检索结果-内蒙古大学图书馆

第32届中国控制与决策会议

作者： Naijun Liu Tao Lu Yinghao Cai Rui Wang Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology of the Chinese Academy of Sciences

Traditional programming method can achieve certain manipulation tasks with the assumption that robot environment is known and ***,with robots gradually applied in more domains,robots often encounter working scenes which are complicated,unpredictable,and *** overcome the limitation of traditional programming method,in this paper,we apply deep reinforcement learning(DRL) method to train robot agent to obtain skill *** policy trained with DRL on real-world robot is time-consuming and costly,we propose a novel and simple learning paradigm with the aim of training physical robot ***,our method train a virtual agent in an simulated environment to reach random target position from random initial ***,virtual agent trajectory sequence obtained with the trained policy,is transformed to real-world robot command with coordinate transformation to control robot performing reaching *** show that the proposed method can obtain self-adaptive reaching policy with low training cost,which is of great benefits for developing intelligent and robust robot manipulation skill system.

关键词： Robot reaching skill learning deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Color-sensitive person re-identification 28

Color-sensitive person re-identification

引用

28th International Joint Conference on Artificial Intelligence, IJCAI 2019

作者： Wang, Guan'an Yang, Yang Y. Cheng, Jian Wang, Jinqiao Hou, Zengguang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Beijing China

ISBN: (纸本)9780999241141

Recent deep Re-ID models mainly focus on learning high-level semantic features, while failing to explicitly explore color information which is one of the most important cues for person Re-ID model. In this paper, we propose a novel Color-Sensitive Re-ID to take full advantage of color information. On one hand, we train our model with real and fake images. By using the extra fake images, more color information can be exploited and it can avoid over-fitting during training. On the other hand, we also train our model with images of the same person with different colors. By doing so, features can be forced to focus on the color difference in regions. To generate fake images with specified colors, we propose a novel Color Translation GAN (CTGAN) to learn mappings between different clothing colors and preserve identity consistency among the same person with the clothing color. Extensive evaluations on two benchmark datasets show that our approach significantly outperforms state-of-the-art Re-ID models. © 2019 International Joint Conferences on Artificial Intelligence. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hindsight generative adversarial imitation learning

arXiv

引用

arXiv 2019年

作者： Liu, Naijun Lu, Tao Cai, Yinghao Li, Boyao Wang, Shuo State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Techology Chinese Academy of Sciences

Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising alternative is to train agent learning skills via imitation learning without expert demonstrations, which, to some extent, would extremely expand imitation learning areas. To achieve such expectation, in this paper, we propose Hindsight Generative Adversarial Imitation Learning (HGAIL) algorithm, with the aim of achieving imitation learning satisfying no need of demonstrations. Combining hindsight idea with the generative adversarial imitation learning (GAIL) framework, we realize implementing imitation learning successfully in cases of expert demonstration data are not available. Experiments show that the proposed method can train policies showing comparable performance to current imitation learning methods. Further more, HGAIL essentially endows curriculum learning mechanism which is critical for learning policies. Copyright © 2019, The Authors. All rights reserved.

关键词： Demonstrations

来源：评论

学校读者我要写书评

暂无评论

Parallel Ant Colony Optimization for the Electric Vehicle Routing Problem

Parallel Ant Colony Optimization for the Electric Vehicle Ro...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Michalis Mavrovouniotis Changhe Li Georgios Ellinas Marios Polycarpou KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus School of Automation and Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China University of Geosciences Wuhan China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

Parallelizing metaheuristics has become a common practice considering the computation power and resources available nowadays. The aim of parallelizing a metaheuristic is either to increase the quality of the generated output, given a fixed computation time, or to reduce the required time in generating an output. In this work, we parallelize one of the best-performing ant colony optimization (ACO) algorithms and apply it to the electric vehicle routing problem (EVRP). EVRP is more challenging than the conventional vehicle routing problem, as with the consideration of electric vehicles additional hard constraints arise within the EVRP due to their limited driving range (e.g., the consideration whether electric vehicles need to visit a charging station during their daily operation). The proposed parallel ACO algorithm with several colonies also uses a migration policy to allow communication between the different colonies. From the simulation studies it is shown that parallelizing ACO algorithms, both with and without a migration policy, is highly effective.

关键词： Electric vehicles Routing Batteries Technological innovation Vehicle routing Charging stations Optimization

来源：评论

学校读者我要写书评

暂无评论

Development of a Propeller with Undulating Fins and Its Characteristics

Development of a Propeller with Undulating Fins and Its Char...

引用

IEEE International Conference on Real-time Computing and Robotics (RCAR)

作者： Ruichen Ma Yu Wang Rui Wang Shuo Wang University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology

ISBN: (数字)9781728137261

ISBN: (纸本)9781728137278

This paper addresses some experiments about measurements of thrust and heave force generated by a modular designed biomimetic underwater propeller. The propeller has a ribbon fin that consists of twelve rays linked by a latex membrane. Different forms of waves can be generated by the propeller. A measurement platform is constructed to obtain the thrust and heave force generated by the waves along with the input power of the propeller. Three types of waves are performed on the platform, including sinusoidal waves, fusiform sinusoidal waves and inward counter-propagating sinusoidal waves. By changing the parameters of undulating waves, a total of three hundred series of experiments are implemented. The measurement results of three types of waves are analyzed and the differences among three types of waves are compared.

关键词： Force Propellers Force measurement control systems Standards Robots Current measurement

来源：评论

学校读者我要写书评

暂无评论

RASNet: Segmentation for tracking surgical instruments in surgical videos using refined attention segmentation network

arXiv

引用

arXiv 2019年

作者： Ni, Zhen-Liang Bian, Gui-Bin Xie, Xiao-Liang Hou, Zeng-Guang Zhou, Xiao-Hu Zhou, Yan-Jie State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China CAS Center for Excellence in Brain Science and Intelligence Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China

Segmentation for tracking surgical instruments plays an important role in robot-assisted surgery. Segmentation of surgical instruments contributes to capturing accurate spatial information for tracking. In this paper, a novel network, Refined Attention Segmentation Network, is proposed to simultaneously segment surgical instruments and identify their categories. The U-shape network which is popular in segmentation is used. Different from previous work, an attention module is adopted to help the network focus on key regions, which can improve the segmentation accuracy. To solve the class imbalance problem, the weighted sum of the cross entropy loss and the logarithm of the Jaccard index is used as loss function. Furthermore, transfer learning is adopted in our network. The encoder is pre-trained on ImageNet. The dataset from the MICCAI EndoVis Challenge 2017 is used to evaluate our network. Based on this dataset, our network achieves state-of-the-art performance 94.65% mean Dice and 90.33% mean IOU. Copyright © 2019, The Authors. All rights reserved.

关键词： Surgical equipment

来源：评论

学校读者我要写书评

暂无评论

The relationship between rising temperatures and malaria incidence in Hainan, China, from 1984 to 2010: a longitudinal cohort study

引用

The Lancet Planetary Health 2022年第4期6卷 e350-e358页

作者： Wang, Zengmiao Liu, Yonghong Li, Yapin Wang, Guangze Lourenço, José Kraemer, Moritz He, Qixin Cazelles, Bernard Li, Yidan Wang, Ruixue Gao, Dongqi Li, Yuchun Song, Wenjing Sun, Dingwei Dong, Lu Pybus, Oliver G Stenseth, Nils Chr Tian, Huaiyu State Key Laboratory of Remote Sensing Science Center for Global Change and Public Health College of Global Change and Earth System Science Beijing Normal University Beijing China Ministry of Education Key Laboratory for Biodiversity and Ecological Engineering College of Life Sciences Beijing Normal University Beijing China School of National Security and Emergency Management Beijing Normal University Beijing China Central Theater Center for Disease Control and Prevention of PLA Beijing China Hainan Center for Disease Control and Prevention Haikou China Department of Zoology University of Oxford UK Oxford United Kingdom Harvard Medical School Harvard University Boston MA United States Boston Children's Hospital Boston MA United States Department of Ecology and Evolution University of Chicago Chicago IL United States Institut de Biologie de l’École Normale Supérieure Unité Mixte de Recherche 8197 Centre National de la Recherche Scientifique et École Normale Supérieure Paris France Unité Mixte Internationnale 209 Mathematical and Computational Modeling of Complex Systems Institut de Recherche pour le Développement et Sorbonne Université Bondy France Centre for Ecological and Evolutionary Synthesis Department of Biosciences University of Oslo Oslo Norway Biosystems and Integrative Sciences Institute University of Lisbon Lisbon Portugal Department of Pathobiology and Population Science The Royal Veterinary College UK London United Kingdom

Background: The influence of rising global temperatures on malaria dynamics and distribution remains controversial, especially in central highland regions. We aimed to address this subject by studying the spatiotemporal heterogeneity of malaria and the effect of climate change on malaria transmission over 27 years in Hainan, an island province in China. Methods: For this longitudinal cohort study, we used a decades-long dataset of malaria incidence reports from Hainan, China, to investigate the pattern of malaria transmission in Hainan relative to temperature and the incidence at increasing altitudes. Climatic data were obtained from the local meteorological stations in Hainan during 1984–2010 and the WorldClim dataset. A temperature-dependent R₀ model and negative binomial generalised linear model were used to decipher the relationship between climate factors and malaria incidence in the tropical region. Findings: Over the past few decades, the annual peak incidence has appeared earlier in the central highland regions but later in low-altitude regions in Hainan, China. Results from the temperature-dependent model showed that these long-term changes of incidence peak timing are linked to rising temperatures (of about 1·5°C). Further, a 1°C increase corresponds to a change in cases of malaria from –5·6% (95% CI –4·5 to –6·6) to –9·2% (95% CI –7·6 to –10·9) from the northern plain regions to the central highland regions during the rainy season. In the dry season, the change in cases would be 4·6% (95% CI 3·7 to 5·5) to 11·9% (95% CI 9·8 to 14·2) from low-altitude areas to high-altitude areas. Interpretation: Our study empirically supports the idea that increasing temperatures can generate opposing effects on malaria dynamics for lowland and highland regions. This should be further investigated and incorporated into future modelling, disease burden calculations, and malaria control, with attention for central highland regions under climate change. Funding: S

关键词：

来源：评论

学校读者我要写书评

暂无评论

Raunet: Residual attention u-net for semantic segmentation of cataract surgical instruments

arXiv

引用

arXiv 2019年

作者： Ni, Zhen-Liang Bian, Gui-Bin Zhou, Xiao-Hu Hou, Zeng-Guang Xie, Xiao-Liang Wang, Chen Zhou, Yan-Jie Li, Rui-Qi Li, Zhen University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Cas Center for Excellence in Brain Science and Intelligence Technology Beijing100190 China

Semantic segmentation of surgical instruments plays a cru-cial role in robot-assisted surgery. However, accurate segmentation of cataract surgical instruments is still a challenge due to specular reec-tion and class imbalance issues. In this paper, an attention-guided net-work is proposed to segment the cataract surgical instrument. A new at-tention module is designed to learn discriminative features and address the specular reection issue. It captures global context and encodes se-mantic dependencies to emphasize key semantic features, boosting the feature representation. This attention module has very few parameters, which helps to save memory. Thus, it can be exibly plugged into other networks. Besides, a hybrid loss is introduced to train our network for addressing the class imbalance issue, which merges cross entropy and logarithms of Dice loss. A new dataset named Cata7 is constructed to evaluate our network. To the best of our knowledge, this is the first cataract surgical instrument dataset for semantic segmentation. Based on this dataset, RAUNet achieves state-of-the-art performance 97.71% mean Dice and 95.62% mean IOU. Copyright © 2019, The Authors. All rights reserved.

关键词： Surgical equipment

来源：评论

学校读者我要写书评

暂无评论

Robot assisted rehabilitation of the arm after stroke:prototype design and clinical evaluation

引用

Science China(Information Sciences) 2017年第7期60卷 252-258页

作者： Liang PENG Zeng-Guang HOU Long PENG Lincong LUO Weiqun WANG State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology

Robot assisted rehabilitation training is a promising tool for post-stroke patients’ recovery, and some new challenges are imposed on robot design, control, and clinical evaluation. This paper presents a novel upper limb rehabilitation robot that can provide safe and compliant force feedbacks to the patient for the benefits of its stiff and low-inertia parallel structure, highly backdrivable capstan-cable transmission, and impedance control method in the workspace. The "assist-as-needed"(AAN) clinical training principle is implemented through the "virtual tunnel" force field design, the "assistance threshold" strategy, as well as the virtual environment training games, and preliminary clinical results show its effectiveness for motor relearning for both acute and chronic stroke patients, especially for coordinated movements of shoulder and elbow.

关键词： rehabilitation robot passive training active training force feedback impedance control

来源：评论

学校读者我要写书评

暂无评论

Back Cover: PD-L1 Aptamer-Functionalized Metal–Organic Framework Nanoparticles for Robust Photo-Immunotherapy against Cancer with Enhanced Safety (Angew. Chem. Int. Ed. 5/2023)

引用

Angewandte Chemie International Edition 2023年第5期62卷

作者： Dr. Jingfang Zhang Dr. Wenzhe Li Dr. Yafei Qi Dr. Guorong Wang Prof. Lele Li Prof. Zhengyu Jin Prof. Jie Tian Prof. Yang Du Beijing Key Laboratory for Bioengineering and Sensing Technology School of Chemistry and Biological Engineering University of Science and Technology Beijing Beijing 100083 China CAS Key Laboratory for Biomedical Effects of Nanomaterials and Nanosafety and CAS Center for Excellence in Nanoscience National Center for Nanoscience and Technology Beijing 100190 China State Key Laboratory of Natural and Biomimetic Drugs School of Pharmaceutical Sciences Peking University Beijing 100191 China CAS Key Laboratory of Molecular Imaging Beijing Key Laboratory of Molecular Imaging the State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Department of Radiology Peking Union Medical College Hospital Peking Union Medical College and Chinese Academy of Medical Sciences Beijing 100730 China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine School of Medicine Beihang University Beijing 100191 China

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：