检索结果-南通市图书馆

Computational Visual Media 2024年第1期10卷 27-43页

作者： Mingye Xu Zhipeng Zhou Yali Wang Yu Qiao Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine intelligence-Synergy Systems Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518000China University of Chinese Academy of Sciences Beijing065001China Shanghai AI Laboratory Shanghai200001China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for SocietyShenzhen518000China Alibaba DAMO Academy Hangzhou242332China

Robustness and generalization are two challenging problems for learning point cloud *** tackle these problems,we first design a novel geometry coding model,which can effectively use an invariant eigengraph to group points with similar geometric information,even when such points are far from each *** also introduce a large-scale point cloud dataset,*** consists of 184 categories and 51,915 synthetic objects,which brings new challenges for point cloud classification,and provides a new benchmark to assess point cloud cross-domain ***,we perform extensive experiments on point cloud classification,using ModelNet40,ScanObjectNN,and our PCNet184,and segmentation,using ShapeNetPart and *** method achieves comparable performance to state-of-the-art methods on these datasets,for both supervised and unsupervised *** and our dataset are available at https://***/MingyeXu/PCNet184.

关键词： geometry coding self-supervised learning point cloud classification segmentation 3D analysis

A deep convolutional neural network for diabetic retinopathy detection via mining local and long-range dependence

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 153-166页

作者： Xiaoling Luo Wei Wang Yong Xu Zhihui Lai Xiaopeng Jin Bob Zhang David Zhang shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of TechnologyShenzhenChina Peng Cheng Laboratory ShenzhenChina shenzhen institute of artificial intelligence and robotics for society ShenzhenChina College of Big Data and Internet Shenzhen Technology UniversityShenzhenChina The Department of Computer and Information Science University of MacaoMacaoMacaoChina The Chinese University of Hong Kong(shenzhen) ShenzhenChina

Diabetic retinopathy(DR),the main cause of irreversible blindness,is one of the most common complications of *** present,deep convolutional neural networks have achieved promising performance in automatic DR detection *** convolution operation of methods is a local cross-correlation operation,whose receptive field de-termines the size of the local neighbourhood for ***,for retinal fundus photographs,there is not only the local information but also long-distance dependence between the lesion features(*** and exudates)scattered throughout the whole *** proposed method incorporates correlations between long-range patches into the deep learning framework to improve DR ***-wise re-lationships are used to enhance the local patch features since lesions of DR usually appear as *** Long-Range unit in the proposed network with a residual structure can be flexibly embedded into other trained *** experimental results demon-strate that the proposed approach can achieve higher accuracy than existing state-of-the-art models on Messidor and EyePACS datasets.

关键词： image classification medical image processing pattern recognition

Grasp Detection with Hierarchical Multi-Scale Feature Fusion and Inverted Shuffle Residual

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第1期29卷 244-256页

作者： Wenjie Geng Zhiqiang Cao Peiyu Guan Fengshui Jing Min Tan Junzhi Yu State Key Laboratory of Multimodal artificial intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of artificial intelligence University of Chinese Academy of SciencesBeijing 100049China Department of Advanced Manufacturing and robotics College of EngineeringPeking UniversityBeijing 100871China

Grasp detection plays a critical role for robot *** pixel-wise grasp detection networks with encoder-decoder structure receive much attention due to good accuracy and ***,they usually transmit the high-level feature in the encoder to the decoder,and low-level features are *** is noted that low-level features contain abundant detail information,and how to fully exploit low-level features remains ***,the channel information in high-level feature is also not well ***,the performance of grasp detection is *** solve these problems,we propose a grasp detection network with hierarchical multi-scale feature fusion and inverted shuffle *** low-level and high-level features in the encoder are firstly fused by the designed skip connections with attention module,and the fused information is then propagated to corresponding layers of the decoder for in-depth feature *** a hierarchical fusion guarantees the quality of grasp ***,an inverted shuffle residual module is created,where the high-level feature from encoder is split in channel and the resultant split features are processed in their respective *** such differentiation processing,more high-dimensional channel information is kept,which enhances the representation ability of the ***,an information enhancement module is added before the encoder to reinforce input *** proposed method attains 98.9%and 97.8%in image-wise and object-wise accuracy on the Cornell grasping dataset,respectively,and the experimental results verify the effectiveness of the method.

关键词： grasp detection hierarchical multi-scale feature fusion skip connections with attention inverted shuffle residual

Human-robot object handover:Recent progress and future direction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Biomimetic intelligence & robotics 2024年第1期4卷 1-13页

作者： Haonan Duan Yifan Yang Daheng Li Peng Wang institute of Automation Chinese Academy of SciencesBeijing 100190China School of artificial intelligence University of Chinese Academy of SciencesBeijing 100049China Centre for artificial intelligence and robotics Hong Kong Institute of Science and InnovationChinese Academy of SciencesHong Kong 999077China

Human-robot object handover is one of the most primitive and crucial capabilities in human-robot *** is of great significance to promote robots to truly enter human production and life scenarios and serve human in numerous *** progressions in the field of human-robot object handover have been made by *** article reviews the recent literature on human-robot object *** this end,we summarize the results from multiple dimensions,from the role played by the robot(receiver or giver),to the end-effector of the robot(parallel-jaw gripper or multi-finger hand),to the robot abilities(grasp strategy or motion planning).We also implement a human-robot object handover system for anthropomorphic hand to verify human-robot object handover *** review aims to provide researchers and developers with a guideline for designing human-robot object handover methods.

关键词： Human-robot interactions Object handover

Key-Part Attention Retrieval for Robotic Object Recognition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第3期29卷 644-655页

作者： Jierui Liu Zhiqiang Cao Yingbo Tang State KeyLaboratory of Multimodal artificial intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of artificial intelligence University of Chinese Academy of SciencesBeijing 100049China

The ability to recognize novel objects with a few visual samples is critical in the robotic *** methods mainly concern the recognition of inter-category objects,however,the object recognition fromdifferent sub-classes within the same category remains challenging due to their similar *** thispaper,we propose a key-part attention retrieval solution to distinguish novel objects of different sub-classesaccording to a few samples without ***,an object encoder,including convolutional neuralnetwork with attention and key-part aggregation,is designed to generate object attention map and extract theobject-level embedding,where object attention map from the middle stage of the backbone is used to guide thekey-part ***,to overcome the non-differentiability drawback of key-part attention,the objectencoder is trained in a two-step scheme,and a more stable object-level embedding is *** this basis,the potential objects are located from a scene image by mining connected domains of the attention *** the embedding of each potential object and embeddings from support data,the recognition of thepotential objects is *** effectiveness of the proposed method is verified by experiments.

关键词： key-part attention retrieval robotic object recognition

Efficient nonnegative tensor decomposition using alternating direction proximal method of multipliers

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 Journal of Electronics 2024年

作者： Deqing WANG Guoqiang HU State Key Laboratory of robotics Shenyang Institute of Automation Chinese Academy of Sciences institutes for robotics and Intelligent Manufacturing Chinese Academy of Sciences Key Laboratory of Marine robotics College of artificial intelligence Dalian Maritime University

Nonnegative CANDECOMP/PARAFAC（NCP） tensor decomposition is a powerful tool for multiway signal processing. The optimization algorithm alternating direction method of multipliers（ADMM） has become increasingly popular for solving tensor decomposition problems in the block coordinate descent framework. However,the ADMM-based NCP suffers from rank deficiency and slow convergence for some large-scale and highly sparse tensor data. The proximal algorithm is preferred to enhance optimization algorithms and improve convergence properties. In this study, we propose a novel NCP algorithm using the alternating direction proximal method of multipliers（ADPMM） that consists of the proximal algorithm. The proposed NCP algorithm can guarantee convergence and overcome the rank deficiency. Moreover, we implement the proposed NCP using an inexact scheme that alternatively optimizes the subproblems. Each subproblem is optimized by a finite number of inner iterations yielding fast computation speed. Our NCP algorithm is a hybrid of alternating optimization and ADPMM and is named *** experimental results on synthetic and real-world tensors demonstrate the effectiveness and efficiency of our proposed algorithm.

关键词：

Energy-efficient buffer and service rate allocation in manufacturing systems using hybrid machine learning and evolutionary algorithms

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Advances in Manufacturing 2024年第2期12卷 227-251页

作者： Si-Xiao Gao Hui Liu Jun Ota Key Laboratory of Traffic Safety on Track of Ministry of Education Institute of Artificial Intelligence and Robotics(IAIR)School of Traffic and Transportation EngineeringCentral South UniversityChangsha410075People’s Republic of China Research into Artifacts Center for Engineering School of EngineeringThe University of TokyoTokyoJapan

Currently,simultaneous buffer and service rate allocation is a topic of interest in the optimization of manufacturing *** allocation problems have been solved previously to satisfy economic requirements;however,owing to the progress of green manufacturing,energy conservation and environmental protection have become increasingly ***,an energy-efficient approach is developed to maximize the throughput and minimize the energy consumption of manufacturing systems,subject to the total buffer capacity,total service rate,and predefined energy *** energy-efficient approach integrates the simulated annealing-non-dominated sorting genetic algorithm-II with the honey badger algorithm-histogram-based gradient boosting regression *** former algorithm searches for Pareto-optimal solutions of sufficient *** latter algorithm builds prediction models to rapidly calculate the throughput,energy consumption,and energy *** examples show that the proposed hybrid approach can achieve a better solution quality compared with previously reported ***,the prediction models can rapidly evaluate manufacturing systems with sufficient *** study benefits the multi-objective optimization of green manufacturing systems.

关键词： Energy-efficient allocation Multi-objective optimization Energy efficiency Energy consumption Machine learning

Atten-ganCV:An End-to-end Close-coupled Image-generating Cross-view Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Atten-ganCV:An End-to-end Close-coupled Image-generating Cro...

Correcting of the unexpected localization measurement for indoor automatic mobile robot transportation based on a neural network

2023中国自动化大会

作者： Wenjie Song Jianru Xue institute of artificial intelligence and robotics Xi'an Jiaotong University

Cross-view geo-localization aims to match the query input ground-view image and the aerial-view images in the reference dataset one by one to determine the ground image's geographic location. This research is extremely challenging because the variation of the observation angle between cross-view images brings about great geometric appearance differences between image pairs. Nowadays, the introduction of generative networks into matching models has been shown to work well on the CVUSA(Cross-View USA) dataset, and the latest models clarify the paradigm of end-to-end generative cross-view image matching methods. However, this result relies on an assumption on the dataset: for all query input ground images, there must exist a reference aerial image that is exactly centered on the location of that image, which is clearly not consistent with real-world application scenarios;and the performance of state-of-the-art generative models degrades significantly when departing from this assumption of center alignment. To address this problem, this paper provides a generative model(atten-ganCV) for non-centeraligned datasets. This model feeds the query ground image directly into a generative adversarial network to obtain a generated aerial view image, where the generator atten-UNet innovatively introduces an attention mechanism. Then, model matches the synthesized image with the real aerial image in the reference dataset one by one, and finally obtains the matching result with the highest similarity, thus determining the geographic location of the query input. The model is tested on both the center-aligned CVUSA dataset and the non-center-aligned VIGOR(Cross-view Image Geo-localization beyond One-to-one Retrieval) dataset. In the VIGOR dataset, this model achieves approximately the same accuracy as the state-of-the-art model with 3 times the inference speed.

关键词：

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Transportation Safety and Environment 2024年第2期6卷 24-35页

作者： Jiahao Huang Steffen Jung inger Hui Liu Kerstin Thurow Center for Life Science Automation(CELISCA) University of RostockRostock 18119Germany institute of Automation University of RostockRostock 18119Germany institute of artificial intelligence&robotics(IAIR) School of Traffic&Transportation EngineeringCentral South UniversityChangsha 410075HunanChina

The increasing use of mobile robots in laboratory settings has led to a higher degree of laboratory ***,when mobile robots move in laboratory environments,mechanical errors,environmental disturbances and signal interruptions are *** can compromise the accuracy of the robot’s localization,which is crucial for the safety of staff,robots and the laboratory.A novel time-series predicting model based on the data processing method is proposed to handle the unexpected localization measurement of mobile robots in laboratory *** proposed model serves as an auxiliary localization system that can accurately correct unexpected localization errors by relying solely on the historical data of mobile *** experimental results demonstrate the effectiveness of this proposed method.

关键词： mobile robots laboratory automation indoor localization neural network

Reinforcement Learning Navigation for Robots Based on Hippocampus Episode Cognition

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2024年第1期21卷 288-302页

作者： Jinsheng Yuan Wei Guo Zhiyuan Hou Fusheng Zha Mantian Li Pengfei Wang Lining Sun State Key Laboratory of robotics and System Harbin Institute of Technology(HIT)Harbin 150001China shenzhen Academy of Aerospace Technology Shenzhen 518057China School of Mechanical and Electrical Engineering Lanzhou University of TechnologyLanzhou 730050China

artificial intelligence is currently achieving impressive success in all ***,autonomous navigation remains a major challenge for *** learning is used for target navigation to simulate the interaction between the brain and the environment at the behavioral level,but the artificial Neural Network trained by reinforcement learning cannot match the autonomous mobility of humans and *** hippocampus–striatum circuits are considered as key circuits for target navigation planning and *** paper aims to construct a bionic navigation model of reinforcement learning corresponding to the nervous system to improve the autonomous navigation performance of the *** ventral striatum is considered to be the behavioral evaluation region,and the hippocampal–striatum circuit constitutes the position–reward *** this paper,a set of episode cognition and reinforcement learning system simulating the mechanism of hippocampus and ventral striatum is constructed,which is used to provide target guidance for the robot to perform autonomous *** with traditional methods,this system reflects the high efficiency of learning and better Environmental *** research is an exploration of the intersection and fusion of artificial intelligence and neuroscience,which is conducive to the development of artificial intelligence and the understanding of the nervous system.

关键词： Episode cognition Reinforcement learning Hippocampus Robot navigation