检索结果-南通市图书馆

VLSI Design for High-Precision Three-Dimensional Depth Perception Chip

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2021年第3期30卷 556-560页

作者： GE Chenyang YAO Huimin ZHOU Yanhui DENG Pengchao Institute of artificial Intelligence and robotics Xi'an Jiaotong University Institute of electromagnetic and information technology Xi'an Jiaotong University

This paper presents a Very large scale integration(VLSI) design method for Three-dimensional(3 D) depth perception chip based on infrared coding structure light. The primary sub-modules on the chip contain the speckle pattern preprocessing module, blockmatching disparity estimation, depth mapping and postprocessing. The chip employs pipelining technology,and after Application specific integrated circuit(ASIC)verification, it proves that our chip has more advantages in performance of depth precision(12 bits, 1 mm @ 1 m),image resolution(1280×960), time delay(less than 17 ms),range limit(0.4～6 m). It also can generate more stable and smooth depth map in real-time, which can be used in 3 D recognition, motion capture or scene perception.

关键词： Semiconductor integrated circuits Image recognition Computer vision and image processing techniques 3D depth perception structure light coding VLSI ASIC

High-performance liquid metal electromagnetic actuator fabricated by femtosecond laser

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Extreme Manufacturing 2024年第2期6卷 511-521页

作者： Yiyu Chen Hao Wu Rui Li Shaojun Jiang Shuneng Zhou Zehang Cui Yuan Tao Xinyuan Zheng Qianqian Zhang Jiawen Li Guoqiang Li Dong Wu Jiaru Chu Yanlei Hu CAS Key laboratory of Mechanical Behavior and Design of Materials Key Laboratory of Precision Scientific Instrumentation of Anhui Higher Education InstitutesDepartment of Precision Machinery and Precision InstrumentationUniversity of Science and Technology of ChinaHefei 230027People’s Republic of China Key laboratory of Testing Technology for Manufacturing Process of Ministry of Education Southwest University of Science and TechnologyMianyang 621010People’s Republic of China Department of Mechanical Engineering The University of Hong KongHong Kong Special Administrative Region of ChinaPeople’s Republic of China

Small-scale electromagnetic soft actuators are characterized by a fast response and simplecontrol,holding prospects in the field of soft and miniaturized *** use of liquid metal(LM)to replace a rigid conductor inside soft actuators can reduce the rigidity and enhance the actuation performance and *** research efforts,challenges persist in the flexible fabrication of LM soft actuators and in the improvement of actuation *** address these challenges,we developed a fast and robust electromagnetic soft microplate actuator based on a laser-induced selective adhesion transfer *** with unprecedentedly thin LM circuit and customized low Young’s modulus silicone rubber(1.03 kPa),our actuator exhibits an excellent deformation angle(265.25?)and actuation bending angular velocity(284.66 rad·s^(-1)).Furthermore,multiple actuators have been combined to build an artificial gripper with a wide range of *** actuator presents new possibilities for designing small-scaleartificial machines and supports advancements in ultrafast soft and miniaturized robotics.

关键词： soft actuators femtosecond laser liquid metal

A Hybrid Neural Network Model for Marine Dissolved Oxygen Concentrations Time-Series Forecasting Based on Multi-Factor Analysis and a Multi-Model Ensemble

在线全文

学校读者我要写书评

暂无评论

Engineering 2021年第12期7卷 1751-1765页

作者： Hui Liu Rui Yang Zhu Duan Haiping Wu Institute of artificial Intelligence and robotics(IAIR) Key Laboratory of Traffic Safety on Track of Ministry of EducationSchool of Traffic and Transportation EngineeringCentral South UniversityChangsha 410075China

Dissolved oxygen(DO)is an important indicator of aquaculture,and its accurate forecasting can effectively improve the quality of aquatic *** this paper,a new DO hybrid forecasting model is proposed that includes three stages:multi-factor analysis,adaptive decomposition,and an optimizationbased ***,considering the complex factors affecting DO,the grey relational(GR)degree method is used to screen out the environmental factors most closely related to *** consideration of multiple factors makes model fusion more ***,the series of DO,water temperature,salinity,and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform(EWT)***,five benchmark models are utilized to forecast the sub-series of EWT *** ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm(PSOGSA).Finally,a multi-factor ensemble model for DO is obtained by weighted *** performance of the proposed model is verified by timeseries data collected by the pacific islands ocean observing system(PacIOOS)from the WQB04 station at *** evaluation indicators involved in the experiment include the Nash–Sutcliffe efficiency(NSE),Kling–Gupta efficiency(KGE),mean absolute percent error(MAPE),standard deviation of error(SDE),and coefficient of determination(R^(2)).Example analysis demonstrates that:①The proposed model can obtain excellent DO forecasting results;②the proposed model is superior to other comparison models;and③the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.

关键词： Dissolved oxygen concentrations forecasting Time-series multi-step forecasting Multi-factor analysis Empirical wavelet transform decomposition Multi-model optimization ensemble

A DDPG-based solution for optimal consensus of continuous-time linear multi-agent systems

在线全文

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2023年第8期66卷 2441-2453页

作者： LI Ye LIU ZhongXin LAN Ge SADER Malika CHEN ZengQiang College of artificial Intelligence Nankai UniversityTianjin 300350China Tianjin Key laboratory of Intelligent robotics Nankai UniversityTianjin 300350China College of Software Nankai UniversityTianjin 300350China

Modeling a system in engineering applications is a time-consuming and labor-intensive task,as system parameters may change with temperature,component aging,*** this paper,a novel data-driven model-free optimal controller based on deep deterministic policy gradient(DDPG)is proposed to address the problem of continuous-time leader-following multi-agent *** deal with the problem of the dimensional explosion of state space and action space,two different types of neural nets are utilized to fit them instead of the time-consuming state iteration *** minimal energy consumption,the proposed controller achieves consensus only based on the consensus error and does not require any initial admissible ***,the controller is self-learning,which means it can achieve optimal control by learning in real time as the system parameters ***,the proofs of convergence and stability,as well as some simulation experiments,are provided to verify the algorithm’s effectiveness.

关键词： leader-following consensus optimal control reinforcement learning deep deterministic policy gradient(DDPG)

Progress and Challenge of artificial Intelligence

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2006年第5期21卷 810-822页

作者：史忠植郑南宁 Key laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 P.R. China The laboratory of artificial Intelligence and robotics Xi'an Jiaotong University Xi'an 710049 P.R. China

artificial Intelligence （AI） is generally considered to be a subfield of computer science, that is concerned to attempt simulation, extension and expansion of human intelligence. artificial intelligence has enjoyed tremendous success over the last fifty years. In this paper we only focus on visual perception, granular computing, agent computing, semantic grid. Human-level intelligence is the long-term goal of artificial intelligence. We should do joint research on basic theory and technology of intelligence by brain science, cognitive science, artificial intelligence and others. A new cross discipline intelligence science is undergoing a rapid development. Future challenges are given in final section.

关键词： artificial intelligence visual perception machine learning agent computing semantic web intelligence science

artificial Intelligence Meets Flexible Sensors:Emerging Smart Flexible Sensing Systems Driven by Machine Learning and artificial Synapses

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano-Micro Letters 2024年第1期16卷 235-273页

作者： Tianming Sun Bin Feng Jinpeng Huo Yu Xiao Wengan Wang Jin Peng Zehua Li Chengjie Du Wenxian Wang Guisheng Zou Lei Liu Department of Mechanical Engineering State Key Laboratory of Tribology in Advanced EquipmentKey Laboratory for Advanced Manufacturing by Materials Processing TechnologyMinistry of Education of PR ChinaTsinghua UniversityBeijing 100084People’s Republic of China College of Materials Science and Engineering Shanxi ProvinceTaiyuan University of TechnologyTaiyuan 030024People’s Republic of China

The recent wave of the artificial intelligence(AI)revolution has aroused unprecedented interest in the intelligentialize of human *** an essential component that bridges the physical world and digital signals,flexible sensors are evolving from a single sensing element to a smarter system,which is capable of highly efficient acquisition,analysis,and even perception of vast,multifaceted *** challenging from a manual perspective,the development of intelligent flexible sensing has been remarkably facilitated owing to the rapid advances of brain-inspired AI innovations from both the algorithm(machine learning)and the framework(artificial synapses)*** review presents the recent progress of the emerging AI-driven,intelligent flexible sensing *** basic concept of machine learning and artificial synapses are *** new enabling features induced by the fusion of AI and flexible sensing are comprehensively reviewed,which significantly advances the applications such as flexible sensory systems,soft/humanoid robotics,and human activity *** two of the most profound innovations in the twenty-first century,the deep incorporation of flexible sensing and AI technology holds tremendous potential for creating a smarter world for human beings.

关键词： Flexible electronics Wearable electronics Neuromorphic Memristor Deep learning

adaptive patient-cooperative compliant control of lower limb rehabilitation robot

在线全文

学校读者我要写书评

暂无评论

Biomimetic Intelligence & robotics 2024年第2期4卷 42-49页

作者： Lingling Chen Jjiabao Huang Yanglong Wang Shijie Guo Mengge Wang Xin Guo School of artificial Intelligence Hebei University of TechnologyTianjin 300400China Inteligent Rehabilitation Device and Detection Technology Engineering Research Centre of the Ministry of Education Tianjin 300400China School of Mechanical Engineering Hebei University of TechnologyTianjin 300400China School of Electrical Engineering Hebei University of TechnologyTianjin 300400China

With the increase in the number of stroke patients,there is a growing demand for rehabilitation ***-assisted training is expected to play a crucial role in meeting this *** ensure the safety and comfort of patients during rehabilitation training,it is important to have a patient-cooperative compliant control system for rehabilitation *** order to enhance the motion compliance of patients during rehabilitation training,a hierarchical adaptive patient-cooperative compliant control strategy that includes patient-passive exercise and patient-cooperative exercise is proposed.A low-level adaptive backstepping position controller is selected to ensure accurate tracking of the desired *** the high-level,an adaptive admittance controller is employed to plan the desired trajectory based on the interaction force between the patient and the *** results of the patient-robot cooperation experiment on a rehabilitation robot show a significant improvement in tracking trajectory,with a decrease of 76.45%in the dimensionless squared jerk(DSJ)and a decrease of 15.38%in the normalized root mean square deviation(NRMSD)when using the adaptive admittance *** proposed adaptive patient-cooperative control strategy effectively enhances the compliance of robot movements,thereby ensuring the safety and comfort of patients during rehabilitation training.

关键词： Compliant control Lower limb rehabilitation robot(LLRR) adaptive admittance controller adaptive backstepping controller Human-robot interaction

An execution control method for the Aerostack aerial robotics framework

维普期刊数据库评论

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 Information Technology & Electronic Engineering 2019年第1期20卷 60-75页

作者： Martin MOLINA Alberto CAMPORREDONDO Hriday BAVLE AlejANDro RODRIGUEZ-RAMOS Pascual CAMPOY Department of artificial Intelligence Universidad Politécnica de Madrid Centre for Automation and robotics Universidad Politécnica de Madrid

Execution control is a critical task of robot architectures which has a deep impact on the quality of the final system. In this study, we describe a general method for execution control, which is a part of the Aerostack software framework for aerial robotics, and present technical challenges for execution control and design decisions to develop the method. The proposed method has an original design combining a distributed approach for execution control of behaviors(such as situation checking and performance monitoring) and centralizes coordination to ensure consistency of the concurrent execution. We conduct experiments to evaluate the method. The experimental results show that the method is general and usable with acceptable development efforts to efficiently work on different types of aerial missions. The method is supported by standards based on a robot operating system(ROS) contributing to its general use, and an open-source project is integrated in the Aerostack framework. Therefore, its technical details are fully accessible to developers and freely available to be used in the development of new aerial robotic systems.

关键词： Aerial robotics Control architecture Behavior-based control Executive system

Vision‐audio fusion SLAM in dynamic environments

在线全文

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1364-1373页

作者： Tianwei Zhang Huayan Zhang Xiaofei Li Shenzhen Institute of artificial Intelligence and robotics for Society ShenzhenChina Department of robotics Ritsumeikan UniversityShigaJapan Westlake University and Westlake Institute for Advanced Study HangzhouChina

Moving humans,agents,and subjects bring many challenges to robot self‐localisation and environment *** adapt to dynamic environments,SLAM researchers typically apply several deep learning image segmentation models to eliminate these moving ***,these moving obstacle segmentation methods cost too much computation resource for the onboard processing of mobile *** the current industrial environment,mobile robot collaboration scenario,the noise of mobile robots could be easily found by on‐board audio‐sensing processors and the direction of sound sources can be effectively acquired by sound source estimation algorithms,but the distance estimation of sound sources is ***,in the field of visual perception,the 3D structure information of the scene is relatively easy to obtain,but the recognition and segmentation of moving objects is more *** address these problems,a novel vision‐audio fusion method that combines sound source localisation methods with a visual SLAM scheme is proposed,thereby eliminating the effect of dynamic obstacles on multi‐agent *** heterogeneous robots experiments in different dynamic scenes indicate very stable self‐localisation and environment reconstruction performance of our method.

关键词： dynamic environment intelligent robots sensor fusion