检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Peng, Yiheng Luo, Jingjing Wang, Hongbo Chen, Li Guo, Shijie Guo, Yuzhu Li, Yang The Institute of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai200433 China Engineering Research Center of AI and Robotics Ministry of Education Shanghai200043 China Department of Automation Sciences and Electrical Engineering Beihang University Beijing100191 China School of Automation Science and Electrical Engineering China

Transfer learning offers a promising solution to the annotation and calibration challenges associated with motor imagery (MI) electroencephalogram (EEG) decoding during neural-feedback rehabilitation. In this study, we address the challenge of online unsupervised cross-subject adaptation in MI-EEG classification, where target samples arrive sequentially, and we should adapt the model online with limited target data. We focus on the testing stage and propose a MI Fully Test-Time Adaptation (MI-FTTA) method that essentially enables online training using limited and unlabeled target data. MI-FTTA effectively alleviates the influence of noisy pseudo labels with teacher-student mutual learning and time-constrained sample selection. Through recalculating normalization statistics with limited accessible source and target information and prototype-based cross-domain contrastive learning, MI-FTTA adaptively enhances the representational capability of models. It thoroughly harnesses the limited online target samples to enhance adaptation performance. Experimental evaluations are conducted using three classification datasets , including two-class (BCI-IV2b), three-class (High-Gamma), and four-class (BCI-IV2a) scenarios. MI-FTTA demonstrates its superiority by surpassing direct source model deployment with an average performance gain of 4.11\% across different scenarios. Notably, our proposed approach also achieves a significant improvement over 12 different online test-time adaptation algorithms at three different backbones, thus affirming its *** work represents early endeavor in source-free fully test-time adaptation for cross-subject MI-EEG decoding. © 2024, The Authors. All rights reserved.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Exciting Trajectories for Identifying Dynamic Parameters of Serial Robots

Optimal Exciting Trajectories for Identifying Dynamic Parame...

引用

IEEE International Conference on Mechatronics and automation

作者： Ruiqing Luo Sheng Bao Liang Du Zhengtao Hu Yukun Liu Jianjun Yuan Shanghai Robotics Institute School of Mechatronic Engineering and Automation Shanghai University Shanghai China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai China Graduate School of Engineering Science osaka university Toyonaka Osaka Japan

Accurate parameter identification of serial robots is of paramount importance to achieve satisfactory performance in performing highly dynamic tasks or obtaining realistic simulations. Focusing on the issue of optimizing excitation trajectory in the parameter identification process, a novel optimization algorithm is proposed by taking into account the interplay among different optimization criteria, in which the initial optimization index is introduced. To this end, the Lie-theory-based dynamic identification approach is introduced to illustrate the impact of trajectory optimization for the identification result, and we conduct a one-way analysis of torque prediction variance to determine whether significant improvements have been made or not. Finally, an experimental comparison between several optimization criteria is implemented for a 7 degrees-of-freedom (DoFs) Franka collaborative robot, the findings show that the proposed approach is capable of minimizing the overall trajectory optimization time while ensuring the identification robustness as compared to several other optimization criteria, which can offer a significant advantage in achieving fast and robust identification.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Electrospinning drug-loaded polycaprolactone/polycaprolactone-gelatin multi-functional bilayer nanofibers composite scaffold for postoperative wound healing of cutaneous squamous cell carcinoma

Biomedical Technology

引用

Biomedical Technology 2024年 8卷 65-80页

作者： Song, Yongteng Hu, Qingxi Liu, Suihong Yao, Guotai Zhang, Haiguang Rapid Manufacturing Engineering Center School of Mechatronic Engineering and Automation Shanghai University Shanghai 200444 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai 200072 China National Demonstration Center for Experimental Engineering Training Education Shanghai University Shanghai 200444 China Department of Dermatology Shanghai Fourth People's Hospital School of Medicine Tongji University Shanghai 200434 China Engineering Science and Mechanics Department Penn State University University Park 16802 PA United States

Cutaneous squamous cell carcinoma (cSCC) tumor resection surgery poses challenges due to incomplete cancer cell removal, which increases the risk of local recurrence and micrometastasis, while large-scale surgical wounds are susceptible to severe infections. Therefore, a drug-loaded multi-functional bilayer nanofibers skin scaffold was fabricated for postoperative wound care of cSCC. Briefly, the antibacterial drug enrofloxacin (ENR) was loaded into polycaprolactone (PCL) nanofibers using electrospinning to form an antibacterial nanofiber membrane (PCL-ENR) as the outer layer of scaffold. The anticancer drug bleomycin (BLM) was loaded into PCL/Gelatin (Gel) nanofibers via electrospinning to form an anticancer nanofiber membrane (PG-BLM) as the inner layer of scaffold. ENR and BLM were successfully loaded into the scaffold. The scaffold had excellent physicochemical properties, with the outer layer exhibiting hydrophobicity and excellent antibacterial activity, and the inner layer showing hydrophilicity and outstanding anticancer activity. The elongation at break and tensile modulus of the scaffold were 26.35 ± 1.61 % and 15.25 ± 1.56 MPa, respectively. In vitro and in vivo experiments suggested that the scaffold not only has good biocompatibility to promote wound healing but also could inhibit the proliferation of A431 cells, which has great potential clinical application in postoperative wound care of cSCC. © 2024 The Authors

关键词： Antibacterial and anticancer Bilayer nanofibers skin scaffold Cutaneous squamous cell carcinoma Drug-loaded Electrospinning Postoperative wound care

来源：评论

学校读者我要写书评

暂无评论

Resilient source seeking with robot swarms

Resilient source seeking with robot swarms

引用

IEEE Conference on Decision and Control

作者： Antonio Acuaviva Jesus Bautista Weijia Yao Juan Jimenez Hector Garcia de Marina Department of Computer Architecture and Automation Universidad Complutense de Madrid Spain Department of Computer Engineering Automation and Robotics Research Centre for Information and Communication Technologies (CITIC-UGR) University of Granada Granada Spain School of Robotics Hunan University

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

We present a solution for locating the source, or maximum, of an unknown scalar field using a swarm of mobile robots. Unlike relying on the traditional gradient information, the swarm determines an ascending direction to approach the source with arbitrary precision. The ascending direction is calculated from field strength measurements at the robot locations and their relative positions concerning the swarm centroid. Rather than focusing on individual robots, we focus the analysis on the density of robots per unit area to guarantee a more resilient swarm, i.e., the functionality remains even if individuals go missing or are misplaced during the mission. We reinforce the algorithm’s robustness by providing sufficient conditions for the swarm shape so that the ascending direction is almost parallel to the gradient. The swarm can respond to an unexpected environment by morphing its shape and exploiting the existence of multiple ascending directions. Finally, we validate our approach numerically with hundreds of robots. The fact that a large number of robots with a generic formation always calculate an ascending direction compensates for the potential loss of individuals.

关键词： Sufficient conditions Shape Focusing Position measurement Robustness Mobile robots Robots

来源：评论

学校读者我要写书评

暂无评论

Semi-Closed-Loop Constant Force Control of a Multi-Modes Rigid-Flexible Underactuated Gripper 23rd

Semi-Closed-Loop Constant Force Control of a Multi-Modes Rig...

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and engineering, IFToMM CCMMS 2022

作者： Chen, Weilin Feng, Zihong Lu, Qinghua Wei, Huiling Qin, Xiaolu Mo, Jiacheng Tang, Yu Wei, Sheng School of Mechatronics Engineering and Automation Foshan University 33 Guangyun Road Guangdong Foshan528000 China Academy of Interdisciplinary Studies Guangdong Polytechnic Normal University Guangzhou510665 China Engineering Research Center for Intelligent Robotics Jihua Laboratory Foshan528200 China

ISBN: (纸本)9789811993978

Grasping force control is important to realize safe and reliable robotic manipulation. In this paper, a semi-closed-loop constant grasping force control strategy of the multi-modes rigid-flexible underactuated gripper is designed to eliminate the influence of full-closed-loop control system on the grasping dexterity. For the two-point grasping mode and enveloped grasping mode, the inverse static model of gripper were established based on the forward static models proposed in our previous research and the numerical fitting. A semi-closed-loop PID constant grasping force control strategy was designed using the established statics models. Matlab Simulink was utilized to verify the proposed control strategy. Further, the multi-modes grasping force control system was built, and the effect of deformation for the flexible linkages on the equivalent size of grasped object was considered to correct the proposed control strategy by the analysis of balance position and numerical fitting. Finally, the rapidity, accuracy and stability of corrected control strategy were verified by experiments. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Force control

来源：评论

学校读者我要写书评

暂无评论

Design and Control of Continuous Jumping Gaits for Humanoid Robots Based on Motion Function and Reinforcement Learning

引用

Procedia Computer Science 2024年 250卷 51-57页

作者： Zida Zhao Shilong Sun Haodong Huang Qingbin Gao Wenfu Xu State Key Laboratory of Robotics and System (HIT) Harbin Institute of Technology Harbin Heilongjiang China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen 518055 China

Continuous jumping of humanoid robots is a challenging problem that requires appropriate gait and force control for the robot to achieve. Reinforcement learning (RL) has been applied to the motion control of humanoid robots and has achieved significant progress. However, traditional RL control methods primarily rely on designing reward signals to generate human-like movements, and it requires developing complex reward signals for continuous jumping, resulting in limited actions and suboptimal jumping performance. To address this issue, we have designed motion functions for humanoid continuous jumping and incorporated them into the RL framework to obtain desired human-like continuous jumping actions. Furthermore, two different jumping gaits are designed to investigate the jumping effects produced by different jumping functions: bent-knee jumping (BJ) and straight-knee jumping (SJ). BJ is a typical jumping style where the legs flex during the jumping process to accumulate energy, enabling higher explosive power. SJ is more suitable for tasks requiring quick responses, as the legs remain upright during the jump, providing faster reaction speed. The performance in continuous jumping tasks has been evaluated by comparing the effects of training with different jumping functions. This research has particular guidance for improving the jumping ability of robots and enhancing the stability and efficiency of humanoid continuous jumping.

关键词： Continuous jumping gaits Humanoid robots Motion function Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Simulation Research on Residual Stress of Swage Autofrettage-processed High-Pressure Cylinder 9

Simulation Research on Residual Stress of Swage Autofrettage...

引用

2023 9th International Conference on Applied Materials and Manufacturing Technology, ICAMMT 2023

作者： Sun, Lihua Zhou, Rongxuan Li, Guiqin Li, Jianing Mitrouchev, Peter Engineering Training Center Changchun University of Technology Changchun China School of Mechanical Engineering and Automation Northeastern University Shenyang China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai University Shanghai China University Grenoble Alpes G-SCOP Grenoble France

The vital component of the high-pressure pump is the high-pressure cylinder, which undergoes pulsating cyclic loads during operation. This exposure can lead to fatigue cracking and limit the pump's overall performance. To address this issue, a swage autofrettage treatment method for the high-pressure cylinder is proposed based on the principles of autofrettage technology. The structure parameters of the mandrel are designed to optimize its role in the treatment process. Subsequently, a swage autofrettage simulation model is established, considering the Bauschinger effect to analyze the distribution of residual stress about the mandrel interference percentage. The results demonstrate that the swage autofrettage treatment improves the stress distribution in the high-pressure cylinder, causing the inner wall surface to undergo a circumferential residual compressive stress. Within a specific range, the Bauschinger effect becomes more significant as the mandrel interference percentage increases. This study provides insights for enhancing the durability and performance of high-pressure cylinders while adhering to mechanical engineering standards. © Published under licence by IOP Publishing Ltd.

关键词： Residual stresses

来源：评论

学校读者我要写书评

暂无评论

A Sparrow Search Algorithm Based on Dynamic Selection of Evolutionary Directions

A Sparrow Search Algorithm Based on Dynamic Selection of Evo...

引用

2023 China automation Congress, CAC 2023

作者： Zeng, Zhou Jiang, Tianyu Zhang, Shulan Tan, Ping Wang, Yi Ding, Jin Shuohuang Railway Development Limited Liability Company Su Ning China School of Automation and Electrical Engineering Zhejiang University of Science and Technology Hang Zhou China Zhejiang Guozi Robotics Co. Ltd Hang Zhou China

ISBN: (纸本)9798350303759

The sparrow search algorithm (SSA) is a swarm intelligence algorithm with strong search ability and fast convergence, but it may converge early and fall into local extremes in evolution. To address these problems, an improved multi-strategy sparrow search algorithm based on multi-strategy (MSSSA) is proposed. Firstly, we propose the idea of evolutionary direction division based on the change of individual position for the safety state of the producers. Secondly, the improved upper confidence bound (UCB) and epsilon-greedy methods are fused to achieve better evolutionary direction selection for discoverers in different confidence interval ranges. Finally, the mechanism of normal distribution is analysed to construct a standard deviation function about the evolutionary algebra to realize the adaptive position update of the discoverer, and then improve the iteration capability. The results of benchmark experiments show that MSSSA has better mean, standard deviation and optimal solutions compared with other commonly used SSA algorithms. The improved SSA algorithm has better solution quality. © 2023 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face Anti-Spoofing 18

CPL-CLIP: Compound Prompt Learning for Flexible-Modal Face A...

引用

18th IEEE International Joint Conference on Biometrics, IJCB 2024

作者： Zhang, Ying Zhu, Xiangyu Liu, Ajian Lin, Xun Wan, Jun Zhang, Jing Lei, Zhen Beihang University School of Computer Science and Engineering China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation China University of Chinese Academy of Sciences School of Artificial Intelligence China Macau University of Science and Technology School of Computer Science and Engineering China Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation China

ISBN: (纸本)9798350364132

Face anti-spoofing (FAS) is pivotal in safeguarding the integrity of face recognition systems. Flexible-modal FAS utilizes multi-modal data and trains a unified model adaptable to any single-modal testing scenario. This innovation addresses the shortcomings of conventional multi-modal FAS approaches, which typically demand separate model training and deployment for each modality. However, existing flexible-modal FAS approaches activate specific network branches based on the modality of the tested sample. This not only increases the model's parameters but also necessitates the provision of the image's modality for testing, thereby constraining deployment flexibility. To address the issue, we present Compound Prompt Learning CLIP (CPL-CLIP), a novel method for flexible-modal FAS. This approach capitalizes on a learned textual prompt that is nearly independent of modality, thus bolstering class-based classification across arbitrary modalities. Specifically, our CPL-CLIP introduces a Dual-Branch Prompt (DBP), consisting of class and modal prompts that describe and guide classification, where each prompt is composed of learnable vectors and fixed templates. To further render the class prompt as modality-agnostic as possible, a Cosine Similarity Loss (CSL) is proposed to facilitate the maximal separation of the class prompt from the modality prompt. With only the class prompt utilized during testing, CPL-CLIP enables deployment in diverse modal testing scenarios without the necessity of the test image's modality to be known. Extensive experiments demonstrate CPL-CLIP's superiority over existing methods on several flexible-modal FAS benchmarks. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

3D Printing of Collagen Nerve Scaffold with Multichannel Characteristics 6

3D Printing of Collagen Nerve Scaffold with Multichannel Cha...

引用

6th International Conference on Mechanical, Electrical and Material Application, MEMA 2023

作者： Wang, Yi-Chen Zhang, Li-Ming Guo, Kai Wang, He-Ran School of Mechanical Engineering Shenyang Ligong University Shenyang110159 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China

Given the difficulty in preparing multichannel nerve scaffolds for peripheral nerve repair, a method of manufacturing multichannel collagen nerve scaffolds by multi-nozzle 3D printing technology was proposed. Gelatin material is used as the core melting material because of its temperature-sensitive characteristics. A collagen nerve scaffold with a multichannel structure was manufactured by temperature-rising removal after printing, and the scaffold with different collagen concentrations was analyzed and evaluated in terms of microtubule diameter and mechanical properties. The research results show that the mechanical properties of the scaffold are gradually enhanced with an increase in collagen concentration. When the concentration of collagen is between 5% and 6%, the quality of the microtubule is significantly improved compared with the 4% collagen scaffold. Combined with the distribution of microtubule diameter, a lower concentration of collagen will lead to the collapse and deformation of the print structure, while a higher concentration of collagen will lead to the existence of voids in the print structure. Considering the manufacturing process, microtubule diameter, and mechanical properties of collagen nerve scaffold, 5% collagen nerve scaffold is the best and is expected to meet the requirements of peripheral nerve regeneration. © Published under licence by IOP Publishing Ltd.

关键词： Collagen

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：