检索结果-内蒙古大学图书馆

14th International Conference on Information Technology in Medicine and Education, ITME 2024

作者： Jiang, Haolong Gu, Lingdan Wang, Jiayu Lan, Xiao Liu, Qinyao Wang, Fanxin Xi'an Jiaotong Liverpool University University of Liverpool School of Advanced Technology Department of Electrical and Electronic Engineering Suzhou China Xi'an Jiaotong Liverpool University School of Robotics Department of Intelligence Robotics Engineering With Contemporary Entrepreneurialism Suzhou China Xi'an Jiaotong Liverpool University School of Advanced Technology Department of Information and Computer Science Suzhou China Xi'an Jiaotong Liverpool University School of Advanced Technology Department of Electrical and Electronic Engineering Suzhou China Xi'an Jiaotong Liverpool University School of Advanced Technology Department of Mechatronics and Robotics Suzhou China

ISBN: (纸本)9798350356670

Navigating cluttered indoor environments presents a significant challenge for aerial robots, requiring agility, speed, and a high level of reliability to avoid collisions. This project aims to address this challenge by developing advanced algorithms for lightweight drones, enabling them to reach target location and carrying out delivery efficiently and safely. Utilizing camera data to map and avoid obstacles, we create a system that not only maps and perceives the environment but also navigates its path to the destination. Included in the educational content, this project demonstrates the effectiveness of the technology through practical applications and real-world testing, helping the next generation of engineers accumulate technical experience and broaden their understanding of drone navigation algorithms and applications in system integration. It has a milestone impact on education and development of the drone field. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Automatic Cataract and Cholesterol Detection System Based on Recurrent Neural Network (RNN): A Comparison with Convolutional Neural Network (CNN) and Siamese Neural Network (SNN) 1

引用

19th International Conference of Intelligent Unmanned Systems, ICIUS 2023

作者： Lie, Zener S. Widodo, Jatmiko A. F. Hanesi, Isabel K. P. Moningka, Matthew R. N. Mariana, Y. Astuti, Winda Akmeliawati, Rini Automotive and Robotics Program Computer Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia Product Design program Industrial Engineering Department BINUS ASO School of Engineering Bina Nusantara University Jakarta11480 Indonesia Robotics and Automation Research Group School of Electrical and Mechanical Engineering The University of Adelaide North Terrace Campus Adelaide Australia

ISBN: (数字)9789819765911

ISBN: (纸本)9789819765904

In Indonesia, the majority of blindness cases, approximately 81%, are attributed to cataract. Additionally, 35% of the population has higher cholesterol levels than the standard normal range. The lack of specialized medical equipment, such as the slit-lamp (Ruparelia in Dalhousie Med J 49(1), [1]) bio-microscope, and trained professionals, especially in rural areas, make it difficult to detect these conditions through eye examinations. To address this issue, a supervised machine learning method, the Recurrent Neural Network (RNN), has been utilized to create an iris scanner system that can identify cataract and high cholesterol in a patient. This system will classify eyes into three categories, i.e., cataract, high cholesterol, and normal iris. The computer simulations indicate that this technique is more accurate and requires less training time compared to the existing Convolutional Neural Network (ANN) and Siamese Neural Network (SNN)-based method, while achieving 100% accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Comparison between Docker and Kubernetes based Edge Architectures for Enabling Remote Model Predictive Control for Aerial Robots 48

Comparison between Docker and Kubernetes based Edge Architec...

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Santi Seisa, Achilleas Gajanan Satpute, Sumeet Nikolakopoulos, George Luleå University of Technology Robotics and Ai Team Department of Computer Electrical and Space Engineering Luleå Sweden

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Edge computing is becoming more and more popular among researchers who seek to take advantage of the edge resources and the minimal time delays, in order to run their robotic applications more efficiently. Recently, many edge architectures have been proposed, each of them having their advantages and disadvantages, depending on each application. In this work, we present two different edge architectures for controlling the trajectory of an Unmanned Aerial Vehicle (UAV). The first architecture is based on docker containers and the second one is based on kubernetes, while the main framework for operating the robot is the Robotic Operating System (ROS). The efficiency of the overall proposed scheme is being evaluated through extended simulations for comparing the two architectures and the overall results obtained. © 2022 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Real-Time Imitation of Human Head Motions, Blinks and Emotions by Nao Robot: A Closed-Loop Approach 11

Real-Time Imitation of Human Head Motions, Blinks and Emotio...

引用

11th RSI International Conference on robotics and Mechatronics, ICRoM 2023

作者： Rayati, Keyhan Feizi, Amirhossein Beigy, Alireza Shahverdi, Pourya Masouleh, Mehdi Tale Kalhor, Ahmad Louie, Wing-Yue Geoffrey University of Tehran Human and Robot Interaction Lab Electrical and Computer Engineering Tehran Iran Shahrood University of Technology Department of Electrical Engineering Shahrood Iran Oakland University Intelligent Robotics Laboratory Michigan United States

ISBN: (纸本)9798350308105

This paper introduces a novel approach for enabling real-time imitation of human head motion by a Nao robot, with a primary focus on elevating human-robot interactions. By using the robust capabilities of the MediaPipe as a computer vision library and the DeepFace as an emotion recognition library, this research endeavors to capture the subtleties of human head motion, including blink actions and emotional expressions, and seamlessly incorporate these indicators into the robot's responses. The result is a comprehensive framework which facilitates precise head imitation within human-robot interactions, utilizing a closed-loop approach that involves gathering real-time feedback from the robot's imitation performance. This feedback loop ensures a high degree of accuracy in modeling head motion, as evidenced by an impressive R2 score of 96.3 for pitch and 98.9 for yaw. Notably, the proposed approach holds promise in improving communication for children with autism, offering them a valuable tool for more effective interaction. In essence, proposed work explores the integration of real-time head imitation and real-time emotion recognition to enhance human-robot interactions, with potential benefits for individuals with unique communication needs. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

FAIR-FATE: Fair Federated Learning with Momentum 23rd

FAIR-FATE: Fair Federated Learning with Momentum

引用

23rd International Conference on Computational Science, ICCS 2023

作者： Salazar, Teresa Fernandes, Miguel Araújo, Helder Abreu, Pedro Henriques Centre for Informatics and Systems Department of Informatics Engineering of the University of Coimbra University of Coimbra Coimbra Portugal Institute of Systems and Robotics Department of Electrical and Computer Engineering of the University of Coimbra University of Coimbra Coimbra Portugal

ISBN: (纸本)9783031359941

While fairness-aware machine learning algorithms have been receiving increasing attention, the focus has been on centralized machine learning, leaving decentralized methods underexplored. Federated Learning is a decentralized form of machine learning where clients train local models with a server aggregating them to obtain a shared global model. Data heterogeneity amongst clients is a common characteristic of Federated Learning, which may induce or exacerbate discrimination of unprivileged groups defined by sensitive attributes such as race or gender. In this work we propose FAIR-FATE: a novel FAIR FederATEd Learning algorithm that aims to achieve group fairness while maintaining high utility via a fairness-aware aggregation method that computes the global model by taking into account the fairness of the clients. To achieve that, the global model update is computed by estimating a fair model update using a Momentum term that helps to overcome the oscillations of non-fair gradients. To the best of our knowledge, this is the first approach in machine learning that aims to achieve fairness using a fair Momentum estimate. Experimental results on real-world datasets demonstrate that FAIR-FATE outperforms state-of-the-art fair Federated Learning algorithms under different levels of data heterogeneity. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Implementing SLAM for Robot Navigation with Lidar in ROS Platform 4

Implementing SLAM for Robot Navigation with Lidar in ROS Pla...

引用

4th IEEE International Conference on Emerging Frontiers in electrical and Electronic Technologies, ICEFEET 2024

作者： Verma, Gaurav Kumar Ray, Ranjit Swar, Surya Narayan Meena, Gagan Deep Dept. of Electrical Engineering National Institute of Technology Patna India Underwater Robotics & Autonomous Group CSIR-Central Mechanical Engineering Research Institute Durgapur India Department of Computer Science & Engineering Gandhi Institute of Engineering and Technology University Gunupur India

ISBN: (纸本)9798331528614

This research covers the implementation of SLAM (Simultaneous Localization and Mapping) with Ouster OS0 LiDAR (Light Detection and Ranging) sensor in the Robot Operating System (ROS1) Noetic. Using the high-frequency capabilities of the ouster, this method works towards mapping and localization in structured and unstructured environments. The paper explains the Ouster sensor integration in the ROS1 Noetic environment, providing information on the sensor calibration, data acquisition, and pre-processing. The ROS ecosystem in Ubuntu 20.04 is set to process the data streams coming from the ouster LiDAR sensor which is further utilised to create map and localize the robot. The Ouster LiDAR sensor scans every object in its field of view (in 3D), the data is then used for the SLAM. SLAM is executed using the Direct Lidar Odometry (DLO) algorithm for mapping and simultaneously helping the robot with localization and enabling it to navigate through the environment smoothly and precisely. © 2024 IEEE.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Multimodal Human Detection using RGB, Thermal and LiDAR modalities for Robotic Perception

Multimodal Human Detection using RGB, Thermal and LiDAR moda...

引用

IEEE International Conference on Automation Science and engineering (CASE)

作者： Kennedy O. S. Mota Luís Garrote Cristiano Premebida Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Portugal

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

People detection is a relevant research topic in artificial perception with wide range of applications from security, surveillance, robotics to autonomous driving. Overcoming challenges in this field involves advanced algorithms, combination of machine learning approaches, as well as the use of sensory data e.g., from cameras and LiDARs. This work addresses the problem of people detection using YOLO, a state-of-the-art object detection method, trained on three distinct data sources LiDAR, RGB (color) and ‘thermal’ (long-wave infra-red) images. The rationale for combining multiple-sensory representation relies on the assumption that each sensor has its own advantages and disadvantages, but together they normally complement each other - specially in real-world conditions. LiDAR contributes to a physically-interpretable mapping of the environment, providing precise information regarding size/dimension and location of the objects, while RGB and thermal provide relevant textural features. The sensors have been calibrated w.r.t. each other thus, allowing the LiDAR’s point-clouds to be projected into the image plane, followed by an up-sampling step, to create dense-depth maps (DM) that enable direct use of the YOLO framework. To support the experiments, a new multi-sensory dataset has been collected using a mobile robot. Besides single-modality models, this paper also explores early and late-fusion strategies. Finally, the new dataset has been made available in a Github repository 1 .

关键词： YOLO Laser radar Machine learning algorithms Surveillance Soft sensors Thermal engineering Robot vision systems Security Mobile robots Software development management

来源：评论

学校读者我要写书评

暂无评论

Online 3D Bin Packing for Novel Objects Based on Deep Reinforcement Learning

Online 3D Bin Packing for Novel Objects Based on Deep Reinfo...

引用

2023 International Conference on Advanced robotics and Intelligent Systems, ARIS 2023

作者： Chien, Shao-Yu Wong, Ching-Chang Tamkang University College of Engineering Doctoral Program in Robotics New Taipei City25137 Taiwan Tamkang University Electrical and Computer Engineering Department New Taipei City25137 Taiwan

ISBN: (纸本)9798350302714

In this paper, a method using deep reinforcement learning is proposed to deal with the 3D online bin packing problem. The packing objects are not limited to several specific or fixed cuboid objects, but are composed of more than a thousand objects and randomly generated cuboids, which make the trained policy network can handle novel unknown objects. In addition, the posture of the object in the box can be any angle, not limited to horizontal and vertical. In the proposed method, four voxel maps are used as inputs, and a Soft Actor-Critic (SAC) algorithm is used to train a policy network. On the other hand, in order to deal with various objects with irregular shapes, a packing task simulator with physics engine enable the policy network to learn the state of falling and stacking objects. In terms of training environment of deep reinforcement learning, the proposed method can be applied to boxes of different sizes because of the scalable image information. Moreover, a reward function and a training strategy with gradually increasing difficulty are proposed to effectively improve the learning of policy network. In terms of experimental results, the results on a random object bin packing task in a simulator illustrate the effectiveness of the proposed method. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Compliant Robot-Assisted Mold Polishing Application Using the Franka Emika Robot 49

A Compliant Robot-Assisted Mold Polishing Application Using ...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Xenya, Michael Christopher Cortesao, Rui Institute of Systems and Robotics University of Coimbra Electrical and Computer Engineering Department Coimbra3030-290 Portugal FOE GCTU PMB100 Accra Ghana

ISBN: (纸本)9798350331820

Metal mold casting for many application areas remains imperfect since this involves the control of numerous factors that affect workpiece quality. Surface roughness which remains one of the many issues related to metal mold cast is often mitigated by means of grinding and polishing. As many attempts are being made to address this challenge through robot-assisted techniques, we focus on rapid mold polishing using the Franka Emika (FE) robot and its programming resources, including a built-in impedance control architecture. To accomplish the objective, mold surface segmentation is necessary. For each segment, the polishing approach is based on surface normals, relative motion, and torque sensor data. Results were obtained with open platform communication-unified architecture (opc-ua) client and server that record torque and force data. Results show that tuning internal impedance control parameters for polishing tasks is feasible. © 2023 IEEE.

关键词： Polishing

来源：评论

学校读者我要写书评

暂无评论

AG-VPReID: A Challenging Large-Scale Benchmark for Aerial-Ground Video-based Person Re-Identification

arXiv

引用

arXiv 2025年

作者： Nguyen, Huy Nguyen, Kien Pemasiri, Akila Liu, Feng Sridharan, Sridha Fookes, Clinton School of Electrical Engineering and Robotics Queensland University of Technology Australia Department of Electrical and Computer Engineering Drexel University United States

We introduce AG-VPReID, a challenging large-scale benchmark dataset for aerial-ground video-based person re-identification (ReID), comprising 6,632 identities, 32,321 tracklets, and 9.6 million frames captured from drones (15-120m altitude), CCTV, and wearable cameras. This dataset presents a real-world benchmark to investigate the robustness of Person ReID approaches against the unique challenges of cross-platform aerial-ground settings. To address these challenges, we propose AG-VPReID-Net, an end-to-end framework combining three complementary streams: (1) an Adapted Temporal-Spatial Stream addressing motion pattern inconsistencies and temporal feature learning, (2) a Normalized Appearance Stream using physics-informed techniques to tackle resolution and appearance changes, and (3) a Multi-Scale Attention Stream handling scale variations across drone altitudes. Our approach integrates complementary visual-semantic information from all streams to generate robust, viewpoint-invariant person representations. Extensive experiments demonstrate that AG-VPReID-Net outperforms state-of-the-art approaches on both our new dataset and other existing video-based ReID benchmarks, showcasing its effectiveness and generalizability. The relatively lower performance of all state-of-the-art approaches, including our proposed approach, on our new dataset highlights its challenging nature. The AG-VPReID dataset, code and models are available at https://***/agvpreid25/AG-VPReID-Net. © 2025, CC BY.

关键词： Drones

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：