检索结果-内蒙古大学图书馆

26th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2023

作者： Marciniak, Tomasz Stankiewicz, Agnieszka Zaradzki, Przemyslaw Poznan University of Technology Division of Electronic Systems and Signal Processing Institute of Automatic Control and Robotics Department of Control Robotics and Electrical Engineering Poznan Poland

ISBN: (纸本)9798350304985

This paper presents an analysis of the effectiveness of blood vessel segmentation in human retinal images. The segmentation process was carried out for three-dimensional optical coherence tomography (OCT) scans using the author's publicly available CAVRI-C database. A 3D version of the U-Net artificial neural network was used. Various dimensions of the input blocks were investigated to determine their influence on the segmentation process. The effectiveness of the proposed solutions was evaluated using various metrics and the results obtained were compared with the 2D solution, also based on neural networks. The use of the proposed solutions allowed us to improve the segmentation even by 15% (in the case of the F1-score). © 2023 Division of Signal Processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Optical tomography

来源：评论

学校读者我要写书评

暂无评论

A Multi-party Asymmetric Self-play Algorithm and Its Application in Multi-USV Adversarial Game Simulations 24

A Multi-party Asymmetric Self-play Algorithm and Its Applica...

引用

2024 International Conference on Machine Learning, Pattern Recognition and Automation engineering, MLPRAE 2024

作者： Rao, Jinjun Wang, Cong Liu, Mei Lei, Jingtao Giernacki, Wojciech Department of Precision Mechanical Engineering School of Mechatronic Engineering and Automation Shanghai University China Institute of Robotics and Machine Intelligence Faculty of Automatic Control Robotics and Electrical Engineering Poznan University of Technology Poland

ISBN: (纸本)9798400709876

Aiming at the problem that the combination of self-play (SP) and deep reinforcement learning (DRL) only involves two-party games and the policy learning of each party is limited, a multi-party asymmetric self-play algorithm (MASP) is proposed. Firstly, by improving the ELO scoring system, the ELO scoring takes into account each party of the unmanned surface vehicle (USV) clusters, and the imbalance of the number of USV clusters, so that the frequency of exchanging strategies of all USV clusters in the confrontation process is equal. Secondly, it ensures that USV clusters have a balanced combat ability, and at the same time ensures that the combat ability of all parties is strong and weak and the gap is not too wide. In addition, the parameters are dynamically set to reduce the update frequency of the policy of the stronger party. The experimental results show that the MASP can make the USV clusters learn more effective policies, have a shorter game time, and obtain higher rewards and ELO scores in the simple 2v2 adversarial game scenario and the three-party game scenario of a warship escort mission. © 2024 ACM.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5575-5588页

作者： Jiang, Zihan Ma, Yiqun Shi, Bingyu Lu, Xin Xing, Jian Goncalves, Nuno Jin, Bo Suzhou215000 China Northeast Forestry University College of Computer and Control Engineering Harbin150000 China University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Coimbra3030-290 Portugal

This article introduces a novel model for low-quality pedestrian trajectory prediction, the social nonstationary transformers (NSTransformers), that merges the strengths of NSTransformers and spatiotemporal graph transformer (STAR). The model can capture social interaction cues among pedestrians and integrate features across spatial and temporal dimensions to enhance the precision and resilience of trajectory predictions. We also propose an enhanced loss function that combines diversity loss with logarithmic root mean squared error (log-RMSE) to guarantee the reasonableness and diversity of the generated trajectories. This design adapts well to complex pedestrian interaction scenarios, thereby improving the reliability and accuracy of trajectory prediction. Furthermore, we integrate a generative adversarial network (GAN) to model the randomness inherent in pedestrian trajectories. Compared to the conventional standard Gaussian distribution, our GAN approach better simulates the intricate distribution found in pedestrian trajectories, enhancing the trajectory prediction's diversity and robustness. Experimental results reveal that our model outperforms several state-of-the-art methods. This research opens the avenue for future exploration in low-quality pedestrian trajectory prediction. © 2024 IEEE.

关键词： Stars

来源：评论

学校读者我要写书评

暂无评论

TOWARD SUPPORT-FREE, ZERO-DEGREE OVERHANG ADDITIVE MANUFACTURING USING A WANDERING CENTER OF MOTION

TOWARD SUPPORT-FREE, ZERO-DEGREE OVERHANG ADDITIVE MANUFACTU...

引用

ASME 2024 International Mechanical engineering Congress and Exposition, IMECE 2024

作者： Todd, Brody A. DeVries, Levi D. Kutzer, Michael D.M. Department of Weapons Robotics & Control Engineering United States Naval Academy AnnapolisMD21402 United States

ISBN: (纸本)9780791888605

In recent years, additive manufacturing (AM) has revolutionized traditional manufacturing processes by enabling complex geometries to be printed with enhanced design flexibility and reduced lead *** additive manufacturing processes utilize a planar, layer-by-layer deposition of materials ranging from plastics and ceramics to various composites and *** these traditional AM methods enable manufacturers to create made-to-order, functional parts, complex geometrical designs with large overhanging features often require sacrificial support structures to maintain material strength and *** research aims to develop a method of AM that adheres to zero-overhang constraints and eliminates the support structure requirements for complex *** proposed method leverages existing research on spherical layering and introduces a novel approach to AM involving a "wandering" remote center of motion (RCM).Using a wandering (***) RCM, spherical layering techniques can be applied to more complex geometries, specifically geometries that are not within the set of'star-convex' *** paper introduces the wandering RCM method in 2D by developing an algorithm to define unique RCM positions for a given *** goal is to decompose non-star convex polygons into multiple partitions of star-convex shapes, enabling the complete fill of a polygon using a 2D realization of spherical *** work leverages an extension to Chvátal's Art Gallery Problem, using "guard" positions to define RCM positions within the part's polygonal *** from 2D analysis demonstrate the feasibility of filling non-convex polygonal regions under a zero-overhang approach. Copyright © 2024 by The United States Government.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Task Load Based Persistent Coverage control for Large-Scale Domains Using Multi-Agent Systems with Anisotropic Sensors

Task Load Based Persistent Coverage Control for Large-Scale ...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Odoy, Kyle Rodríguez-Seda, Erick J. United States Naval Academy Department of Weapons Robotics and Control Engineering AnnapolisMD United States

ISBN: (纸本)9798331504847

Multi-agent coverage control refers to the task of coordinating autonomous robots to effectively survey and gather information across a task-domain. This paper introduces a novel approach that addresses agents equipped with anisotropic sensors and constrained by nonholonomic movement, aiming to ensure persistent coverage and maintain awareness over a large-scale domain. The approach employs redefined Voronoi partitions that leverage each agent's local coverage domain based on its relative task load. The task load herein refers to the level of awareness that each agent has about the domain and the size of its area of dominance, all indirectly encoded in the Voronoi's mass. To account for the vehicles' nonholonomic nature and velocity constraints, the proposed approach is extended using the minimum curvature-based distance when determining the agent's area of dominance. A set of simulations involving teams of three and five agents showcases the effectiveness of the proposed control approach. © 2025 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

All-Fabric Bi-directional Actuators for Multi-joint Assistance of Upper Limb

引用

Journal of Bionic engineering 2023年第6期20卷 2661-2669页

作者： Junlin Ma Diansheng Chen Zhe Liu Jie Wei Xianglin Zhang Zihan Zeng Yongkang Jiang Institute of Robotics Beihang UniversityBeijing100191China Department of Control Science and Engineering Tongji UniversityShanghai201804China Frontiers Science Center for Intelligent Autonomous Systems Shanghai201210China

According to clinical studies,upper limb robotic suits are vital to reduce therapist fatigue and accelerate patient *** pneumatic actuators have drawn increasing attention for the development of wearable robots due to their low weight,flexibility,and high power-to-weight ***,most of current actuators were designed for the flexion assistance of a specific joint,and that for joint extension requires further ***,designing an actuator for diverse working scenarios remains a *** this paper,we propose an all-fabric bi-directional actuator to assist the flexion and extension of the elbow,wrist,and fingers.A mathematical model is presented that predicts the deformation and guides the design of the proposed bi-directional *** further validate the applicability and adaptability of the proposed actuator for different joints,we developed a 3-DOF soft robotic *** results show that the robotic suit can assist the motion of the elbow,wrist,and finger of the subject.

关键词： Soft robotic suits Fabric-based actuators Multi-DOF motion Upper limb rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Video Stabilization using RAFT-based Optical Flow

Video Stabilization using RAFT-based Optical Flow

引用

2023 International Conference on robotics and Automation in Industry, ICRAI 2023

作者： Ashar, Rana Sadiq, Burhan Mohiuddin, Hira Ashraf, Saniya Imran, Muhammad Ullah, Anayat Control Automotive and Robotics Lab National Centre of Robotics and Automation Rawalpindi Pakistan Balochistan University of IT Engineering and Management Sciences Department of Electronic Engineering Quetta Pakistan

ISBN: (纸本)9781665464727

Video Stabilization is the basic need for modern-day video capture. Many methods have been proposed throughout the years including 2D and 3D-based models as well as models that use optimization and deep neural networks. This work describes the implementation of cutting-edge Recurrent All-Pairs Field Transforms (RAFT) for optical flow estimation in video stabilization. we use a pipeline that accommodates the large motion. It then passes the results to the optical flow for better accuracy. After that, it satisfies the inaccuracies of the optical flow and makes it robust to occlusion, Parallax, and moving objects. Our approach yields better results (visually and quantitatively) compared to other optimization and deep learning-based visual stabilization techniques. © 2023 IEEE.

关键词： Geometrical optics

来源：评论

学校读者我要写书评

暂无评论

Decentralized Task Assignment for Networked Unmanned Aerial Vehicles

Decentralized Task Assignment for Networked Unmanned Aerial ...

引用

2025 IEEE SoutheastCon, SoutheastCon 2025

作者： Szarafinski, Hava Kiriakidis, Kiriakos U.S. Naval Academy Department of Weapons Robotics and Control Engineering AnnapolisMD United States

ISBN: (纸本)9798331504847

Competing with the technical advancements of near-peer adversaries, the Navy is shifting towards increased use of Unmanned Aerial Vehicles (UAVs) to accomplish missions. Formations of networked UAVs are susceptible to single-point failure when assigned tasks centrally, leading to the need for decentralization. This paper investigates the optimal allocation of tasks among networked UAVs by means of distributed algorithms to avoid the single-point vulnerability. Furthermore, it addresses the issue of incomplete information about assignment costs, the result of limited direct connections within the formation. The research synthesizes the Hungarian and consensus classes of algorithms to achieve decentralized task allocation subjected to unknown assignment costs and communications being restricted to immediate neighbors. Within the scope of this paper, the number of tasks and agents are equal and agents know their own costs. Assignment costs of other agent-task pairs are not globally known. The success of the proposed approach is established by demonstrating that the synthesized algorithm reaches the same task assignment compared to centralized optimization using the global cost matrix. © 2025 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Odometry and Inertial Sensor-based Localization of a Snake Robot

Odometry and Inertial Sensor-based Localization of a Snake R...

引用

2023 International Conference on robotics and Automation in Industry, ICRAI 2023

作者： Shahid, Ramsha Baloch, Anam Tahir, Humayun Ullah, Anayat National Centre of Robotics and Automation Control Automotive and Robotics Lab Rawalpindi Pakistan Balochistan University of IT Engineering and Management Sciences Department of Electronic Engineering Quetta Pakistan

ISBN: (纸本)9781665464727

Terrain adaptability gives snake robots an edge over wheeled mobile robots. Snake robot's applications expansion to disaster management is due to its limbless and modular design. Replicating the navigation and locomotion of a biological snake have been in the spotlight for many researchers. In this study, a robust localization algorithm of a snake robot is developed. A sensor fusion-based algorithm using probabilistic approaches: UKF (Unscented Kalman Filter) and EKF (Extended Kalman Filter) has been proposed. Odometry is fused with one and two IMUs (Inertial Measurement Units) with both probabilistic approaches. Evaluation of results in a simulation environment showed that the fusion of two IMUs and odometry using EKF outer performs in terms of accuracy when odometry is fused with one IMU using EKF. Furthermore, the fusion of two IMUs and odometry with UKF is computationally expensive resulting in a large convergence time which is not the best suitable approach that can be utilized for the snake robot. © 2023 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning: An Approach on the Riemannian Manifold for Multiclass Motor Imagery EEG Brain-Computer Interface 30

Transfer Learning: An Approach on the Riemannian Manifold fo...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Sun, Xu Chu, Yaqi Luo, Yang Zhao, Xingang Northeastern University Department of Control Engineering Shenyang110819 China China Institutes for Robotics and Intelligent Manufacturing Shenyang110016 China

ISBN: (纸本)9798350391916

Motor imagery (MI) EEG-based brain-computer interface (BCI) facilitates direct communication between the brain's intentions and a computer. In essence, it allows a person to control external equipment by decoding EEG signals during the mental imagery of limb movements. However, due to the intricate individual variances in EEG signals, creating a general decoding model with parameters applicable to all subjects is exceptionally challenging. Consequently, a prolonged calibration process is necessary to gather labeled subject-specific data for each individual, making it less user-friendly. A potential solution to this problem is transfer learning, a methodology that transfers knowledge from related domains to a target domain. To tackle the problem, this paper proposes a novel transfer learning approach on the Riemannian manifold framework in the context of multiclass MI EEG-based BCI classification. Particularly, a user-specific frequency band selection (FBS) method with MI EEG class distinctiveness is utilized to improve the accuracy and efficiency of Riemannian space calculations, which is measured using the inter-class distance and intra-class variance on the manifold. Then, the Riemannian space Alignment (RA) strategy is used to calibrate the MI EEG variances of different subjects. The comparative experiments between the proposed approach and baseline/conventional methods are conducted on a public dataset with four-class motor imagery EEG, including two-class transfer learning scenario and four-class transfer learning scenario. proposed transfer learning approach is outperformed. Compared with the baseline/conventional methods using a fixed wide frequency band, the preliminary results suggests that the proposed approach can significantly improve the transfer learning performance for the MI EEG signals from different subjects in Riemannian space. © 2024 IEEE.

关键词： Brain computer interface

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：