检索结果-内蒙古大学图书馆

International Conference on Control, Automation and Systems ( ICCAS)

作者： Jaewon Park Changki Sung Seunghee Lee Dongwan Kang Hyun Myung School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon South Korea Hanwha Aerospace Seongnam-Si South Korea School of Electrical Engineering KI-Robotics Korea Advanced Institute of Science and Technology Daejeon South Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

Cross-view geo-localization (CVGL) is the problem of determining the location of a ground-level camera with respect to an extensive database of geo-tagged aerial images. While GNSS can provide location data, using images alone for localization can be especially beneficial in scenarios where GNSS signals are obstructed or unreliable. Although CVGL is treated as a retrieval-based visual place recognition (VPR) task, it is more challenging due to the critical view-point domain gap. To reduce this gap, contrastive learning methods have demonstrated superior performance, especially by applying hard negative sampling. However, the issue with previous hard negative sampling is its high computational cost, making training time-consuming when performed at every epoch. In this study, we propose a more effective hard negative sampling method. We introduce sampling strategies that remove unnecessary similarity map calculations, effectively computing only for the queries. We utilize the proposed effective hard negative sampling method, conducting contrastive learning with the information noise-contrastive estimation (InfoNCE) loss function. Our work demonstrated more efficient training and superior performance compared with the existing approaches on CVUSA and VIGOR, common cross-view datasets.

关键词： Training Global navigation satellite system Image retrieval Vegetation mapping Symbols Contrastive learning Feature extraction Sampling methods Vectors Satellite images

来源：评论

学校读者我要写书评

暂无评论

Predictive Simulation of Hemiparetic Gait Based on Neural Impairments

Predictive Simulation of Hemiparetic Gait Based on Neural Im...

引用

RSI/ISM International Conference on robotics and Mechatronics (ICROM)

作者： Hossein Barati Kamran Nazari Iman Kardan Alireza Akbarzadeh Department of Mechanical Engineering Center of Advanced Rehabilitation and Robotics Research (FUM-CARE) Ferdowsi University of Mashhad Mashhad Iran

Hemiparetic gait is the most common walking impairment after a stroke that causes abnormal movement patterns. However, the neuromuscular impairments that may lead to this type of gait are not fully understood. Predictive neuromechanical simulations allow for exploring how neural and biomechanical impairments affect gait performance based on dynamic optimization method. To simulate a hemiparetic gait, we used a predictive simulation software (SCONE) with a neuromuscular model of human, walking in the sagittal plane. The model is used to implement different neural impairments such as decreased unilateral muscle excitations and spastic hyperreflexia in quadriceps and ankle plantar flexors. Neural impairments were modeled in three cases of pure neural weakness, pure spastic hyperreflexia, and a combination of both, to investigate their contribution to hemiparetic gait. For validation, all simulation results were compared with experimental gait data of hemiparetic stroke patients. Our results exhibited better agreement with experimental data when a combination of neural impairments was used to simulate hemiparetic gait. In this case, the walking speed was slower than in other cases (0.47 m/s), and spatiotemporal parameters matched well with experimental data. The cross-correlation was highest in paretic knee angle $(\mathrm{R}=0.99)$ and strong in paretic and non-paretic hip angle $(\mathrm{R}\gt 0.92)$. In terms of joint kinetics, hip and ankle moments showed strong cross-correlation in the paretic side $(\mathrm{R}\gt 0.71)$ and moderate in knee moment $(\mathrm{R}=0.66)$. Future works could utilize our predictive simulations to design and develop assistive devices and control strategies of lower-limb exoskeletons to improve gait performance in post-stroke patients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review and application of Edge AI solutions for mobile collaborative robotic platforms 55

Review and application of Edge AI solutions for mobile colla...

引用

55th CIRP Conference on Manufacturing Systems, CIRP CMS 2022

作者： Ramasubramanian, Aswin K. Mathew, Robins Preet, Inder Papakostas, Nikolaos Laboratory for Advanced Manufacturing Simulation and Robotics School of Mechanical and Materials Engineering University College Dublin Ireland CeADAR-Ireland's Center for Applied AI University College Dublin Ireland

Edge AI technologies have emerged as a powerful solution for gathering and processing data in real-time, supporting the development of advanced applications for process monitoring, planning and control. Edge AI devices coupled with different sensory systems can be used for facilitating the synergetic human-robot collaboration at the shop floor level. This paper reviews edge AI devices and solutions that may potentially support the operation of cells or workstations comprising human operators and mobile robotic platforms. The use of edge AI-capable devices for operator tracking in real-world applications and the potential of edge AI technologies towards developing and deploying process digital twins are discussed. The main goal is to investigate how edge AI solutions may improve the performance of processes where a collaborative mobile manipulator works alongside a human operator in a safe and reliable manner. Lastly, the use of advanced communication frameworks, such as the Robot Operating System (ROS), is discussed in the context of supporting the seamless interaction between a collaborative mobile platform and Edge AI devices. © 2022 The Authors. Published by Elsevier B.V.

关键词： Collaborative Manipulators Control Robot Sensor

来源：评论

学校读者我要写书评

暂无评论

Eversion Robots for Mapping Radiation in Pipes

arXiv

引用

arXiv 2023年

作者： Mack, Thomas Al-Dubooni, Mohammed Althoefer, Kaspar The Centre for Advanced Robotics @ Queen Mary School of Engineering and Materials Science Queen Mary University of London United Kingdom

A system and testing rig were designed and built to simulate the use of an eversion robot equipped with a radiation sensor to characterise an irradiated pipe prior to decommissioning. The magnets were used as dummy radiation sources which were detected by a hall effect sensor mounted in the interior of the robot. The robot successfully navigated a simple structure with sharp 45° and 90° swept bends as well as constrictions that were used to model partial blockages. © 2023, CC BY.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration

arXiv

引用

arXiv 2024年

作者： Liu, Junjia Li, Zhuo Yu, Minghao Dong, Zhipeng 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 Genoa Italy

Humanoid robots are envisioned as embodied intelligent agents capable of performing a wide range of human-level loco-manipulation tasks, particularly in scenarios requiring strenuous and repetitive labor. However, learning these skills is challenging due to the high degrees of freedom of humanoid robots, and collecting sufficient training data for humanoid is a laborious process. Given the rapid introduction of new humanoid platforms, a cross-embodiment framework that allows generalizable skill transfer is becoming increasingly critical. To address this, we propose a transferable framework that reduces the data bottleneck by using a unified digital human model as a common prototype and bypassing the need for re-training on every new robot platform. The model learns behavior primitives from human demonstrations through adversarial imitation, and the complex robot structures are decomposed into functional components, each trained independently and dynamically coordinated. Task generalization is achieved through a human-object interaction graph, and skills are transferred to different robots via embodimentspecific kinematic motion retargeting and dynamic fine-tuning. Our framework is validated on five humanoid robots with diverse configurations, demonstrating stable loco-manipulation and highlighting its effectiveness in reducing data requirements and increasing the efficiency of skill transfer across platforms. Copyright © 2024, The Authors. All rights reserved.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

PEGG-Net: Pixel-Wise Efficient Grasp Generation in Complex Scenes

PEGG-Net: Pixel-Wise Efficient Grasp Generation in Complex S...

引用

IEEE Conference on Cybernetics and Intelligent Systems

作者： Haozhe Wang Zhiyang Liu Lei Zhou Huan Yin Marcelo H. Ang Advanced Robotics Centre National University of Singapore Singapore Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China

ISBN: (数字)9798350364194

ISBN: (纸本)9798350364200

Vision-based grasp estimation is an essential part of robotic manipulation tasks in the real world. Existing planar grasp estimation algorithms have been demonstrated to work well in relatively simple scenes. However, when it comes to complex scenes, such as cluttered scenes with messy backgrounds and moving objects, the algorithms from previous works are prone to generate inaccurate and unstable grasping contact points. In this work, we first study the existing planar grasp estimation algorithms and analyze the related challenges in complex scenes. Secondly, we design a Pixel-wise Efficient Grasp Generation Network (PEGG-Net) to tackle the problem of grasping in complex scenes. PEGG-Net can achieve improved state-of-the-art performance on the Cornell dataset (98.9%) and second-best performance on the Jacquard dataset (93.8%), outperforming other existing algorithms without the introduction of complex structures. Thirdly, PEGG-Net could operate in a closed-loop manner to add robustness in dynamic environments using position-based visual servoing (PBVS). Finally, we conduct real-world experiments on static, dynamic, and cluttered objects in different complex scenes. The results show that our proposed network achieves a high success rate in grasping irregular objects, household objects, and workshop tools. To benefit the community, our trained model and supplementary materials are available at https://***/HZWang96/PEGG-Net.

关键词： Mechatronics Heuristic algorithms Estimation Random access memory Grasping Robustness Visual servoing

来源：评论

学校读者我要写书评

暂无评论

Elbow Soft Robot Rehabilitation System for Hemiplegic Stroke Patients Based on sEMG Control

Elbow Soft Robot Rehabilitation System for Hemiplegic Stroke...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Qifeng Xun Benjamin W.K. Ang Chen-Hua Yeow Department of Biomedical Engineering and Advanced Robotics Centre National University of Singapore Singapore Singapore Department of Biomedical Engineering National University of Singapore Singapore

Stroke can result in limb disorders, and many stroke victims will experience unilateral limb problems. Therefore, post-disease rehabilitation, particularly for the upper limbs, is crucial. In general, professionals or family members must accompany patients during rehabilitation. However, it is inconvenient and could impede the development of the recovery process. Therefore, a rehabilitation tool that is self-controllable by the patient, basic in design, and simple to use is beneficial to the patient's recovery. In this study, to help stroke patients with unilateral limb abnormalities regain self-control, a set of elbow rehabilitation equipment was created. It is simple to use, safe, and reliable. The patient can control the soft robot to mend the elbow using the surface Electromyography (sEMG) signal from the healthy arm. Five classification models' classification results were compared, and Support Vector Machine (SVM) accuracy was found to be 97% accurate. The SVM model is chosen for real-time control, considering classification accuracy, stability, and operation time. The elbow flexion and extension real-time control experiments are conducted. The system execution time can be as long as 2.275 seconds and 2.188 seconds when elbow flexion and extension are performed, respectively. For the rehabilitation of stroke patients, this study provides a wide range of possible applications.

关键词： Support vector machines Stroke (medical condition) Soft robotics Real-time systems Magnetic heads Electromyography Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Design of a Variable Stiffness Spring with Human-Selectable Stiffness

Design of a Variable Stiffness Spring with Human-Selectable ...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Chase W. Mathews David J. Braun Department of Mechanical Engineering Advanced Robotics and Control Laboratory within the Center for Rehabilitation Engineering and Assistive Technology Vanderbilt University Nashville Tennessee USA

Springs are commonly used in wearable robotic devices to provide assistive joint torque without the need for motors and batteries. However, different tasks (such as walking or running) and different users (such as athletes with strong legs or the elderly with weak legs) necessitate different assistive joint torques, and therefore, springs with different stiffness. Variable stiffness springs are a special class of springs which can exert more or less torque upon the same deflection, provided that the user is able to change the stiffness of the spring. In this paper, we present a novel variable stiffness spring design in which the user can select a preferred spring stiffness similar to switching gears on a bicycle. Using a leg-swing experiment, we demonstrate that the user can increment and decrement spring stiffness in a large range to effectively assist the hip joint during leg oscillations. Variable stiffness springs with human-selectable stiffness could be key components of wearable devices which augment locomotion tasks, such as walking, running, and swimming.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dual Multilayer Extension Actuator for High Extension and High Compression Force Applications

Dual Multilayer Extension Actuator for High Extension and Hi...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Jonathan William Ambrose Dylan Sin You Cheah Raye Chen-Hua Yeow Department of Biomedical Engineering Advanced Robotics Center at the National University of Singapore (NUS) Singapore Department of Biomedical Engineering Nanyang Polytechnic (NYP) Singapore

Soft robotic actuators possess several unique characteristics, such as being generally compliant and lightweight, making them suitable for safe human interaction to be deployed in various industries. However, they are often designed for an intended purpose, making them impractical for a different task. This paper aims to introduce a new way of utilising a new class of soft silicone actuators capable of incorporating them into applications that require both pushing and pulling. The dual multilayer extension actuator (DMEA) is compact and lightweight at 8 g, capable of an extension ratio of 300% and a high pulling force-to-weight ratio of 200 with the assistance of vacuum pressure at 30% extension ratio. The fabrication of the DMEA is described in detail and followed by characterisation tests of the DMEA compared to the FEA model. Finally, we showcase the DMEA pulling a 3D-printed arm as a potential assistive device and demonstrate the DMEA versatility by deploying the DMEA onto everyday household products like scissors and kitchen tongs.

关键词： Industries Fabrication Actuators Force Dynamics Soft robotics Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

Gene Regulatory Network Model for Adaptive Flocking Patterns of Multi-Agent Systems

Gene Regulatory Network Model for Adaptive Flocking Patterns...

引用

IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems

作者： Wenji Li Chuangbin Chen Zhaojun Wang Chaotao Guan Boxi Wang Dongliang Wang Jiafan Zhuang Zhun Fan International Cooperation Base of Evolution Intelligence and Robotics of Guangdong Province College of Engineering Shantou University Shantou China UESTC Shenzhen Institute for Advanced Study

ISBN: (数字)9798331506056

ISBN: (纸本)9798331506063

In unknown environments, it's crucial for a multi-agent system to perceive changes in the surroundings and automatically adjust its flocking shapes. To address this need, our study proposes a formation control strategy based on Gene Regulatory Networks (named FC-GRN). The FC-GRN abstracts key elements in generating formation patterns, such as targets, obstacles, agents, and their neighbors, as different types of “cells” and efficiently generates and adjusts flocking shapes by simulating dynamic interactions among them. The FC-GRN ensures all agents sensitively perceive environmental changes and adjust their positions in the formation accordingly, thus achieving adaptive flocking shapes. This enables the system to effectively prevent individual dispersion or detachment, enhancing overall cohesion. Simulation results clearly demonstrate that the the FC-GRN strategy allows agents to flexibly rearrange their positions based on environmental changes, effectively maintaining formation compactness and coherence.

关键词： Adaptation models Shape Simulation Coherence Control systems Formation control Real-time systems Intelligent systems Dispersion Multi-agent systems

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：