systems Group TCS Research India College of Science and Engineering Flinders University Australia Faculty of Information Technology Monash University Australia

High Dynamic Range (HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes. Due to the high costs associated with HDR imaging, the literature offers various data-driven methods for HDR image reconstruction from Low Dynamic Range (LDR) counterparts. A common limitation of these approaches is missing details in regions of the reconstructed HDR images, which are over- or under-exposed in the input LDR images. To this end, we propose a simple and effective method, HistoHDR-Net, to recover the fine details (e.g., color, contrast, saturation, and brightness) of HDR images via a fusion-based approach utilizing histogram-equalized LDR images along with self-attention guidance. Our experiments demonstrate the efficacy of the proposed approach over the state-of-art *** Codes Artificial intelligence, Computer vision, Machine learning, Deep learning Copyright © 2024, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation

arXiv

引用

arXiv 2025年

作者： Gao, Jianqi Pang, Xizheng Liu, Qi Li, Yanjie The Department of Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics School of Inteligence Science and Engineering Harbin Institute of Technology Shenzhen518055 China The Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China

Reinforcement learning-based mapless navigation holds significant potential. However, it faces challenges in indoor environments with local minima area. This paper introduces a safe mapless navigation framework utilizing hierarchical reinforcement learning (HRL) to enhance navigation through such areas. The high-level policy creates a sub-goal to direct the navigation process. Notably, we have developed a sub-goal update mechanism that considers environment congestion, efficiently avoiding the entrapment of the robot in local minimum areas. The low-level motion planning policy, trained through safe reinforcement learning, outputs real-time control instructions based on acquired sub-goal. Specifically, to enhance the robot’s environmental perception, we introduce a new obstacle encoding method that evaluates the impact of obstacles on the robot’s motion planning. To validate the performance of our HRL-based navigation framework, we conduct simulations in office, home, and restaurant environments. The findings demonstrate that our HRL-based navigation framework excels in both static and dynamic scenarios. Finally, we implement the HRL-based navigation framework on a TurtleBot3 robot for physical validation experiments, which exhibits its strong generalization capabilities. Copyright © 2025, The Authors. All rights reserved.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Parallel Path Planning for Multi-Robot Coordination 25

Parallel Path Planning for Multi-Robot Coordination

引用

25th IEEE International Conference on Autonomous Robot Systems and Competitions, ICARSC 2025

作者： Ribeiro, Jorge Brilhante, Marina Matos, Diogo Miguel Silva, Carlos A. Sobreira, Heber Costa, Pedro INESC TEC - Institute for Systems and Computer Engineering Technology and Science CRIIS - Centre of Robotics in Industry and Intelligent Systems Porto 4200-465 Portugal University of Porto Faculty of Engineering Porto 4200-465 Portugal Flowbotic Mobile Systems S.A Viseu 3530-259 Portugal

ISBN: (纸本)9798331538606

Multi-robot coordination aims to synchronize robots for optimized, collision-free paths in shared environments, addressing task allocation, collision avoidance, and path planning challenges. The Time Enhanced A∗ (TEA*) algorithm addresses multi-robot pathfinding offering a centralized and sequential approach. However, its sequential nature can lead to order-dependent variability in solutions. This study enhances TEA∗ through multi-threading, using thread pooling and parallelization techniques via OpenMP, and a sensitivity analysis enabling parallel exploration of robot-solving orders to improve robustness and the likelihood of finding efficient, feasible paths in complex environments. The results show that this approach improved coordination efficiency, reducing replanning needs and simulation time. Additionally, the sensitivity analysis assesses TEA*'s scalability across various graph sizes and number of robots, providing insights into how these factors influence the efficiency and performance of the algorithm. © 2025 IEEE.

关键词： centralized path planning multi-robot system multi-threading sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Lossless Compression Technique in Quantum Secure Direct Communication

A Comparative Study of Lossless Compression Technique in Qua...

引用

Cyber Security and Computing (CyberComp), International Conference on

作者： Izlin Zuriani Ishak Liew Seow Wooi Nur Ziadah Harun Nur Shahirah Azahari Sofia Najwa Ramli Osman Ghazali Department of Information Technology and Communication Politeknik Seberang Perai Pulau Pinang Malaysia Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia Selangor Malaysia Faculty of AI and Robotics Raffles University Johor Malaysia Department of Information Security and Web Technology Faculty of Computer Science and Information Technology Universiti Tun Hussein Onn Malaysia Johor Malaysia School of Computing Universiti Utara Malaysia Kedah Malaysia

ISBN: (数字)9798350387728

ISBN: (纸本)9798350387735

This is a comparative study to explore the performance of three lossless compression techniques, namely Run Length Encoding (RLE), Shannon-Fano Coding (SFC), and Huffman Coding (HC) in the context of a Hybrid M-Ary in Braided Single Stage (HMBSS) protocol communication scheme. The previous study on HMBSS using HC found that HC's compression technique has drawbacks, i.e., it is sensitive to errors and noise in the transmission channel and limited to certain data types. These drawbacks did affect the value of the compression rate limit. In this study, we evaluate the effectiveness of RLE, SFC, and HC in terms of data size reduction, coding efficiency, and data transmission time by comparing their results arising from the simulation experiments using Python coding in Jupiter Notebook and developed based on the HMBSS protocol algorithm. This simulation experiment starts with an initial six randomly generated datasets. Each dataset is tested using three compression techniques, which resulted in 18 different datasets. The results from the experiments reveal that SFC and HC consistently achieved a higher compression ratio and coding efficiency than RLE. These two compression techniques' algorithms effectively reduce the data size while preserving the original information. In our study, we also find that the data transmission time is increased with larger text sizes for all three compression techniques. This indicates that the larger the data size, the more transmission time is required with regard to what the compression technique's algorithm is.

关键词： Protocols Quantum computing Jupiter Noise Decoding Complexity theory Data communication Channel coding Huffman coding Testing

来源：评论

学校读者我要写书评

暂无评论

Motion Control in Multi-Rotor Aerial Robots Using Deep Reinforcement Learning

Motion Control in Multi-Rotor Aerial Robots Using Deep Reinf...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Gaurav Shetty Mahya Ramezani Hamed Habibi Holger Voos Jose Luis Sanchez-Lopez Faculty of Science Technology and Medicine Automation and Robotics Research Group Interdisciplinary Centre for Security Reliability and Trust (SnT) University of Luxembourg Luxembourg Bonn-Rhein-Sieg University of Applied Sciences Germany

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

This paper investigates the application of Deep Reinforcement Learning (DRL) to address motion control challenges in drones for additive manufacturing (AM). Dronebased additive manufacturing offers a flexible and autonomous solution for material deposition in large-scale or hazardous environments. However, achieving robust real-time control of a multi-rotor aerial robot under varying payloads and potential disturbances remains challenging. Traditional controllers like PID often require frequent parameter re-tuning, limiting their applicability in dynamic scenarios. We propose a DRL framework that learns adaptable control policies for multirotor drones performing waypoint navigation in AM tasks. We compare Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic Policy Gradient (TD3) within a curriculum learning scheme designed to handle increasing complexity. Our experiments show TD3 consistently balances training stability, accuracy and success, particularly when mass variability is introduced. These findings provide a scalable path toward robust, autonomous drone control in additive manufacturing.

关键词： Training Accuracy Three-dimensional printing Autonomous aerial vehicles Deep reinforcement learning Aircraft navigation Complexity theory Motion control Thermal stability Drones

来源：评论

学校读者我要写书评

暂无评论

Development of a Novel Redundant Parallel Mechanism with Enlarged Workspace and Enhanced Dexterity for Fracture Reduction Surgery

Development of a Novel Redundant Parallel Mechanism with Enl...

引用

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

作者： Quan Yuan Xu Liang Tingting Su Weibang Bai ShanghaiTech Automation and Robotics (STAR) Center School of Information Science and Technology ShanghaiTech University Shanghai China School of Automation and Intelligence Beijing Jiaotong University Beijing China Faculty of Information Technology Beijing University of Technology Beijing China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

The limited workspace and complex singularity issues are predominant factors impeding the clinical applicability of fracture reduction parallel robots. To address these challenges, this paper proposes a novel redundant parallel mechanism (NRPM) for robotic-assisted fracture reduction with an enlarged workspace and enhanced dexterity capabilities based on the traditional Stewart parallel mechanism (SPM). With six redundant degrees-of-freedom (DOFs) added to the novel mechanism, the kinematics of NRPM needs to be thoroughly analyzed. Furthermore, the calculation of its workspace and determination of its dexterity are deduced. Both the analytical simulation and real experiment results demonstrated the effectiveness and superior performance of the proposed NRPM compared to SPM.

关键词： Parallel robots Force Surgery Prototypes Phantoms Kinematics Intelligent robots

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：