检索结果-南通市图书馆

Bio-inspired Design and Inverse Kinematics Solution of an Omnidirectional Humanoid Robotic Arm with Geometric and Load Capacity Constraints

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2024年第2期21卷 778-802页

作者： Zhichao Zhu Zirong Luo Yiming Zhu Tao Jiang Minghai Xia Shanjun Chen Boyu Jin College of intelligence science and technology National University of Defense TechnologyChangshaChina

Inspired by the driving muscles of the human arm,a 4-Degree of Freedom(DOF)concentrated driving humanoid robotic arm is proposed based on a spatial double parallel four-bar *** four-bar mechanism design reduces the inertia of the elbow-driving unit and the torque by 76.65%and 57.81%,*** the human pose regulation strategy that the human arm picks up a heavy object by adjusting its posture naturally without complicated control,the robotic arm features an integrated position-level closed-form inverse solution method considering both geometric and load capacity *** method consists of a geometric constraint model incorporating the arm angle(φ)and the Global Configuration(GC)to avoid joint limits and singularities,and a load capacity model to constrain the feasible domain of the arm ***,trajectory tracking simulations and experiments are conducted to validate the feasibility of the proposed inverse solution *** simulated maximum output torque,maximum output power and total energy consumption of the robotic arm are reduced by up to 2.0%,13.3%,and 33.3%,*** experimental results demonstrate that the robotic arm can bear heavy loads in a human-like posture,effectively reducing the maximum output torque and energy consumption of the robotic arm by 1.83%and 5.03%,respectively,while avoiding joints beyond geometric and load capacity *** proposed design provides a high payload–weight ratio and an efficient pose control solution for robotic arms,which can potentially broaden the application spectrum of humanoid robots.

关键词： Humanoid robotic arm Bio-inspired design Inverse kinematics solution Load capacity constraint Geometric constraint

Unsupervised Multi-Expert Learning Model for Underwater Image Enhancement

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 708-722页

作者： Hongmin Liu Qi Zhang Yufan Hu Hui Zeng Bin Fan the School of intelligence science and technology and the Institute of Artificial intelligence University of Science and Technology BeijingBeijing 100083China the School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China IEEE

Underwater image enhancement aims to restore a clean appearance and thus improves the quality of underwater degraded *** methods feed the whole image directly into the model for ***,they ignored that the R,G and B channels of underwater degraded images present varied degrees of degradation,due to the selective absorption for the *** address this issue,we propose an unsupervised multi-expert learning model by considering the enhancement of each color ***,an unsupervised architecture based on generative adversarial network is employed to alleviate the need for paired underwater *** on this,we design a generator,including a multi-expert encoder,a feature fusion module and a feature fusion-guided decoder,to generate the clear underwater ***,a multi-expert discriminator is proposed to verify the authenticity of the R,G and B channels,*** addition,content perceptual loss and edge loss are introduced into the loss function to further improve the content and details of the enhanced *** experiments on public datasets demonstrate that our method achieves more pleasing results in vision *** metrics(PSNR,SSIM,UIQM and UCIQE) evaluated on our enhanced images have been improved obviously.

关键词： Multi-expert learning underwater image enhancement unsupervised learning

维普期刊数据库

An underwater vest containing an antioxidant MXene hydrogel for sensitive recognition of fish locomotion

在线全文

学校读者我要写书评

暂无评论

Microsystems & Nanoengineering 2024年第2期10卷 115-131页

作者： Chengxiu Yang Jiafei Hu Lihui Liu Shaowei Wu Mengchun Pan Yan Liu Haomiao Wang Peisen Li Qi Zhang Weicheng Qiu Huihui Luo College of intelligence science and technology National University of Defense TechnologyChangsha410073China

The perception of fish locomotion is important for understanding their adaptive behaviors and ethological ***,the main strategy used for extracting fish attitudes involves the use of a vision-based monitoring system,which is limited in its range of observation and cannot perform tracking for long ***,we report the use of a wearable tagging electronic device,referred to as an underwater vest,to capture the surrounding flow field disturbances triggered by swimming or momentary postural *** of these goals were achieved by integrating a pair of pseudocapacitive pressure-sensing units and a flexible circuit ***,additional conditions,such as variable hydraulic pressures and minimal changes in fish posture,require high stability and sensitivity of the sensing ***,hybrid hydrogel electrodes were developed through cross-linking MXene with holey-reduced graphene oxide nanosheets and further modification with 1-ethyl-3-methylimidazolium dicyanamide ionic liquids,which increased the interfacial capacitance and long-term interfacial activity of the ***,the sensing unit exhibited ultrahigh sensitivity(S_(max)~136,207 kPa^(−1))in an aquatic environment for 60 days and superior high-pressure resolution(10 Pa)within a wide working range of 1 ***,an underwater vest integrated with such sensing units clearly distinguished and recorded fish *** believe that the designed device may open avenues in flow field monitoring and ocean current detection and provide new insights into the development of sensitive underwater tagging.

关键词： underwater fish linking

A deep Koopman operator-based modelling approach for long-term prediction of dynamics with pixel-level measurements

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on intelligence technology 2024年第1期9卷 178-196页

作者： Yongqian Xiao Zixin Tang Xin Xu Xinglong Zhang Yifei Shi College of intelligence science and technology National University of Defense TechnologyChangshaChina

Although previous studies have made some clear leap in learning latent dynamics from high-dimensional representations,the performances in terms of accuracy and inference time of long-term model prediction still need to be *** this study,a deep convolutional network based on the Koopman operator(CKNet)is proposed to model non-linear systems with pixel-level measurements for long-term *** adopts an autoencoder network architecture,consisting of an encoder to generate latent states and a linear dynamical model(i.e.,the Koopman operator)which evolves in the latent state space spanned by the *** decoder is used to recover images from latent *** to a multi-step ahead prediction loss function,the system matrices for approximating the Koopman operator are trained synchronously with the autoencoder in a mini-batch *** this manner,gradients can be synchronously transmitted to both the system matrices and the autoencoder to help the encoder self-adaptively tune the latent state space in the training process,and the resulting model is time-invariant in the latent ***,the proposed CKNet has the advantages of less inference time and high accuracy for long-term *** are per-formed on OpenAI Gym and Mujoco environments,including two and four non-linear forced dynamical systems with continuous action *** experimental results show that CKNet has strong long-term prediction capabilities with sufficient precision.

关键词： deep neural networks image motion analysis image sequences sequential estimation

Proposing a machine learning approach to analyze and predict basic high-temperature properties of iron ore fines and its factors

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research(International) 2024年第5期31卷 1082-1094页

作者： Qing-ke Sun Yao-zu Wang Jian-liang Zhang Zheng-jian Liu Le-le Niu Chang-dong Shan Yun-fei Ma Institute of Artificial intelligence University of Science and Technology BeijingBeijing100083China School of intelligence science and technology University of Science and Technology BeijingBeijing100083China School of Metallurgical and Ecological Engineering University of Science and Technology BeijingBeijing100083China

The basic high-temperature properties of iron ore play a crucial role in optimizing sintering and ore blending,but the testing process for these properties is complex and has significant lag time,which cannot meet the actual needs of ore blending.A prediction model for the basic high-temperature properties of iron ore fines was thus proposed based on a combination of machine learning algorithms and genetic ***,the prediction accuracy of different machine learning models for the basic high-temperature properties of iron ore fines was ***,a random forest model optimized by genetic algorithms was built,further improving the prediction accuracy of the *** test results show that the random forest model optimized by genetic algorithms has the highest prediction accuracy for the lowest assimilation temperature and liquid phase fluidity of iron ore,with a determination coefficient of 0.903 for the lowest assimilation temperature and 0.927 for the liquid phase fluidity after *** trained model meets the fluctuation requirements of on-site testing and has been successfully applied to actual production on site.

关键词： Iron ore Basic high-temperature property Machine learning Random forest Genetic algorithm

Small tracking error correction for moving targets of intelligent electro-optical detection systems

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Mechanical Engineering 2024年第2期19卷 29-44页

作者： Cheng SHEN Zhijie WEN Wenliang ZHU Dapeng FAN Mingyuan LING College of intelligence science and technology National University of Defense TechnologyChangsha 410073China

Small tracking error correction for electro-optical systems is essential to improve the tracking precision of future mechanical and defense *** threats,such as“low,slow,and small(LSS)”moving targets,pose increasing challenges to *** core goal of this work is to address the issues,such as small tracking error correction and aiming control,of electro-optical detection systems by using mechatronics drive modeling,composite velocity–image stability control,and improved interpolation filter design.A tracking controller delay prediction method for moving targets is proposed based on the Euler transformation model of a two-axis,two-gimbal cantilever beam coaxial *** tracking error formation is analyzed in detail to reveal the scientific mechanism of composite control between the tracking controller’s feedback and the motor’s velocity–stability *** improved segmental interpolation filtering algorithm is established by combining line of sight(LOS)position correction and multivariable typical tracking fault ***,a platform with 2 degrees of freedom is used to test the *** LSS moving target shooting object with a tracking distance of S=100 m,target board area of A=1 m^(2),and target linear velocity of v=5 m/s is *** show that the optimal method’s distribution probability of the tracking error in a circle with a radius of 1 mrad is 66.7%,and that of the traditional method is 41.6%.Compared with the LOS shooting accuracy of the traditional method,the LOS shooting accuracy of the optimized method is improved by 37.6%.

关键词： electro-optical detection system small tracking error moving target visual servo aiming contro

Six million Q factor micro fused silica shell resonator with teeth-like tines released by femtosecond laser-assisted chemical etching

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science China(Technological sciences) 2024年第6期67卷 1923-1932页

作者： ZHAO Tao SHI Yan LU Kun XI Xiang WU XueZhong XIAO DingBang College of intelligence science and Engineering National University of Defense TechnologyChangsha410073China

The quality factor(Q factor)is a crucial performance parameter for *** this paper,a novel release method for highquality micro fused silica shell resonators with teeth-like tines with good surface morphology is *** method is based on femtosecond laser-assisted chemical ***,the optimal energy range of femtosecond laser modification is obtained through mechanism ***,the optimal parameters for a straight line and arc pattern are determined by optimizing the average output power,processing speed,and processing *** results demonstrate why edge breakage in rounded corners is easy under different ***,according to these conclusions,the processing is performed on a micro fused silica shell resonator with a Q factor exceeding 6 *** addition,subsurface damage is rare throughout the fabrication process,and the surface roughness of the released cross section reaches the nanometer *** improved Q factor helps suppress mechanical thermal noise and reduce zero bias and zero bias drift,constituting the primary method for enhancing the performance of the resonant gyroscope.

关键词： micro hemispherical resonator fused silica laser-assisted chemical etching quality factor

维普期刊数据库

同方期刊数据库

Understanding adversarial attacks on observations in deep reinforcement learning

在线全文

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第5期67卷 69-83页

作者： You QIAOBEN Chengyang YING Xinning ZHOU Hang SU Jun ZHU Bo ZHANG department of Computer science and technology Beijing National Research Center for Information Science and Technology Tsinghua-Bosch Joint Center for Machine Learning Institute for Artificial Intelligence Tsinghua University Peng Cheng Laboratory

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease the cumulative expected reward of a victim by manipulating its observations. Despite the efficiency of previous optimization-based methods for generating adversarial noise in supervised learning, such methods might not achieve the lowest cumulative reward since they do not generally explore the environmental ***, a framework is provided to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space. The reformulation approach adopted herein generates an optimal adversary in the function space of targeted attacks, repelling them via a generic two-stage framework. In the first stage, a deceptive policy is trained by hacking the environment and discovering a set of trajectories routing to the lowest reward or the worst-case performance. Next, the adversary misleads the victim to imitate the deceptive policy by perturbing the observations. Compared to existing approaches, it is theoretically shown that our adversary is strong under an appropriate noise level. Extensive experiments demonstrate the superiority of the proposed method in terms of efficiency and effectiveness, achieving state-of-the-art performance in both Atari and MuJoCo environments.

关键词： deep learning reinforcement learning adversarial robustness adversarial attack

A Tutorial on Federated Learning from Theory to Practice:Foundations,Software Frameworks,Exemplary Use Cases,and Selected Trends

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 824-850页

作者： M.Victoria Luzón Nuria Rodríguez-Barroso Alberto Argente-Garrido Daniel Jiménez-López Jose M.Moyano Javier Del Ser Weiping Ding Francisco Herrera department of Software Engineering Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain department of Computer science and Artificial intelligence Andalusian Research Institute in Data Science and Computational Intelligence(DaSCI)University of GranadaGranada 18071Spain department of Communications Engineering University of the Basque Country(UPV/EHU)and also with TECNALIABasque Research&Technology Alliance(BRTA)Spain School of Information science and technology Nantong UniversityNantong 226019China

When data privacy is imposed as a necessity,Federated learning(FL)emerges as a relevant artificial intelligence field for developing machine learning(ML)models in a distributed and decentralized *** allows ML models to be trained on local devices without any need for centralized data transfer,thereby reducing both the exposure of sensitive data and the possibility of data interception by malicious third *** paradigm has gained momentum in the last few years,spurred by the plethora of real-world applications that have leveraged its ability to improve the efficiency of distributed learning and to accommodate numerous participants with their data *** virtue of FL,models can be learned from all such distributed data sources while preserving data *** aim of this paper is to provide a practical tutorial on FL,including a short methodology and a systematic analysis of existing software ***,our tutorial provides exemplary cases of study from three complementary perspectives:i)Foundations of FL,describing the main components of FL,from key elements to FL categories;ii)Implementation guidelines and exemplary cases of study,by systematically examining the functionalities provided by existing software frameworks for FL deployment,devising a methodology to design a FL scenario,and providing exemplary cases of study with source code for different ML approaches;and iii)Trends,shortly reviewing a non-exhaustive list of research directions that are under active investigation in the current FL *** ultimate purpose of this work is to establish itself as a referential work for researchers,developers,and data scientists willing to explore the capabilities of FL in practical applications.

关键词： Data privacy distributed machine learning federated learning software frameworks

维普期刊数据库