检索结果-南通市图书馆

Position-aware pushing and grasping synergy with deep reinforcement learning in clutter

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第3期9卷 738-755页

作者： Min Zhao Guoyu Zuo Shuangyue Yu Daoxiong Gong Zihao Wang Ouattara Sie Intelligent Robotics laboratory Faculty of Information TechnologyBeijing University of TechnologyBeijingChina Beijing Key laboratory of Computational Intelligence and Intelligent systems BeijingChina laboratory of Biomechatronics and Intelligent Robotics(BIRO) Department of Mechanical and Aerospace EngineeringNorth Carolina State UniversityRaleighNorth CarolinaUSA

The positional information of objects is crucial to enable robots to perform grasping and pushing manipulations in *** effectively perform grasping and pushing manipu-lations,robots need to perceive the position information of objects,including the co-ordinates and spatial relationship between objects(e.g.,proximity,adjacency).The authors propose an end-to-end position-aware deep Q-learning framework to achieve efficient collaborative pushing and grasping in ***,a pair of conjugate pushing and grasping attention modules are proposed to capture the position information of objects and generate high-quality affordance maps of operating positions with features of pushing and grasping *** addition,the authors propose an object isolation metric and clutter metric based on instance segmentation to measure the spatial re-lationships between objects in cluttered *** further enhance the perception capacity of position information of the objects,the authors associate the change in the object isolation metric and clutter metric in cluttered environment before and after performing the action with reward function.A series of experiments are carried out in simulation and real-world which indicate that the method improves sample efficiency,task completion rate,grasping success rate and action efficiency compared to state-of-the-art end-to-end *** that the authors’system can be robustly applied to real-world use and extended to novel *** material is available at https://***/NhG\_k5v3NnM}{https://***/NhG\_k5v3NnM.

关键词： deep learning deep neural networks intelligent robots

Quantum key distribution over a mimicked dynamic-scattering channel

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

Science China(information Sciences) 2024年第4期67卷 323-330页

作者： Qi-Hang LU Fang-Xiang WANG Wei CHEN Hai-Yang FU Yin-Jie LU Shuang WANG De-Yong HE Zhen-Qiang YIN Guang-Can GUO Zheng-Fu HAN CAS Key laboratory of Quantum information University of Science and Technology of China CAS Center for Excellence in Quantum information and Quantum Physics University of Science and Technology of China Hefei National laboratory University of Science and Technology of China

Free-space quantum key distribution(QKD) plays an important role in the global quantum network. However, free space channels suffer from the atmospheric turbulence and scattering effects of haze,fog, and dust, which significantly weaken the performance of QKD or even block the secure quantum ***, we prove the performance of QKD over a dynamic scattering channel can be enhanced significantly using a fast wavefront shaping technique. The system achieves on average 10-dB enhancement of quantum transmission efficiency and establishes a secure quantum link for QKD. Our work demonstrates the feasibility of QKD through free-space dynamic scattering channels and enhances the deployment capability of complex-channel QKD system.

关键词： quantum key distribution free space channel channel turbulence channel scattering wavefront shaping

On the upper bounds of (1,0)-super solutions for the regular balanced random (k,2s)-SAT problem

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第4期18卷 139-146页

作者： Yongping WANG Daoyun XU Jincheng ZHOU School of information Guizhou University of Finance and EconomicsGuiyang 550025China College of Computer Science and Technology Guizhou UniversityGuiyang 550025China School of Computer and information Qiannan Normal University for NationalitiesDuyun 558000China Key laboratory of Complex systems and Intelligent Optimization of Guizhou Province Duyun 558000China

This paper explores the conditions which make a regular balancedrandom(k,2s)-CNFformula(1,O)-unsatisfiable with high *** conditions also make a random instance of the regular balanced(k-1,2(k-1)s)-SAT problem unsatisfiable with high probability,where the instance obeys a distribution which differs from the distribution obeyed by a regular balanced random(k-1,2(k-1)s)-CNF *** F be a regular balanced random(k,2s)-CNF formula where k≥3,then there exists a number so such that F is(1,O)-unsatisfiable with high probability if s>so.A numerical solution of the number so when k e(5,6,...,14)is given to conduct simulated *** simulated experiments verify the theoretical ***,the experiments also suggest that F is(1,O)-satisfiable with high probability if s is less than a certain value.

关键词： regular balanced random(k,2s)-SAT problem (1,0)-super solution upper bound

Mutual information oriented deep skill chaining for multi‐agent reinforcement learning

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

CAAI Transactions on Intelligence Technology 2024年第4期9卷 1014-1030页

作者： Zaipeng Xie Cheng Ji Chentai Qiao WenZhan Song Zewen Li Yufeng Zhang Yujing Zhang Key laboratory of Water Big Data Technology of Ministry of Water Resources Hohai UniversityNanjingChina College of Computer and information Hohai UniversityNanjingChina Center for Cyber‐Physical systems University of GeorgiaAthensGeorgiaUSA information Networking Institute Carnegie Mellon UniversityPittsburghPennsylvaniaUSA Department of Electrical and systems Engineering University of PennsylvaniaPhiladelphiaPennsylvaniaUSA

Multi‐agent reinforcement learning relies on reward signals to guide the policy networks of individual ***,in high‐dimensional continuous spaces,the non‐stationary environment can provide outdated experiences that hinder convergence,resulting in ineffective training performance for multi‐agent *** tackle this issue,a novel reinforcement learning scheme,Mutual information Oriented Deep Skill Chaining(MioDSC),is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration *** rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment *** addition,MioDSC can generate cooperative policies using the options framework,allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi‐agent *** was evaluated in the multi‐agent particle environment and the StarCraft multi‐agent challenge at varying difficulty *** experimental results demonstrate that MioDSC outperforms state‐of‐the‐art methods and is robust across various multi‐agent system tasks with high stability.

关键词： artificial intelligence techniques decision making intelligent multi‐agent systems

Suppression of modulation-induced polarization error in spliceless open-loop fiber optic gyroscope [Invited]

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

Chinese Optics Letters 2024年第7期22卷 6-11页

作者： Lin Chen Peitong He Biqiang Jiang Jianlin Zhao Key laboratory of Light Field Manipulation and information Acquisition and Shaanxi Key Laboratory of Optical Information TechnologySchool of Physical Science and TechnologyNorthwestern Polytechnical UniversityXi’an 710129China Zhejiang Lab Hangzhou 311100China

The suppression of polarization cross talk in lead zirconate titanate phase modulators as a key error source has been challenging for open-loop fiber optic gyroscopes(FOGs).We developed a polarization-diversity optical frequency domain reflectometry(OFDR)to measure the distributed modulation polarization error in the *** error contributes 8×10^(−6) rad to FOG’s bias *** a UV-fabricated in-fiberλ/4 wave plate and polarization-mode converter with fiber taper technology,the modulation error has been suppressed by 15 dB in assembled *** approach reduced error with temperature from 25°/h to 0.7°/h,meeting the requirements of control-level gyroscopes with bias errors less than 1°/h.

关键词： fiber optic gyroscope inline wave plate optical frequency domain reflectometry polarization-mode converter.

Long-term variation of Arctic Sudden Stratospheric Warmings(SSW) and potential causes

在线全文

学校读者我要写书评

暂无评论

Earth and Planetary Physics 2024年第5期8卷 742-752页

作者： QingRan Li ShaoDong Zhang KaiMing Huang ChunMing Huang Yun Gong WenTao Tang Zheng Ma School of Electronic information Wuhan University Guizhou Normal University Key laboratory of Geospace Environment and Geodesy Ministry of Education State Key laboratory of information Engineering in Surveying Mapping and Remote Sensing School of Electronic information Engineering Jingchu University of Technology

Utilizing the European Centre for Medium-Range Weather Forecast(ECMWF) Reanalysis v5(ERA5), for the first time, we have confirmed close links among Sudden Stratospheric Warmings(SSWs) in the Northern Hemisphere(NH), the polar vortices, and stratospheric Planetary Waves(PWs) by analyzing and comparing their trends. Interestingly, within overall increasing trends, the duration and strength of SSWs exhibit increasing and decreasing trends before and after the winter of 2002, respectively. To reveal possible physical mechanisms driving these trends, we analyzed the long-term trends of the winter(from December to February) polar vortices and of stratospheric PWs with zonal wave number 1. Notably, our results show that in all three time periods(the entire period of 41winters, 1980 to 2020, and the two subperiods — 1980-2002 and 2002-2020) enhancing SSWs were always accompanied by weakening winter polar vortices and strengthening polar PWs like Stationary Planetary Waves(SPWs) and 16-day waves, and vice versa. This is the first proof, based on ERA5 long-term trend data, that weakening polar vortices and enhancing stratospheric PWs(especially SPWs) could cause an increase in SSWs.

关键词： sudden stratospheric warmings stationary planetary waves 16-day waves polar vortrices long-term trend correlation coefficient

LFM Radar Source Passive Localization Algorithm Based on Range Migration

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 Beijing Institute of Technology 2024年第2期33卷 130-140页

作者： Dandan Li Deyi Wang Hao Huan Beijing Key laboratory of Fractional Signals and systems School of Information and ElectronicsBeijing Institute of TechnologyBeijing 100081China Beijing Aerospace Automatic Control Institute Beijing 100854China

Traditional single-satellite passive localization algorithms are influenced by frequency and angle measurement accuracies,resulting in error estimation of emitter position on the order of ***,a single-satellite localization algorithm based on passive synthetic aper-ture(PSA)was introduced,enabling high-precision ***,its estimation of azimuth and range distance is considerably affected by the residual frequency offset(RFO)of uncoopera-tive system ***,it requires data containing a satellite flying over the radia-tion source for RFO *** estimating the RFO,an accurate estimation of azimuth and range distance can be carried out,which is difficult to achieve in practical *** LFM radar source passive localization algorithm based on range migration is proposed to address the dif-ficulty in estimating frequency *** algorithm first provides a rough estimate of the pulse repetition time(PRT).It processes intercepted signals through range compression,range interpola-tion,and polynomial fitting to obtain range migration ***,it uses the changing information of range migration and an accurate PRT to formulate a system of nonlinear equations,obtaining the emitter position and a more accurate PRT through a two-step localization *** offset only induces a fixed offset in range migration,which does not affect the changing *** algorithm can also achieve high-precision localization in squint ***,the effectiveness of this algorithm is verified through simulations.

关键词： passive localization range migration residual frequency offset

Lens-free wavefront shaping method for a diffuse non-lineof-sight link in visible light communication

在线全文

学校读者我要写书评

暂无评论

Chinese Optics Letters 2024年第2期22卷 81-87页

作者：陈超旭周晓萌李子薇沈超张俊文施剑阳迟楠 Key laboratory for information Science of Electromagnetic Waves(MoE) Fudan UniversityShanghai 200433China Peng Cheng laboratory Shenzhen 518038China

In this Letter,we propose and experimentally demonstrate a lens-free wavefront shaping method that utilizes synchronized signal block beam alignment and a genetic algorithm(SSBGA)for a diffuse non-line-of-sight(NLOS)visible light communication(VLC)*** proposed method effectively controls the position and mobility of visible light beams by partitioning spatial light modulator pixels and manipulating beams to converge at distinct spatial positions,thereby enhancing wavefront shaping efficiency,which achieves a significant 23.9 dB optical power enhancement at+2 mm offset,surpassing the lens-based continuous sequence(CS)scheme by 21.7 ***+40°angle,the improvement reaches up to 11.8 dB and 16.8 dB compared to the results with and without lens-based CS,respectively.A maximum rate of 5.16 Gbps is successfully achieved using bit-power loading discrete multi-tone(DMT)modulation and the proposed SSBGA in an NLOS VLC system,which outperforms the lens-based CS by 1.07 Gbps and obtains a power saving of 55.6%during the transmission at4 *** the best of our knowledge,this is the first time that high-speed communication has been realized in an NLOS VLC system without a lens.

关键词： non-line-of-sight lens-free wavefront shaping visible light communication

Thickness dependence of superconductivity in layered GeP_(5)

在线全文

学校读者我要写书评

暂无评论

Rare Metals 2024年第3期43卷 1323-1328页

作者： Lin Wu Ke-Meng Yang Wei Gan Rui-Chun Xiao Ya-Jie Dai Xi Tang Hong Lin Hui Han Hui Li information Materials and Intelligent Sensing laboratory of Anhui Province Institute of Physical Science and Information TechnologyAnhui UniversityHefei230601China

Understanding the relationship between dimensionality and superconductivity has attracted substantial research *** this work,we report the effective modulation of superconductivity in GeP_(5)through *** superconducting phase transition temperature improves by~10%as the thickness of GeP_(5)decreases from bulk to~96 nm,behaving as a unique negative relationship between the superconducting phase transition temperatureand thickness.

关键词： superconductivity dimensionality