检索结果-内蒙古大学图书馆

SeaFree-GS: Reconstructing Underwater 3D Scenes With True Appearances

IEEE Signal Processing Letters 2025年 32卷 2114-2118页

作者： Liu, Shaohua Gao, Ning Fu, Shaowen Zhong, Xiaoqing Li, Hongjue Beihang University School of Astronautics Shenyuan Honors College Beijing100191 China Beihang University School of Astronautics Beijing100191 China Beijing Aerospace Automatic Control Institute Beijing100854 China National Key Laboratory of Science and Technology on Aerospace Intelligent Control Beijing100854 China China Academy of Space Technology Beijing100094 China Beijing Key Laboratory of System Design for Reusable Launch Vehicle State Key Laboratory of High- Efficiency Reusable Aerospace Transportation Technology China

Reconstructing underwater 3D scenes with accurate appearances is crucial for numerous tasks. However, existing underwater 3D reconstruction methods often fail to restore the true scene appearance due to degradation in underwater images caused by water effects. In this letter, we propose SeaFree-GS, a novel approach leveraging 3D Gaussian Splatting (3DGS) to reconstruct underwater scenes with their true appearances. Specifically, we introduce a Degradation-Aware Dual-Color Modeling strategy, where each Gaussian is assigned an intrinsic color representing the true scene appearance and a viewpoint-dependent degraded color to incorporate water effects. For a given viewpoint, this strategy physically derives the corresponding degraded colors from the intrinsic colors to render the underwater image. To improve reconstruction accuracy, we introduce a Content-Based Loss for selective enhancement of supervision over foreground and background regions, and a Coarse-Grained Depth Loss to enforce additional geometric constraints. Experiments on three datasets demonstrate that SeaFree-GS achieves state-of-the-art performance in Underwater True Appearance Reconstruction, and also performs competitively in Underwater Novel View Synthesis. © 1994-2012 IEEE.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Enhancing Robot Learning Through Cognitive Reasoning Trajectory Optimization Under Unknown Dynamics

引用

IEEE robotics and Automation Letters 2025年第6期10卷 5401-5408页

作者： Dong, Qingwei Wu, Tingting Zeng, Peng Zang, Chuanzhi Wan, Guangxi Cui, Shijie Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang110016 China Chinese Academy of Sciences Key Laboratory of Networked Control Systems Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China China Mobile Research Institute Beijing100053 China Shenyang University of Technology School of Artifcial Intelligence Shenyang110870 China

In the domain of robot learning, equipping robots with the capability to swiftly acquire operational skills poses a significant challenge. Currently, reinforcement learning techniques are adept at addressing dynamic, unstructured problems involving rich contact scenarios. However, the convergence rate of these algorithms is often slow due to the high dimensionality of the robot state-action mapping space and the extensive initial policy search space. Meanwhile, advancements in large language models (LLMs) have endowed these models with a degree of logical reasoning ability, enabling them to take goal-oriented actions proactively during the initial phase of a robotic task. These models can implicitly generate features of states and uncover underlying patterns in trajectory generation. Yet, in complex manipulative tasks involving rich contact scenarios, LLMs still fall short. Thus, integrating the robust interactive capabilities of reinforcement learning with the strong logical reasoning of LLMs, and enhancing policy search with LLMs, could potentially accelerate the speed of policy searches significantly. In this letter, we introduce a Cognitive Reasoning Trajectory Optimization method. This approach utilizes Low-level Cognitive Control Tuning to enable LLMs with robust logical reasoning to make effective single-step decisions in Markov Decision Process (MDP) tasks. By fitting dynamic models with high-quality cognitive reasoning data and optimizing control strategies, this method constrains the policy search space and enhances the efficiency of trajectory optimization. Experimental results on various manipulative tasks using the Sawyer robot in the Mujoco simulator validate the effectiveness of the proposed algorithm. © 2016 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Design and Fabrication of Wearable Flexible 3D Tactile Sensors 11

Design and Fabrication of Wearable Flexible 3D Tactile Senso...

引用

11th International Conference on Mechatronics and robotics Engineering, ICMRE 2025

作者： Xu, Naijia Zhang, Daohui Fu, Xin Han, BaiSong Hou, Xudong Zhao, Xingang Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang China University of Chinese Academy of Sciences Beijing China Shenyang University of Technology Shenyang China

ISBN: (纸本)9798331509293

In recent years, flexible haptic sensors have gained significant attention for their potential in robotics, inspired by the tactile sensing capabilities of human skin. These sensors enable robots to detect a wide range of haptic information, such as pressure and slip, thereby enhancing their flexibility and sensory capabilities. This paper introduces a flexible 3D haptic sensor with high sensitivity and low hysteresis, designed to detect both normal and tangential forces. The sensor features a three-layer structure: the top layer consists of a flexible square magnet that deforms under external forces, enabling force detection;the middle layer is made of Ecoflex 00-30 elastomer;and the bottom layer is a flexible circuit board (FPCB) embedded with Hall sensors that convert magnetic field changes into electrical signals. The flexible sensor is integrated into a smart glove by sewing it onto the thumb and index finger positions. By combining sensor data with machine learning algorithms, the glove achieves handwriting recognition with a classification accuracy of 96.67%. Additionally, the glove incorporates slip sensing capabilities to monitor grip states in real-time during object manipulation. These features make the sensor highly suitable for applications in wearable technology and human-computer interaction, with promising prospects for advancing human-robot interaction and robotics in general. © 2025 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Stabilization of zinc anode by trace organic corrosion inhibitors for long lifespan

引用

Chinese Chemical Letters 2025年第3期36卷 538-543页

作者： Wenfeng Shao Chuanlin Li Chenggang Wang Guangsen Du Shunshun Zhao Guangmeng Qu Yupeng Xing Tianshuo Guo Hongfei Li Xijin Xu School of Physics and Technology University of JinanJi’nan 250022China State Key Laboratory of Chemical Resource Engineering Beijing University of Chemical TechnologyBeijing 100029China School of Chemistry and Chemical Engineering Shandong UniversityJi’nan 250100China School of System Design and Intelligent Manufacturing Southern University of Science and TechnologyShenzhen 518000China

Aqueous zinc-ion batteries are highly favored for their enhanced safety and reduced ***,there exist challenges including zinc dendrite,hydrogen evolution,and surface corrosion to be *** electrolyte additives is a highly convenient approach to solving zinc anode-related *** by industrial corrosion protection,a trace amount of the corrosion inhibitor urotropine(URT)is used as an electrolyte additive to protect the zinc *** calculation and experimental analysis confirm the adsorption of URT molecules onto the surface of Zn,which inhibits hydrogen *** adsorption further leads to the formation of an inorganic-organic bilayer solid electrolyte interface(SEI)on the surface of the zinc anode,effectively protecting the Zn anode from corrosion,hydrogen evolution and zinc *** presence of SEI enables symmetrical Zn//Zn cells to exhibit a long cycling performance of 1750 h at 1mA/cm^(2)and an average coulombic efficiency of 99.0%at 1mA/cm^(2)in Zn//Cu *** being coupled with polyaniline(PANI),the Zn//PANI full battery displays excellent cycle stability and specific capacity.

关键词： Solid electrolyte interface Aqueous zinc-ion battery Corrosion inhibitors Electrolyte additive Zinc anode

来源：评论

学校读者我要写书评

暂无评论

A Pilot Study on Fabric-based Pneumatic Soft Gloves for Assisting Patients with Severe Brachial Plexus Injury

引用

IEEE Transactions on Biomedical Engineering 2025年 PP卷 PP页

作者： Feng, Miao Yang, Dezhi Sun, Jianing Lao, Jie Rui, Jing Gu, Guoying Shanghai Jiao Tong University Robotics Institute State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Key Laboratory of Intelligent Robotics Meta Robotics Institute Shanghai200240 China Southwest Technology and Engineering Research Institute Chongqing400039 China Fudan University Department of Hand Surgery Huashan Hospital China NHC Key Laboratory of Limbs Reconstruction Shanghai Key Laboratory of Peripheral Nerve and Microsurgery Shanghai200040 China

Objective: Robotic gloves show promise in hand assistance due to their wearability and home-based potential, yet empirical research remains limited. This pilot study presents a fabric-based pneumatic soft glove, aiming to identify its potential and challenges in clinical practice by evaluating its effectiveness in assisting patients with severe brachial plexus injury (BPI). Methods: The glove integrates a thumb abduction actuator and four bidirectional fabric-based pneumatic actuators (FPAs) with asymmetric chambers for high output force. Sixteen healthy volunteers and five individuals with BPI, all of whom lacked active hand and wrist movements, were recruited. Participants performed object grasping across 25 cm. The healthy group performed seven tasks using objects weighing up to 2 kg, with muscle activities recorded for analysis. The BPI group further performed tasks with eight objects from the action research arm test (ARAT) and twelve objects for activities of daily living (ADLs), encompassing various sizes, weights, and geometries. Results: In the healthy group, sEMG showed a decrease in 89.3% of trials, with 56.0% of these decreases being significant (p © 1964-2012 IEEE.

关键词： Pneumatic actuators

来源：评论

学校读者我要写书评

暂无评论

Intelligent Fault Diagnosis Method of Train Axle Box Bearing Based on Improved Deep Reinforcement Learning

Intelligent Fault Diagnosis Method of Train Axle Box Bearing...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Meng, Zhangxuan Lei, Zihao Deng, Shuaiqing Gu, Shulong Zhang, Zhifen Su, Yu Wen, Guangrui National Key Lab of Aerospace Power System and Plasma Technology Xi’an Jiaotong University Xi’an 710049 China State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong University Xi’an 710049 China Key Laboratory of Modern Design and Rotor Bearing System of the Ministry of Education Xi’an Jiaotong University Xi’an 710049 China

ISBN: (纸本)9789819639687

Axlebox bearings are the key components of rail transit train bogies, which are crucial to the operation of the train. However, the conditions of transit are relatively complex, coupled with the fact that the optimization of the deep neural network of the existing fault diagnosis methods requires a large number of manual modifications and experience of experts, which makes it difficult to effectively diagnose the faults of axlebox bearings. To address the above issues, this paper proposes an improved deep reinforcement learning strategy based on Dueling Double Deep Q-Network (D3QN) and Prioritized Experience replay (PER) for the fault diagnosis of axlebox bearings. Firstly, D3QN combines Double DQN and Dueling DQN to solve the problem of overestimation of the Q-value of Deep Q Network (DQN) and improve the stability of training. Secondly, by introducing the prioritized experience replay and the elevated reward mechanism, the efficiency of experience utilization and the speed of model convergence is improved. Finally, the proposed method is validated by using subway train transmission system fault simulation datasets of Beijing Jiaotong University (BJTU). The results show that compared with the original DQN method, PER-DR3QN has significant improvement in training efficiency, accuracy and stability. © Beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of gap-filling methods for generating landsat-like land surface temperatures under all-weather conditions

引用

ISPRS Journal of Photogrammetry and Remote Sensing 2025年 225卷 113-130页

作者： Guo, Jiali Quan, Jinling Zhan, Wenfeng Wen, Zhongguan State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research CAS Beijing100101 China College of Resources and Environment University of Chinese Academy of Sciences Beijing100190 China Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology International Institute for Earth System Science Nanjing University Jiangsu Nanjing210046 China College of Environmental Sciences and Engineering Peking University Beijing100871 China

Thermal infrared remote sensors provide cost-effective and widespread land surface temperatures (LSTs) but often with spatiotemporal gaps due to discrete sampling and synoptic disturbance, greatly limiting their reliability and application. Current gap-filling methods have been primarily developed and validated for medium- to low-resolution LSTs;however, with rising demand for spatiotemporally continuous, high-resolution (tens of meters like Landsat) LSTs across disciplines, there is an urgent need to assess these methods’ applicability and uncertainty at higher spatial resolutions under a unified framework. In this study, we apply eight typical and hybrid methods, including temporal interpolation, spatiotemporal interpolation, weight-based fusion, learning-based fusion, and four standard annual temperature cycle (ATC)-based hybrid reconstructions, to fill gaps in irregularly spaced Landsat series over Weishan, Huairou, and Yulin, China. These sites represent cropland in a sub-humid plain, forest in a sub-humid mountain region, and grassland in the semi-arid Loess Plateau. We evaluate their performance in terms of spatiotemporal pattern, statistical accuracy, sensitivity to input data quality and distribution, and adaptability to different synoptic and surface conditions based on cloudy Landsat data and in-situ measurements. Results reveal that the enhanced ATC (EATC) method is optimal among these methods, capturing all-weather spatiotemporal dynamics at the Landsat scale with superior accuracy and robustness under various input, cloud, and ground conditions. In addition, the ATC-based hybrid methods do not necessarily improve the statistical accuracy over their respective typical ones. This comprehensive evaluation provides valuable insights into the selection of appropriate gap-filling methods for generating Landsat-like LSTs under all-weather conditions and highlights the need for further advancements especially in addressing abrupt changes in land cover types an

关键词： Surface stress

来源：评论

学校读者我要写书评

暂无评论

Control, Modeling and Stability Analysis of DRU-based Grid-forming Converter

引用

Chinese Journal of Electrical Engineering 2025年第1期11卷 83-92页

作者： Wencong Wu Minzhi Wang Liang Tu Haiqing Cai Guanglei Yan Xiaohui Qu Haohan Gu Wei Chen State Key Laboratory of HVDC China Southern Power GridGuangzhou 510663China National Energy Power Grid Technology R&D Center Guangzhou 510663China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power Systems China Southern Power GridGuangzhou 510663China CSG Key Laboratory for Power System Simulation China Southern Power GridGuangzhou 510663China School of Electrical Engineering Southeast UniversityNanjing 210096China

Diode rectifier unit(DRU)-based high-voltage direct current(HVDC)transmissionsystems areeffectivein achieving the stableandeconomical operation of offshore *** theuncontrollable characteristicsof DRUs,a grid-forming(GFM)strategy forwind-turbine converters isnecessary to support offshore AC voltageand ***,the active power-synchronization control in traditional GFM converters is unsuitable for DRU-based GFM ***,the stability issue for DRU-based HVDC systems involving DRU-based GFM and grid-following(GFL)converters has not yet been *** solve these issues,this study begins with the characteristics of a DRU-based HVDC system and presents a control scheme for DRU-based GFM converters for power ***,the dq-frame impedance model of the DRU-based GFM converteris proposed for the stability analysis of the entire HVDC ***,a simulation platform is built to verify the model accuracy and system stability.

关键词： Diode rectifier unit offshore wind-powergeneration grid-forming converter impedance model stabilityanalysis

来源：评论

学校读者我要写书评

暂无评论

A Valuable and Low-Budget Process Scheme of Equivalized 1 nm technology Node Based on 2D Materials

引用

Nano-Micro Letters 2025年第8期17卷 294-305页

作者： Yang Shen Zhejia Zhang Zhujun Yao Mengge Jin Jintian Gao Yuhan Zhao Wenzhong Bao Yabin Sun He Tian College of Integrated Circuit Science and Engineering Shanghai Key Laboratory of Multidimensional Information ProcessingEast China Normal UniversityShanghai 200241People’s Republic of China Institute of Microelectronics and Beijing National Research Center for Information Science and Technology(BNRist) Tsinghua UniversityBeijing 100084People’s Republic of China State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433People’s Republic of China Shaoxin Laboratory Shaoxing 312000People’s Republic of China

Emerging two-dimensional(2D)semiconductors are among the most promising materials for ultra-scaled transistors due to their intrinsic atomic-level *** the stacking process advances,the complexity and cost of nanosheet field-effect transistors(NSFETs)and complementary FET(CFET)continue to *** 1 nm technology node is going to be based on Si-CFET process according to international roadmap for devices and systems(IRDS)(2022,https://***/),but not publicly confirmed,indicating that more possibilities still *** miniaturization advantage of 2D semiconductors motivates us to explore their potential for reducing process costs while matching the performance of next-generation nodes in terms of area,power consumption and *** this study,a comprehensive framework is built.A set of MoS2 NSFETs were designed and fabricated to extract the key parameters and *** then for benchmarking,the sizes of 2D-NSFET are scaled to a extent that both of the Si-CFET and 2D-NSFET have the same average device *** these conditions,the frequency of ultra-scaled 2D-NSFET is found to improve by 36%at a fixed power *** work verifies the feasibility of replacing silicon-based CFETs of 1 nm node with 2D-NSFETs and proposes a 2D technology solution for 1 nm nodes,i.e.,“2D eq 1 nm”*** the same time,thanks to the lower characteristic length of 2D semiconductors,the miniaturized 2D-NSFET achieves a 28%frequency increase at a fixed power ***,developing a standard cell library,these devices obtain a similar trend in 16-bit RISC-V *** work quantifies and highlights the advantages of 2D semiconductors in advanced nodes,offering new possibilities for the application of 2D semiconductors in high-speed and low-power integrated circuits.

关键词： Two-dimensional semiconductors 1 nm technology node Nanosheet field-effect transistors Complementary field-effect transistors Horizontal scaling

来源：评论

学校读者我要写书评

暂无评论

Insulators Defect Detection for Power Grid Based on Improved Yolov7 Algorithm 13

Insulators Defect Detection for Power Grid Based on Improved...

引用

13th International Conference on Intelligent Control and Information Processing, ICICIP 2025

作者： Zhang, Zhiwei Zhuang, Yan Liang, Zhida Kong, Shuai Zhu, Shengyi School of Control Science and Engineering Dalian University of Technology Dalian China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Special Equipment Safety Testing Technology of Zhejiang Province Zhejiang Academy of Special Equipment Science Hangzhou China

ISBN: (纸本)9798331516147

High-current out-of-phase closed bus is an essential link in the transmission of electric energy and is widely used in thermal power stations, hydropower stations and nuclear power plants. Although these busbars have the advantages of excellent dustproof effect and strong magnetic shielding, they are susceptible to insulator aging and damage in long-term operation, posing a potential safety risk to the power grid. Due to the enclosed space inside the bus and the complexity of external maintenance tasks, manual inspection has problems such as inefficiency and low safety. In order to solve these problems, this paper proposes an improved detection algorithm based on Yolov7 for insulator defect detection in hydropower station scenarios. Because of the particularity of Yolov7 network structure and application scenarios, this paper proposes a Channel Feature Enhancement module to enhance the channel representation ability of the network. In addition, an Edge Feature Enhancement module is introduced to improve the boundary detection of insulators by enhancing the contrast between the target and the background. Considering the limitations of existing studies in specific scenarios and the scarcity of dataset, this paper constructs and accurately annotates an insulator defect detection dataset applied to hydropower station scenarios. Experimental results show that the improved-Yolov7-tiny algorithm in this paper achieves a balance between accuracy and inference speed. © 2025 IEEE.

关键词： Magnetic shielding

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：