检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Real-Time Computing and robotics, RCAR 2022

作者： Zhu, Honghui Jin, Kaixiang Yang, Yang Wei, Zhong Liu, Jia Kang, Long Li, Yunquan Nanjing University of Information Science and Technology School of Automation Nanjing210044 China Jiangsu Province Engineering Research Center of Intelligent Meteorological Exploration Robot China Nanjing University of Science and Technology PCA Lab Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Info. of Min. of Education Jiangsu Key Lab of Image and Video Understanding for Social Secty Sch. of Comp. Sci. and Eng Nanjing210094 China South China University of Technology Panyu District Shien-Ming Wu School of Intelligent Engineering Guangzhou China

ISBN: (数字)9781665469838

ISBN: (纸本)9781665469838

This paper describes a novel design of a soft actuator that combines two types of actuation methods: DC motor actuation and supercoiled polymer (SCP) artificial muscle. SCP artificial muscle is used to substitute the traditional cable and attached to the gearmotor. The hybrid actuator intends to alleviate the drawbacks of both actuation methods. This novel actuator features a fast actuation speed and the addition of SCP artificial muscles endow it with a certain degree of compliance. At the same time, the thermal contraction property of SCP artificial muscle can also increase its output force. A soft robotic finger is designed to conFigure the actuator in it. In the experiment section, finger's stiffness and output force tests are performed under three different actuation methods (single SCP/gearmotor kite line/gearmotor SCP). Experiment results demonstrate the superiority of this novel actuator in terms of compliance (compared with gearmotor kite line actuation), actuation speed, and output force (compared with single SCP actuation). This actuator has the potential to be used for grasping and manipulation of soft robots in the future. © 2022 IEEE.

关键词： Actuators

来源：评论

学校读者我要写书评

暂无评论

The Stiffness of 3-PRS PM Across Parasitic and Orientational Workspace

arXiv

引用

arXiv 2024年

作者： Nigatu, Hassen Jihao, Li Zhu, Keqi Zhang, Junhan Guo, Haotian Lu, Guodong Kim, Doik Robot Perception and Grasp Lab School of Mechanical Engineering Zhejiang University Hangzhou310027 China Robotics Research Center of Yuyao Robotics Institute Zhejiang University Yuyao Technology Innovation Center No.479 Ye Shan Road Yuyao Zhejiang Province Ningbo China The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering The Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province Zhejiang University Hangzhou310027 China Korea Republic of

This study investigates the stiffness characteristics of the Sprint Z3 head, also known as 3-PRS Parallel Kinematics Machines, which are among the most extensively researched and viably successful manipulators for precision machining applications. Despite the wealth of research on these robotic manipulators, no previous work has demonstrated their stiffness performance within the parasitic motion space. Such an undesired motion influences their stiffness properties, as stiffness is configuration-dependent. Addressing this gap, this paper develops a stiffness model that accounts for both the velocity-level parasitic motion space and the regular workspace. Numerical simulations are provided to illustrate the stiffness characteristics of the manipulator across all considered spaces. The results indicate that the stiffness profile within the parasitic motion space is both shallower and the values are smaller when compared to the stiffness distribution across the orientation workspace. This implies that evaluating a manipulator’s performance adequately requires assessing its ability to resist external loads during parasitic motion. Therefore, comprehending this aspect is crucial for redesigning components to enhance overall stiffness. © 2024, CC BY.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Detection-and-Excitation Neural Network Achieves Accurate Nasopharyngeal Carcinoma Segmentation in Multi-modality MR Images

Detection-and-Excitation Neural Network Achieves Accurate Na...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Tao, Guihua Li, Haojiang Liu, Lizhi Cai, Hongmin South China University of Technology School of Computer Science and Engineering Guangzhou China Sun Yat-sen University Cancer Center Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy Collaborative Innovation Center for Cancer Medicine Guangzhou China Brain and Affective Cognitive Research Center Pazhou Lab Guangzhou China

ISBN: (纸本)9781665401265

Accurate and reliable segmentation of nasopharyngeal carcinoma (NPC) in magnetic resonance image (MRI) is important for treatment planning and follow-up evaluation. However, it is still challenging because NPC is infiltrative with a vague border and has a tiny volume with varying sizes and shapes. The above problems easily cause the NPC tumors' features to submerge in the process of feature extraction. Standard segmentation methods do not cope with the 'feature submergence' and performed unsatisfactorily in NPC segmentation. To address the problem, a dual-supervised method equipped with the detection-and-excitation module (DEM) was proposed. DEM strengthens the region of interest (ROI) and weakens complex and immense background through incorporating detection feature maps (outline maps) with intermediated segmentation features. To be specific, the DEM explored the outline of the ROI and output a detection feature map by using a supervised layer guided by a tailored loss function. Then, the DEM uses the results to recalibrates the intermediated segmentation. Finally, a neural network equipped with the proposed DEM was elaborately designed to achieve accurate segmentation. We applied the proposed network termed as DENet on a real nasopharyngeal carcinoma dataset to realize automatic NPC tumors segmentation in multi-modality MR images. The proposed DEM enables the neural network to segment NPC tumors within the immense and complex background. Experimental results have demonstrated the effectiveness of the proposed method by comparing it with benchmark models. © 2021 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Kinematic-Model-Free Tip Position Control of Reconfigurable and Growing Soft Continuum robots

Kinematic-Model-Free Tip Position Control of Reconfigurable ...

引用

IEEE International Conference on Soft robotics (RoboSoft)

作者： Ahmad AlAttar Ikhlas Ben Hmida Federico Renda Petar Kormushev Robot Intelligence Lab Dyson School of Design Engineering Imperial College London UK Robotics Lab Dubai Future Labs Dubai UAE Department of Mechanical Engineering Khalifa University of Science and Technology Abu Dhabi UAE Khalifa University Center for Autonomous Robotic Systems (KUCARS) Khalifa University Abu Dhabi UAE

Soft robots have many advantages over their rigid counterparts. These include their inherent compliance, lightweight and high adaptability to cluttered workspaces. Soft continuum robots, biologically inspired snake-like robots, are hyper-redundant and highly deformable. These robots can be challenging to control due to their complex kinematic and dynamic models. This paper presents a novel kinematic-model-free controller that uses a quasi-static assumption in order to control the tip-position of soft continuum robots with threadlike actuation while compensating for gravity simultaneously. The controller was tested on simulated continuum soft robots to demonstrate its ability to guide the tip while following a given trajectory. Novel kinematic-model-free control methods are introduced for soft robots' route and length control. The robustness of the controller is demonstrated with an actuator-failure test. The kinematic-model-free controller provides an adaptive control method for static, re-configuring, and growing soft continuum robots with threadlike actuation.

关键词： Actuators Adaptation models Three-dimensional displays Biological system modeling Position control Kinematics Soft robotics

来源：评论

学校读者我要写书评

暂无评论

Online Hand-Eye Calibration with Decoupling by 3D Textureless Object Tracking

Online Hand-Eye Calibration with Decoupling by 3D Textureles...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Li Jin Kang Xie Wenxuan Chen Xin Cao Yuehua Li Jiachen Li Jiankai Qian Xueying Qin School of Software Shandong University P.R. China Engineering Research Center of Digital Media Technology Ministry of Education P.R. China Zhejiang Lab Intelligent Robot Research Center P.R. China State Key Lab of CAD&CG Zheiiang-University P.R. China

Hand-eye calibration estimates the pose of a camera relative to a robot, which is a fundamental problem for visually guided robots, especially for dynamic object grasping. Most methods use 2D fiducial markers with distinctive visual features and require pre-calibration for accurate calibration, which can not work online. In this paper, we propose a novel hand-eye calibration method based on the natural 3D object, which can work online and automatically even if the object is textureless or weakly textured. We first propose a Pose Refinement Network (PR-Net) to improve the accuracy of 3D object tracking. Then we build a 3D convergence point constraint based on the multi-view information with the accurate object pose to adjust the object position. Finally, we optimize the hand-eye pose by the closed-loop constraint with the optimized object position, solving the problem that is easy to fall into a local minimum. The experiments show that the average error of our hand-eye calibration method is 1.20 degrees and 23.18 mm. The results achieve state-of-the-art by using the working object to realize the online hand-eye calibration.

关键词：

来源：评论

学校读者我要写书评

暂无评论

When Shannon Meets Nonstochastic Information: Communication and Estimation

引用

IEEE Transactions on Automatic Control 2025年

作者： Zhang, Wentao Zuo, Zhiqiang Zhao, Rui Wang, Yijing Hu, Guoqiang Zhang, Hui Wang, Yaonan Hunan University School of Robotics Changsha410082 China Nanyang Technological University Continental-NTU Corporate Lab Singapore639798 Singapore Tianjin University Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin300072 China Nanyang Technological University School of Electrical and Electronic Engineering Singapore639798 Singapore National Engineering Research Center for Robot Visual Perception and Control Changsha410082 China Hunan University College of Electrical and Information Engineering Changsha410082 China

This notes focuses on the issue of whether or not the state of a plant can be estimated when the inputs of communication channel involve noise and disturbance simultaneously. It turns out to calculate the maximum capacity of stationary memoryless multiple quasi-access channel under nonstochastic information theory. It is shown that the maximum information rate over such a channel is determined by a convex hull spanned by the zero-error capacities which are specified on the underlying sample spaces. Moreover, the state of a plant could be estimated provided that the maximal information rate is strictly greater than the topology entropy. © 1963-2012 IEEE.

关键词： Communication channels (information theory)

来源：评论

学校读者我要写书评

暂无评论

A Novel Pose Estimation Method of Object in robotic Manipulation Using Vision-Based Tactile Sensor 5th

A Novel Pose Estimation Method of Object in Robotic Manipula...

引用

5th International Conference on cognitive Systems and Signal Processing, ICCSIP 2020

作者： Zhao, Dan Sun, Fuchun Zhou, Quan Wang, Zongtao Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing100083 China AnHui Province Key Laboratory of Special Heavy Load Robot Anhui University of Technology Ma Anshan China Key Lab of Industrial Computer Control Engineering of Hebei Province Yanshan University Qinhuangdao066000 China

ISBN: (纸本)9789811623356

The computer vision techniques have been widely used in the robotic manipulation for perception and positioning. However, duo to the inaccuracy of camera calibration and measurement, there is a greatly need for more accurate method to estimate the object pose especially for robotic precise manipulation. In this paper, we propose a novel pose estimation method of object in robotic manipulation using a vision-based tactile sensor. The structure of the tactile sensor and the proposed model are introduced in detail, and verification experiments have been performed. The results show the advantages and better performance of the proposed method. © 2021, Springer Nature Singapore Pte Ltd.

关键词： robot vision

来源：评论

学校读者我要写书评

暂无评论

XRJL-HKUST at SemEval-2021 Task 4: WordNet-Enhanced Dual Multi-head Co-attention for reading comprehension of abstract meaning

arXiv

引用

arXiv 2021年

作者： Jiang, Yuxin Shou, Ziyi Wang, Qijun Wu, Hao Lin, Fangzhen HKUST-Xiaoi Robot Joint Lab on Machine Learning and Cognitive Reasoning Department of Computer Science and Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong

This paper presents our submitted system to SemEval 2021 Task 4: Reading Comprehension of Abstract Meaning. Our system uses a large pre-trained language model as the encoder and an additional dual multi-head coattention layer to strengthen the relationship between passages and question-answer pairs, following the current state-of-the-art model DUMA. The main difference is that we stack the passage-question and question-passage attention modules instead of calculating parallelly to simulate re-considering process. We also add a layer normalization module to improve the performance of our model. Furthermore, to incorporate our known knowledge about abstract concepts, we retrieve the definitions of candidate answers from Word-Net and feed them to the model as extra inputs. Our system, called WordNet-enhanced DUalMulti-head Co-Attention (WN-DUMA), achieves 86.67% and 89.99% accuracy on the official blind test set of subtask 1 and subtask 2 respectively. © 2021, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Epileptic Spikes and Seizures Incorporating a Novel Spatial Clustering Prior

Automated Detection of Epileptic Spikes and Seizures Incorpo...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Dong, Hanyang Sheng, Shurong Wang, Xiongfei Gao, Jia-Hong Sun, Yi Yang, Wanli Xiao, Kuntao Teng, Pengfei Luan, Guoming Lv, Zhao Anhui University School of Artificial Intelligence Hefei230601 China Hefei Comprehensive National Science Center Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing Institute of Artificial Intelligence Hefei230088 China Sanbo Brain Hospital Capital Medical University Beijing Key Laboratory of Epilepsy Department of Neurosurgery Beijing China Peking University McGovern Institute for Brain Research Beijing China Peking University Center for Mri Research Academy for Advanced Interdisciplinary Studies Beijing China Peking University Beijing City Key Lab for Medical Physics and Engineering Institute of Heavy Ion Physics School of Physics Beijing China Anhui University Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Hefei230601 China

ISBN: (纸本)9798350386226

A Magnetoencephalography (MEG) time-series recording consists of multi-channel signals collected by superconducting sensors, with each signal's intensity reflecting magnetic field changes over time at the sensor location. Automating epileptic MEG spike detection significantly reduces manual assessment time and effort, yielding substantial clinical benefits. Existing research addresses MEG spike detection by encoding neural network inputs with signals from all channel within a time segment, followed by classification. However, these methods overlook simultaneous spiking occurred from nearby sensors. We introduce a simple yet effective paradigm that first clusters MEG channels based on their sensor's spatial position. Next, a novel convolutional input module is designed to integrate the spatial clustering and temporal changes of the signals. This module is fed into a custom MEEG-ResNet3D developed by the authors, which learns to extract relevant features and classify the input as a spike clip or not. Our method achieves an F1 score of 94.73% on a large real-world MEG dataset Sanbo-CMR collected from two centers, outperforming state-of-the-art approaches by 1.85%. Moreover, it demonstrates efficacy and stability in the Electroencephalographic (EEG) seizure detection task, yielding an improved weighted F1 score of 1.4% compared to current state-of-the-art techniques evaluated on TUSZ, whch is the largest EEG seizure dataset. © 2024 IEEE.

关键词： Magnetoencephalography

来源：评论

学校读者我要写书评

暂无评论

Large Language Models for Generative Information Extraction: A Survey

arXiv

引用

arXiv 2023年

作者： Xu, Derong Chen, Wei Peng, Wenjun Zhang, Chao Xu, Tong Zhao, Xiangyu Wu, Xian Zheng, Yefeng Wang, Yang Chen, Enhong State Key Laboratory of Cognitive Intelligence University of Science and Technology of China Hefei230000 China Department of Data Science City University of Hong Kong Hongkong999077 Hong Kong Jarvis Research Center Tencent YouTu Lab Beijing100029 China Anhui Conch Information Technology Engineering Co. Ltd. Wuhu241000 China

Information extraction (IE) aims to extract structural knowledge from plain natural language texts. Recently, generative Large Language Models (LLMs) have demonstrated remarkable capabilities in text understanding and generation. As a result, numerous works have been proposed to integrate LLMs for IE tasks based on a generative paradigm. To conduct a comprehensive systematic review and exploration of LLM efforts for IE tasks, in this study, we survey the most recent advancements in this field. We first present an extensive overview by categorizing these works in terms of various IE subtasks and techniques, and then we empirically analyze the most advanced methods and discover the emerging trend of IE tasks with LLMs. Based on a thorough review conducted, we identify several insights in technique and promising research directions that deserve further exploration in future studies. We maintain a public repository and consistently update related works and resources on GitHub (LLM4IE repository). Copyright © 2023, The Authors. All rights reserved.

关键词： Information retrieval

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

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

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：