检索结果-内蒙古大学图书馆

43rd Chinese Control Conference, CCC 2024

作者： Jiang, Yihua Liu, Qi Li, Yanjie the Harbin Institute of Technology Shenzhen Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics School of Mechanical Engineering and Automation 518055 China

ISBN: (纸本)9789887581581

Most traditional recommendation systems (RS) improve the model structure to obtain valid user behavior representation and make better recommendations. However, limited by the scale of the model, the model cannot accommodate an extended range of user historical data and cannot effectively extract long-term preferences. Reinforcement learning (RL) aims to maximize the cumulative return. Introducing RL can smoothly solve the long-term and short-term profit balance. However, there are specific problems with the direct combination of the two. Training RS that relies on offline user data will cause the strategy to suffer from an overestimation of action and distribution shift. Unlike the traditional RL environment, the ample space of the RS will also cause problems of insufficient exploration and sparse rewards, making the policy more difficult to learn. In response to the above issues, this work proposes an offline RL two-stage optimization framework. The framework consists of an offline RL method based on unknown behavior to alleviate the problem of action overestimation and a two-stage feature optimization training method to reduce the impact of large spaces. Experimental results prove that the method proposed in this article can effectively improve the long-term recommendation ability of the model and more effectively improve the model performance than the general offline RL algorithm. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Swin-BFB-UNet: A swin transformer-based UNet combined with bottleneck fusion block for vertebra segmentation

Swin-BFB-UNet: A swin transformer-based UNet combined with b...

引用

2024 International Conference on Computer Vision and Image Processing, CVIP 2024

作者： Gao, Yifan Li, Min Miao, Hongxia Jiang, Junfeng College of Information Science and Engineering Hohai University Jiangsu Changzhou China College of Artificial Intelligence and Automation Hohai University Jiangsu Changzhou China Key Laboratory of Maritime Intelligent Cyberspace Technology Hohai University Ministry of Education Jiangsu Changzhou China

ISBN: (纸本)9781510688384

Segmenting the vertebrae is an important part of diagnosing spine diseases and planning surgery. The vertebra's complex anatomy, featuring similar shapes of neighboring bones and vague boundaries, presents substantial challenges for precise semantic segmentation. Traditional methods often depend heavily on local features, making it difficult to capture global context and resulting in less accurate recognition. Consequently, automated and efficient segmentation approaches are crucial to overcoming these issues. This study introduces an innovative Swin-BFB-UNet architecture derived from UNet to enhance vertebra segmentation. We include the Swin Transformer into the encoder to capture both global and local information, hence enhancing vertebra segmentation accuracy. The bottleneck fusion block (BFB) fuses multi-scale features and semantic information, enhancing the model's feature representation. Furthermore, we employ both Dice Loss and Cross-Entropy Loss to alleviate the adverse effects of foreground-background area imbalance. We conducted annotations and experiments on the lateral X-ray images in the BUU-LSPINE dataset. The experimental findings indicate that our model exceeds other leading methodologies, attaining a mDice of 90.3%, hence evidencing its proficiency in precise vertebra segmentation. © 2025 SPIE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Novel Moving Strategy of Teleoperating Manipulation via Exo-Gloves 17th

A Novel Moving Strategy of Teleoperating Manipulation via ...

引用

17th International Conference on intelligent robotics and Applications, ICIRA 2024

作者： Chen, Yanjun Li, Yipeng Du, Wenfu Zeng, Puyi Cheng, Zhongjiang Zhang, Yang Shenzhen Technology University GD Shenzhen518118 China Mechanical Industry Key Laboratory of Intelligent Robotics Technology for 3C Product GD Shenzhen518118 China

ISBN: (纸本)9789819607761

In this paper, a novel type of haptic human-machine interaction was presented to realize teleoperation. The system, consisting of 5 degrees of freedom (DOF) manipulator arm, a gripper and the virtual reality(VR) headset, thus it could enhance the flexibility of manipulation, improving the accuracy of grasp and completing complex and delicate tasks requiring different moving speeds. The detailed design, working space and kinematics of the prototype were discussed, and the experimental results by simulation of grasping bananas showed that the system proposed could further improve the working space and the flexibility of traditional manipulators. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

Enhancing lithium-ion and electric conductive Li_(2)FeSiO_(4)cathode through in situ boron-doping and carbon-coating strategy

引用

Rare Metals 2022年第12期41卷 4055-4064页

作者： Hao-Xiang Li Jia-Hui Zhu Xiao-Bing Huang Tao Zhou Yu-Rong Ren Hunan Provincial Key Laboratory of Chemical Power Sources College of Chemistry and Chemical EngineeringCentral South UniversityChangsha 410083China Hunan Provincial Key Laboratory of Water Treatment Functional Materials Hunan Provincial Key Laboratory for Control Technology of Distributed Electric Propulsion AircraftCollege of Chemistry and Materials EngineeringHunan University of Arts and ScienceChangde 415000China Jiangsu Province Engineering Research Center of Intelligent Manufacturing Technology for the New Energy Vehicle Power Battery Changzhou Key Laboratory of Intelligent Manufacturing and Advanced Technology for Power BatterySchool of Materials Science and EngineeringChangzhou UniversityChangzhou 213164China

The extremely low electrical conductivity and ion-diffusion coefficient of Li_(2)FeSiO_(4)limits its application as a cathode material in lithium-ion ***,in situ boron-doped Li_(2)FeSi_(1)-xB_(x)O_(4-δ)/C(x=0,0.01,0.03,0.05 and 0.07)at the Si site was prepared via the solid-state reaction method using pitch as the c arbon source.B doping in the lattice structure and a c arbon coating on the surface of the composites could effectively enhance the Li^(+)/electron ***,the reduced particle size of the active material with the relatively high specific area via borondoped modification could improve the wettability between the electrolyte and *** the synergistic effect of appropriate boron doping and carbon coating,it exhibits a good rate performance,specific capacity,and cycling *** a result,the as-prepared Li_(2)FeSi_(0.95)B_(0.05)O_(4-δ)/C cathode showed a high discharge capacity of 160.7mAh·g^(-1)at 0.2C,and the capacity retention rate was 96%after 100 cycles at *** work presents an effective path for designing advanced cathode materials for lithium-ion batteries.

关键词： Li_(2)FeSiO_(4) Carbon coating Boron doping Synergistic effect Lithium-ion battery

来源：评论

学校读者我要写书评

暂无评论

CNN coal and rock recognition method based on hyperspectral data

引用

International Journal of Coal Science & technology 2022年第5期9卷 59-70页

作者： Jianjian Yang Boshen Chang Yuchen Zhang Wenjie Luo Shirong Ge Miao Wu School of Mechatronics and Information Engineering China University of Mining and Technology-BeijingBeijing 100083China Key Laboratory of Intelligent Mining and Robotics Ministry of Emergency ManagementBeijingChina

Aiming at the problem of coal gangue identifcation in the current fully mechanized mining face and coal washing,this article proposed a convolution neural network(CNN)coal and rock identifcation method based on hyperspectral ***,coal and rock spectrum data were collected by a near-infrared spectrometer,and then four methods were used to flter 120 sets of collected data:frst-order diferential(FD),second-order diferential(SD),standard normal variable transformation(SNV),and multi-style *** coal and rock refectance spectrum data were pre-processed to enhance the intensity of spectral refectance and absorption characteristics,as well as efectively remove the spectral curve noise generated by instrument performance and environmental factors.A CNN model was constructed,and its advantages and disadvantages were judged based on the accuracy of the three parameter combinations(i.e.,the learning rate,the number of feature extraction layers,and the dropout rate)to generate the best CNN classifer for the hyperspectral data for rock *** experiments show that the recognition accuracy of the one-dimensional CNN model proposed in this paper reaches 94.6%.Verifcation of the advantages and efectiveness of the method were proposed in this article.

关键词： Hyperspectral data Data pre-processing 1D-CNN Coal gangue identifcation

来源：评论

学校读者我要写书评

暂无评论

Fusing Dynamics and Reinforcement Learning for Control Strategy: Achieving Precise Gait and High Robustness in Humanoid Robot Locomotion 23

Fusing Dynamics and Reinforcement Learning for Control Strat...

引用

23rd IEEE-RAS International Conference on Humanoid Robots, Humanoids 2024

作者： Zhao, Zida Huang, Haodong Sun, Shilong Li, Chiyao Xu, Wenfu Harbin Institute of Technology Guangdong Provincial Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics School of Mechanical Engineering and Automation Shenzhen518055 China

ISBN: (纸本)9798350373578

Achieving precise gait planning and high robustness in locomotion control is crucial for the development and application of humanoid robots. In this paper, a novel control strategy is proposed, which combines dynamics control and reinforcement learning (RL), leveraging the precision of dynamics control and the robustness of RL. Specifically, foot placements for each step of the humanoid robot are designed, and the trajectories of the center of mass (CoM) and feet are obtained using a 3D linear inverted pendulum model (3D LIPM). Subsequently, joint angles during motion are calculated based on the trajectories of the CoM and feet using inverse kinematics equations. Finally, the obtained joint angles are trained as baseline actions using RL algorithms. To enhance control robustness, parameter domain randomization is introduced during the training process. By employing this control strategy, simulations of various single-step gaits, such as walking forward, walking to the right, and making right turns, are achieved. Additionally, trajectory tracking, locomotion tests on different terrains, and disturbance resistance are conducted. The simulation results demonstrate that the proposed control strategy enables precise gait control and exhibits strong robustness in humanoid robots. © 2024 IEEE.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

A Legged Small Celestial Body Landing Mechanism:Landing Simulation and Experimental Test

引用

Space(Science & technology) 2023年第1期3卷 453-463页

作者： Zhijun Zhao Shuang Wu Jingdong Zhao Yaobing Wang Chuncheng Zhao Beijing Key Laboratory of Intelligent Space Robotic System Technology and Applications Beijing Institute of Spacecraft System EngineeringBeijing 100094China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150006China Department of Aerospace Science and Technology Polytechnic University of MilanMilan 20133Italy

Landing mechanism tends to rebound and turn over,and the stability time is long when landing on the small celestial *** landing performance in different conditions is necessary to be evaluated to guide the ***,landing performance evaluation is realized by *** factors affecting the landing performance including cardan element damping,foot anchors,retro-rocket thrust,landing slope angle,and landing attitude are analyzed.A microgravity platform is built to test the landing mechanism,and the consistency between the simulation and the experiment is *** the basis of simulation and experiment,some landing suggestions are proposed to improve the landing performance.

关键词： thrust mechanism landing

来源：评论

学校读者我要写书评

暂无评论

A Meta-reinforcement Learning Framework for Adaptive Quadrotor UAV Attitude Control 25th

A Meta-reinforcement Learning Framework for Adaptive Quadro...

引用

25th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2024

作者： Zhao, Kaidong Li, Yanjie Liu, Zihan Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen China School of Mechanical Engineering and Automation The Harbin Institute of Technology Shenzhen Shenzhen518055 China

ISBN: (纸本)9789819642069

This paper presents a meta-reinforcement learning approach for quadrotor UAV attitude control, addressing the limitations of traditional control methods in complex, dynamic, and uncertain environments. Our method integrates the advantages of context learning, Gaussian sampling, and multi-task training to rapidly adapt to diverse aircraft parameters and environmental conditions. Specifically, we utilize historical information quadruples as contextual data to accurately estimate current task characteristics through real-time observation and learning. In the latent space, we employ Gaussian sampling to effectively handle unknown UAV parameters. To validate the method’s efficacy, we conducted a series of experiments in the Bullet simulator, including single attitude tracking, resultant acceleration control, and continuous trajectory tracking. Experimental results demonstrate that our approach significantly outperforms traditional PID controllers and domain randomization-based SAC methods in terms of stability, rapid response, and trajectory tracking precision. Through multi-task training, our controller has developed the ability to swiftly adapt to novel situations. This research provides a robust and flexible solution for adaptive control of quadrotor UAVs, showing promise for more efficient and stable flight control in complex and dynamically changing environments. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Study of the 6.x nm short wavelength radiation spectra of laser-produced erbium plasmas for BEUV lithography

引用

Plasma Science and technology 2023年第6期25卷 41-51页

作者：吴涛王倩陈柳安陆培祥 Hubei Key Laboratory of Optical Information and Pattern Recognition School of Optical Information and Energy EngineeringWuhan Institute of TechnologyWuhan 430205People's Republic of China Guangdong Intelligent Robotics Institute Dongguan 523808People's Republic of China

Beyond extreme ultraviolet(BEUV)radiation with a wavelength of 6.x nm for lithography is responsible for reducing the source wavelength to enable continued miniaturization of semiconductor *** this work,the Required BEUV light at 6.x nm wavelength was generated in dense and hot Nd:YAG laser-produced Er *** spectral contributions from the 4p–4d and 4d–4f transitions of singly,doubly and triply excited states of Er XXIV–Er XXXII in the BEUV band were calculated using Cowan and the Flexible Atomic *** was also found that the radiative transitions between multiply excited states dominate the narrow wavelength window around 6.x *** the assumption of collisional radiative equilibrium of the laser-produced Er plasmas,the relative ion abundance in the experiment was *** the Boltzmann quantum state energy level distribution and Gram–Charlier fitting function of unresolved transition arrays(UTAs),the synthetic spectrum around 6.x nm was finally obtained and compared with the experimental *** spatio-temporal distributions of electron density and electron temperature were calculated based on radiation hydrodynamic simulation in order to identify the contributions of various ionic states to the UTAs arising from the Er plasmas near 6.x nm.

关键词： laser-produced plasmas unresolved transition array collisional radiative equilibrium

来源：评论

学校读者我要写书评

暂无评论

Hardware-Free Event Cameras Temporal Synchronization Based on Event Density Alignment 1

引用

16th International Conference on intelligent robotics and Applications, ICIRA 2023

作者： Li, Wenxuan Dong, Yan Qiu, Shaoqiang Han, Bin State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and Technology Hubei Wuhan430074 China Guangdong Intelligent Robotics Institute Dongguan523106 China

ISBN: (数字)9789819964987

ISBN: (纸本)9789819964970

Event cameras are a novel type of sensor designed for capturing the dynamic changes of a scene. Due to factors such as trigger and transmission delays, a time offset exists in the data collected by multiple event cameras, leading to inaccurate information fusion. Thus, the collected data needs to be synchronized to overcome any potential time offset issue. Hardware synchronization methods require additional circuits, while certain models of event cameras (e.g., CeleX5) do not support hardware synchronization. Therefore, this paper proposes a hardware-free event camera synchronization method. This method determines differences between start times by minimizing the dissimilarity of the event density distributions of different event cameras and synchronizes the data by adjusting timestamps. The experiments demonstrate that the method's synchronization error is less than 10 ms under various senses with multiple models of event cameras. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023.

关键词： Cameras

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：