检索结果-内蒙古大学图书馆

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 722-736页

作者： Da Yu Mingyi Zhang Mantian Li Fusheng Zha Junge Zhang Lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE

Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,known as catastrophic forgetting,due to allowing parameter *** this work,we consider a more practical online class-incremental CL setting,where the model learns new samples in an online manner and may continuously experience new ***,prior knowledge is unavailable during training and *** works usually explore sample usages from a single dimension,which ignores a lot of valuable supervisory *** better tackle the setting,we propose a novel replay-based CL method,which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous ***,besides the previous raw samples,we store the corresponding logits and features in the ***,to imitate the prediction of the past model,we construct extra constraints by leveraging multi-level information stored in the *** the same number of samples for replay,our method can use more past knowledge to prevent *** conduct extensive evaluations on several popular CL datasets,and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic *** further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.

关键词： Catastrophic forgetting class-incremental learning continual learning(CL) experience replay

来源：评论

学校读者我要写书评

暂无评论

MADDPG Based Radar Interference Resource Allocation Decision

MADDPG Based Radar Interference Resource Allocation Decision

引用

2024 China automation Congress, CAC 2024

作者： Jiang, Sen Wang, Bo School of HDU-ITMO Research Center for Intelligent Systems and Robotics Hangzhou Dianzi University Hangzhou310018 China School of Automation International Joint Research Laboratory for Autonomous Robotic Systems Hangzhou Dianzi University Hangzhou310018 China

ISBN: (纸本)9798350368604

For the problem of jamming penetration under the one-to-many scenario with jammer, a real-time radar interference resource allocation method based on the Multi-agent deep deterministic policy gradient (MADDPG) algorithm is proposed. This method describes the interference resource allocation model as a Markov Decision Process (MDP), and designed the state space, action space and reward function for interference resource allocation problem. The jammer is divided into three heterogeneous agents, each responsible for selecting jamming targets, jamming patterns, and jamming power, respectively. These three agents coordinate to enhance the convergence ability of the high-dimensional action space algorithm. Simulation results indicate that the jamming resource allocation method designed in this paper provides better jamming effects on radar positions, higher stability, and effectively improves the operational performance of the jammer. © 2024 IEEE.

关键词： Radar interference

来源：评论

学校读者我要写书评

暂无评论

A Novel Acupuncture Needle Based on FBG for Quantitative Evaluation of Expert Manipulations 20

A Novel Acupuncture Needle Based on FBG for Quantitative Eva...

引用

20th IEEE international Conference on Mechatronics and automation, ICMA 2023

作者： Yuan, Zhihang Zhang, Linshuai Jiang, Tao Gu, Shuoxin Xu, Lin Zhang, Yujie Zeng, Peng Chengdu University of Information Technology School of Automation Sichuan Chengdu China Chengdu University of Traditional Chinese Medicine School of Intelligent Medicine Sichuan Chengdu China Chengdu University of Information Technology International Joint Research Center of Robotics and Intelligence System of Sichuan Province Sichuan Chengdu China

ISBN: (纸本)9798350320831

In the process of acupuncture treatment, it is very important to obtain the pressure information and torque of acupuncture, which can be fed back to the acupuncturist to evaluate the therapeutic effect. At present, most of the sensor needles use resistance strain gauge and piezoelectric ceramic plate to complete force information collection. The above sensors are not only susceptible to the influence of external environment, but their accuracy is not high enough. Therefore, Fiber Bragg grating (FBG) is creatively used as the sensor in the field of acupuncture. It also has innovative significance in the field of acupuncture. In this paper, a three-axis force-sensing needle based on flexural hinge and Fiber Bragg grating (FBG) is designed to sense the contact force and torque when applying twist stitch method. To ensure the feasibility of the sensor needle, a mathematical model was established and an appropriate stiffness structure was designed. The rationality of the sensor needle was verified by static structure analysis and modal analysis of finite element simulation. Finally, it was proved that the sensor needle could meet the design requirements and complete the task of force sensing. © 2023 IEEE.

关键词： Needles

来源：评论

学校读者我要写书评

暂无评论

A Force Control Method of Medical Robot Based on Impedance Control

A Force Control Method of Medical Robot Based on Impedance C...

引用

2024 IEEE international Conference on robotics and Biomimetics, ROBIO 2024

作者： Yuan, Zhihang Zhang, Linshuai Jiang, Tao Gu, Shuoxin Xu, Lin Zhang, Yujie Zeng, Peng Grzegorzek, Marcin School of Automation Chengdu University of Information Technology Sichuan Chengdu China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Sichuan Chengdu China Chengdu University of Information Technology International Joint Research Center of Robotics and Intelligence System of Sichuan Province Sichuan Chengdu China Institute of Medical Informatics University of Lübeck Lübeck23538 Germany

ISBN: (纸本)9781665481090

The problem of dynamic contact between robots and the physical environment has always been a hot research topic with great significance. In the process of rapid development of robotics technology, the field of medical robots has gradually emerged, and the research on compliant control and force control algorithms involved in dynamic contact has become increasingly important. At present, most of the subjects interacting with the environment and moving according to feedback are robotic arms. This paper focuses on a lighter and simpler type of actuator composed of a motor and slide table, studies the commonness of this kind of mechanism, and gives the power control method, and verifies its feasibility through Simulink simulation. © 2024 IEEE.

关键词： Medical robotics

来源：评论

学校读者我要写书评

暂无评论

MADDPG Based Radar Interference Resource Allocation Decision

MADDPG Based Radar Interference Resource Allocation Decision

引用

Chinese automation Congress (CAC)

作者： Sen Jiang Bo Wang Center for Intelligent Systems and Robotics School of HDU-ITMO Research Hangzhou Dianzi University Hangzhou China International Joint Research Laboratory for Autonomous Robotic Systems School of Automation Hangzhou Dianzi University Hangzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

关键词： Markov decision processes Simulation Radar Interference Stability analysis Sensors Resource management Jamming Thermal stability Convergence

来源：评论

学校读者我要写书评

暂无评论

research on the seamless positioning method of an unmanned system based on UWB/IμGNSS fusion for indoor and outdoor

Research on the seamless positioning method of an unmanned s...

引用

2023 international Conference on Advanced Mechatronic Systems, ICAMechS 2023

作者： Jiang, Tao Wang, Qian Zhang, Linshuai Gu, Shuoxin Xu, Lin Tang, Xianggui Chengdu Univ. of Traditional Chinese Med. Unmanned Syst. Intelligent Percept. Contr. Technol. Eng. Laboratory of Sichuan Province Chengdu University of Information Technology School of Intelligent Medicine Chengdu China Chengdu University of Information Technology School of Automation Chengdu China Chengdu University of Information Technology International Joint Research Center of Robotics and Intelligence System of Sichuan Province School of Automation Sichuan Chengdu China

ISBN: (纸本)9798350307474

This paper studies the multi-sensor fusion positioning methods of Ultra-wideband (UWB), Global Navigation Satellite System (GNSS) and Inertial measurement unit (IMU), and constructs a seamless positioning system based on UWB/IμGNSS multi-sensor fusion. In this paper, the indoor location information provided by UWB is fused with IMU location data through extended Kalman filter, which solves the problems of signal loss, track interruption and jump in positioning information when unmanned systems enter indoor environment, and also improves the positioning accuracy of the overall system. In the experiment of the indoor and outdoor scenes of the unmanned vehicle system, the trajectory diagram of each sensor combination positioning mode is counted, and the error of positioning information is analyzed and studied. The results show that the overall positioning error of this method is small, it can provide stable and reliable whole-time positioning information, and achieve the high-precision seamless positioning required by unmanned systems. © 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

Point Cloud based Motion State Estimation Method for Autonomous Driving

Point Cloud based Motion State Estimation Method for Autonom...

引用

2023 international Conference on Advanced Mechatronic Systems, ICAMechS 2023

作者： Jiang, Tao Zhu, Enzhi Wu, Sidong Zhang, Linshuai Gu, Shuoxin Xu, Lin Wang, Qian Tang, Xianggui Chengdu Univ. of Traditional Chinese Med. Unmanned Syst. Intelligent Percept. Contr. Technol. Eng. Laboratory of Sichuan Province Chengdu University of Information Technology School of Intelligent Medicine Chengdu China Chengdu University of Information Technology School of Automation Chengdu China Chengdu Univ. of Info. Technol. Unmanned Syst. Intelligent Perception Control Technology Engineering Laboratory of Sichuan Province Chengdu University of Information Technology School of Automation Chengdu China Chengdu University of Traditional Chinese Medicine School of Automation Chengdu Univ. of Info. Technol. Intl. Jt. Res. Ctr. of Robotics and Intell. Syst. of Sichuan Prov. School of Intelligent Medicine Chengdu China Chengdu University of Information Technology International Joint Research Center of Robotics and Intelligence System of Sichuan Province School of Automation Chengdu China

ISBN: (纸本)9798350307474

Generally, motion vector information primarily stems from moving objects, while static objects contribute minimally to the estimation task. Traditional approaches for motion vector estimation typically rely on scene flow methods that depend on deep models to extract features from individual points at a high cost. These methods then acquire flow information through complex matching mechanisms or feature decoding. Such approaches are computationally expensive and exhibit substantial latency. Moreover, they neglect the importance of motion objects in motion vector estimation and the interference from static objects. Therefore, this paper introduces a novel method that first performs point cloud motion segmentation and subsequently estimates motion vectors. This approach focuses on leveraging point cloud information annotated with motion objects to estimate three-dimensional scene flow more effectively. By employing motion segmentation, we can obtain annotations for moving objects, enabling greater emphasis on the estimation of motion vectors for more challenging cases. In our experiments conducted on the KITTI dataset, the proposed method demonstrates superior performance compared to existing scene flow estimation methods. Specifically, without considering motion segmentation errors, the error in the motion direction is only 0.0363 m/s, showcasing better performance. Additionally, our method achieves an error of 0.076 m for three-dimensional endpoint error (EPE3D), showcasing distinct advantages over current scene flow networks. © 2023 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

BCLH2Pro:A novel computational tools approach for hydrogen production prediction via machine learning in biomass chemical looping processes

引用

Energy and AI 2024年第4期18卷 13-26页

作者： Thanadol Tuntiwongwat Sippawit Thammawiset Thongchai Rohitatisha Srinophakun Chawalit Ngamcharussrivichai Somboon Sukpancharoen Department of Mechanical Engineering Faculty of EngineeringKhon Kaen UniversityKhon Kaen 40002Thailand Department of Automation Robotics and Intelligent System Faculty of EngineeringKhon Kaen UniversityKhon Kaen 40002Thailand Department of Chemical Engineering Faculty of EngineeringKasetsart UniversityBangkok 10900Thailand Center of Excellence in Catalysis for Bioenergy and Renewable Chemicals(CBRC) Faculty of ScienceChulalongkorn UniversityPathumwanBangkok 10330Thailand Institute of Nanoscience and Nanotechnology(ION2) Universiti Putra MalaysiaSerdang 43400SelangorMalaysia Department of Agricultural Engineering Faculty of EngineeringKhon Kaen UniversityKhon Kaen 40002Thailand Center for Alternative Energy Research and Development Khon Kaen UniversityKhon Kaen 40002Thailand

This study optimizes biomass chemical looping processes(BCLpro),a technique for converting biomass to energy,through machine learning(ML)for sustainable energy *** study proposes an integrated Fe_(2)O_(3)-based,BCLpro combining steam gasification for H2 *** Plus is used as the primary tool to generate extensive datasets covering 24 biomass types with 18 feature inputs in a supervised model.A methodology involving K-Nearest Neighbors(KNN),Extreme Gradient Boosting(XGB),Light Gradient Boosting Machine(LGBM),Support Vector Machine(SVM),Random Forest(RF),and CatBoost(CB)algorithms was employed to predict H_(2)yields in the BCLpro,utilizing 10-fold cross-validation for robust model *** highlight the CB algorithm’s superior performance,achieving up to 98%predictive accuracy,with carbon content,reducer temperature,and Fe_(2)O_(3)/Al_(2)O_(3)mass ratio identified as crucial *** algorithm has been developed into a user-friendly tool,BCLH2Pro,accessible via a web *** tool is designed to assist in reducing costs,optimizing biomass selection,and planning operational conditions to maximize H2 yield in BCLpro *** to the tool can be obtained through the following link:http://***/.

关键词： Artificial intelligence Supervised learning Process simulation Chemical looping Agricultural waste

来源：评论

学校读者我要写书评

暂无评论

A High-sensitivity Three-Dimensional Force Sensing Sensor for Minimally Invasive Cardiac Ablation Surgery

A High-sensitivity Three-Dimensional Force Sensing Sensor fo...

引用

IEEE international Conference on Mechatronics and automation

作者： Jie Jiang Linshuai Zhang Shiqi Jiang Yuyang Luo Xin Tian Shuoxin Gu Tao Jiang School of Automation Chengdu University of Information Technology Chengdu China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu China International Joint Research Center of Robotics and Intelligence System of Sichuan Province Chengdu University of Information Technology Chengdu China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

This paper introduces a high-sensitivity distal three-dimensional force sensor designed for cardiac ablation surgery. The sensor combines a force-sensitive structure with fiber Bragg gratings (FBGs) for the measurement of triaxial forces. At the tip of the sensor, an elastic flexure structure is designed, with four pairs of symmetrically arranged U-shaped slots for axial force perception and a modified I-beam structure for lateral force measurement. Five FBG elements are embedded into the elastic flexure structure, with each FBG placed in a tightly suspended manner and fixed at both ends using an adhesive to detect micro-strain and ensure sensitivity. The theoretical force-strain relationship is derived, and decoupling methods are provided. Simulation experiments based on finite element modeling are conducted for static calibration analysis. Simulation results indicate that under axial forces ranging from 0 to 2N, the axial force resolution is 4.46mN, and under lateral forces ranging from -1 to 1N, the lateral force resolutions in the two directions are 0.294mN and 0.293mN, respectively. These findings demonstrate that the sensor exhibits high sensitivity, validating the effectiveness of the design.

关键词： Optical fibers Optical fiber sensors Sensitivity Force measurement Minimally invasive surgery Simulation Force

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of a Novel intelligent Acupuncture Robot

Design and Analysis of a Novel Intelligent Acupuncture Robot

引用

IEEE international Conference on Mechatronics and automation

作者： Zhihang Yuan Linshuai Zhang Tao Jiang Shuoxin Gu Lin Xu Zheng Yu Jingbo Guan Shiqi Jiang School of Automation Chengdu University of Information Technology Chengdu China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu China International Joint Research Center of Robotics and Intelligence System of Sichuan Province Chengdu University of Information Technology Chengdu China

ISBN: (数字)9798350388077

ISBN: (纸本)9798350388084

Acupuncture treats systemic diseases through the conduction of meridians and acupoints, and applies certain manipulations. However, acupuncture has problems such as subjectivity in artificial acupoint selection, difficulty in standardizing acupuncture techniques, and poor uncertainty in acupuncture stimulation. With the rapid development of artificial intelligence technology and medical robotics industry, acupuncture, a traditional medicine, has ushered in new development opportunities. the model of the needle applying mechanism is constructed, and then the static structure analysis and modal analysis are carried out to verify the rationality, feasibility and reliability of the structural design. Then the model is abstracted into a mathematical model and presented in a modular way, which is encapsulated into a usable simulation module after adding constraints and load conditions as well as contact settings. Finally, the feasibility, rationality and reliability of the established model are visually tested by the open-loop control in the form of waveforms.

关键词： Analytical models automation Modal analysis Process control Needles Reliability engineering Mathematical models

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：