检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Alberto Bacchin Leonardo Barcellona Matteo Terreran Stefano Ghidoni Emanuele Menegatti Takuya Kiyokawa Department of Information Engineering Intelligent Autonomous System Lab University of Padova Padua Italy Department of Systems Innovation Graduate School of Engineering Science Osaka University Toyonaka Osaka Japan

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Robotic waste sorting poses significant challenges in both perception and manipulation, given the extreme variability of objects that should be recognized on a cluttered conveyor belt. While deep learning has proven effective in solving complex tasks, the necessity for extensive data collection and labeling limits its applicability in real-world scenarios like waste sorting. To tackle this issue, we introduce a data augmentation method based on a novel GAN architecture called wasteGAN. The proposed method allows to increase the performance of semantic segmentation models, starting from a very limited bunch of labeled examples, such as few as 100. The key innovations of wasteGAN include a novel loss function, a novel activation function, and a larger generator block. Overall, such innovations helps the network to learn from limited number of examples and synthesize data that better mirrors real-world distributions. We then leverage the higher-quality segmentation masks predicted from models trained on the wasteGAN synthetic data to compute semantic-aware grasp poses, enabling a robotic arm to effectively recognizing contaminants and separating waste in a real-world scenario. Through comprehensive evaluation encompassing dataset-based assessments and real-world experiments, our methodology demonstrated promising potential for robotic waste sorting, yielding performance gains of up to 5.8% in picking contaminants. The project page is available at https://***/bach05/***.

关键词： Training Technological innovation Computational modeling Semantic segmentation Grasping Computer architecture Data augmentation Generative adversarial networks Robots Sorting

来源：评论

学校读者我要写书评

暂无评论

Source Data-less Efficient Transfer Learning Based on Layer Importance Index Using Activated Feature Map

Source Data-less Efficient Transfer Learning Based on Layer ...

引用

2022 IEEE International Conference on systems, Man, and Cybernetics, SMC 2022

作者： Kanda, Daigo Nobuhara, Hajime University of Tsukuba Degree Programs in Systems and Information Engineering Graduate School of Science and Technology Tsukuba Japan University of Tsukuba Department of Intelligent Interaction Technologies Tsukuba Japan

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Transfer learning performance in convolutional neural networks (CNNs) depends on the selection of retraining and fixation layers. The conventional method requires source data, which increases the cost proportionally to the data's size. To solve this problem, this study proposed a source-data-less layer importance index that indicates the layers that should be retrained. Consequently, using the maximum activated feature maps generated by the model itself instead of the activated feature maps, the proposed method eliminates the need for any source data. Further, the experimental results on the five image classification datasets demonstrated a strong positive correlation of the proposed layer importance index compared with the conventional method. In addition, the transfer learning method using the layer importance index significantly improved the average classification accuracy compared with fine-tuning. CNNs have become indispensable owing to various applications, and thus, this study aimed at further enhancing its capabilities is relevant to the present and coming times. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Computer vision for road imaging and pothole detection:a state-of-the-art review of systems and algorithms

引用

Transportation Safety and Environment 2022年第4期4卷 3-18页

作者： Nachuan Ma Jiahe Fan Wenshuo Wang JinWu Yu Jiang Lihua Xie Rui Fan Department of Control Science and Engineering Frontiers Science Center for Intelligent Autonomous Systemsand State Key Laboratory of Intelligent Autonomous SystemsTongji UniversityShanghai 201804P.R.China Department of Civil Engineering McGill UniversityMontréalQC H3A 0C3Canada Department of Electronics and Computer Engineering the Hong Kong University of Science and TechnologyHong Kong SAR 999077P.R.China CTO Office ClearMotion Inc.BillericaMA 01821USA School of Electrical and Electronic Engineering Nanyang Technological University50 Nanyang Avenue639798Singapore

Computer vision algorithms have been utilized for 3-D road imaging and pothole detection for over two ***,there is a lack of systematic survey articles on state-of-the-art(SoTA)computer vision techniques,especially deep learningmodels,developed to tackle these *** article first introduces the sensing systems employed for 2-D and 3-D road data acquisition,including camera(s),laser scanners and Microsoft *** then comprehensively reviews the SoTA computer vision algorithms,including(1)classical 2-D image processing,(2)3-D point cloud modelling and segmentation and(3)machine/deep learning,developed for road pothole *** article also discusses the existing challenges and future development trends of computer vision-based road pothole detection approaches:classical 2-D image processing-based and 3-D point cloud modelling and segmentation-based approaches have already become history;and convolutional neural networks(CNNs)have demonstrated compelling road pothole detection results and are promising to break the bottleneck with future advances in self/un-supervised learning for multi-modal semantic *** believe that this survey can serve as practical guidance for developing the next-generation road condition assessment systems.

关键词： Computer vision road imaging pothole detection deep learning image processing point cloud modelling convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

WasteGAN: Data Augmentation for Robotic Waste Sorting through Generative Adversarial Networks

arXiv

引用

arXiv 2024年

作者： Bacchin, Alberto Barcellona, Leonardo Terreran, Matteo Ghidoni, Stefano Menegatti, Emanuele Kiyokawa, Takuya Intelligent Autonomous System Lab Department of Information Engineering University of Padova Padua Italy Department of Systems Innovation Graduate School of Engineering Science Osaka University Osaka Toyonaka Japan

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Multi-Player Potential Game Approach for Sensor Network Localization with Noisy Measurements

A Multi-Player Potential Game Approach for Sensor Network Lo...

引用

IEEE Conference on Decision and control

作者： Gehui Xu Guanpu Chen Baris Fidan Yiguang Hong Hongsheng Qi Thomas Parisini Karl H. Johansson Department of Electrical and Electronic Engineering Imperial College London London UK Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Mechanical and Mechatronics Engineering University of Waterloo Waterloo ON Canada Department of Control Science and Engineering Tongji University shanghai China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai China Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing China Department of Electronic Systems Aalborg University Denmark Department of Engineering and Architecture University of Trieste Italy

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

Sensor network localization (SNL) is a challenging problem due to its inherent non-convexity and the effects of noise in inter-node ranging measurements and anchor node position. We formulate a non-convex SNL problem as a multiplayer non-convex potential game and investigate the existence and uniqueness of a Nash equilibrium (NE) in both the ideal setting without measurement noise and the practical setting with measurement noise. We first show that the NE exists and is unique in the noiseless case, and corresponds to the precise network localization. Then, we study the SNL for the case with errors affecting the anchor node position and the inter-node distance measurements. Specifically, we establish that in case these errors are sufficiently small, the NE exists and is unique. It is shown that the NE is an approximate solution to the SNL problem, and that the position errors can be quantified accordingly. Based on these findings, we apply the results to case studies involving only inter-node distance measurement errors and only anchor position information inaccuracies.

关键词： Location awareness Noise Games Position measurement Nash equilibrium Distance measurement Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Diff-control: A Stateful Diffusion-based Policy for Imitation Learning

Diff-Control: A Stateful Diffusion-based Policy for Imitatio...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Xiao Liu Yifan Zhou Fabian Weigend Shubham Sonawani Shuhei Ikemoto Heni Ben Amor Computing and Augmented Intelligence Arizona State University USA Department of Human Intelligence Systems Graduate School of Life Science and Systems Engineering Kyushu Institute of Technology

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

While imitation learning provides a simple and effective framework for policy learning, acquiring consistent action during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action representation at data curation stage or altering the model itself, both of which do not fully address the scalability of consistent action generation. To overcome this limitation, we introduce the Diff-control policy, which utilizes a diffusion-based model to learn action representation from a state-space modeling viewpoint. We demonstrate that diffusion-based policies can acquire statefulness through a Bayesian formulation facilitated by controlNet, leading to improved robustness and success rates. Our experimental results demonstrate the significance of incorporating action statefulness in policy learning, where Diff-control shows improved performance across various tasks. Specifically, Diff-control achieves an average success rate of 72% and 84% on stateful and dynamic tasks, respectively. Notably, Diff-control also shows consistent performance in the presence of perturbations, outperforming other state-of-the-art methods that falter under similar conditions. Project page: https://***/

关键词： Training Torque Imitation learning Scalability Perturbation methods Process control Sensor systems and applications Robustness Intelligent sensors Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Methane and nitrous oxide emissions from municipal wastewater treatment plants in China:A plant-level and technology-specific study

引用

Environmental science and Ecotechnology 2024年第4期20卷 123-130页

作者： Haiyan Li Liangfang You He Du Bowen Yu Lu Lu Bo Zheng Qiang Zhang Kebin He Nanqi Ren School of Civil and Environmental Engineering Harbin Institute of TechnologyShenzhen518055China Shenzhen Key Laboratory of Ecological Remediation and Carbon Sequestration Institute of Environment and EcologyTsinghua Shenzhen International Graduate SchoolTsinghua UniversityShenzhen518055China Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System ScienceTsinghua UniversityBeijing100084China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing100084China

Wastewater treatment is an important source of greenhouse gases(GHGs).Yet large uncertainties remain in the quantification of GHG emissions from municipal wastewater treatment plants(MWWTPs)in China.A high-resolution and technology-specific emission inventory is still lacking to support mitigation strategies of *** we develop a plant-level and technology-based MWWTP emission inventory for China covering 8703 plants and 19 treatment technology categories by compiling and harmonizing the most up-to-date facility-level ***'s methane(CH_(4))and nitrous oxide(N_(2)O)emissions from MWWTPs in 2020 are estimated to be 150.6 Gg and 22.0 Gg,respectively,with the uncertainty range of-30%to 37%and-30%to 26%at 95%confidence *** find an emission inequality across cities,with the richest cities emitting two times more CH_(4)and N_(2)O per capita from municipal wastewater treatment than the poorest *** emitted CH_(4)and N_(2)O are dominated by Anaerobic/Anoxic/Oxic-,Sequencing Batch Reactor-,Oxidation Ditch-,and Anoxic/Oxic-based MWWTPs of less than 20 years *** the relatively young age structure of China's MWWTPs,the committed emissions highlight the importance of reducing on-site GHG emissions by optimization of operating conditions and innovation *** emission differences among our estimates,previous studies,and the Intergovernmental Panel on Climate Change guidelines are largely attributed to the uncertainties in emission factors,implying the urgent need for more plant-integrated measurements to improve the accuracy of emission accounting.

关键词： Methane Nitrous oxide Emissions Municipal wastewater treatment plants

来源：评论

学校读者我要写书评

暂无评论

Impurity-Robust Bulk Gapless Excitation in the Yb-Based Zigzag Chain Compound YbCuS2

Impurity-Robust Bulk Gapless Excitation in the Yb-Based Zigz...

引用

2020 International Conference on Strongly Correlated Electron systems, SCES 2020

作者： Hori, Fumiya Kinjo, Katsuki Kitagawa, Shunksaku Ishida, Kenji Ohmagari, Yudai Onimaru, Takahiro Depertment of Physics Kyoto University Kyoto606-8502 Japan Department of Quantum Matter Graduate School of Advanced Science and Engineering Hiroshima University Higashihiroshima739-8530 Japan

We have performed 63Cu-nuclear quadrupole resonance (NQR) measurements using a lump sample of the Yb zigzag-chain compound YbCuS2 with a small surface area to investigate the sample dependence of low-temperature magnetic properties in YbCuS2 by comparing with the previous study with different powdered sample. The line width of NQR signals in the present lump sample is larger than that in the previous powdered sample. In addition, the transition temperature T N ∼0.92 K in the present lump sample is lower than that in the previous powdered sample (∼0.95 K). These results suggest that the quality of the present lump sample is worse than that of the previous powdered sample. However, the T-linear behavior of the nuclear spin-lattice relaxation rate 1/T1 was observed below 0.5 K and the value of 1/T 1 T in both samples is almost the same even though the sample quality and sample geometry are different. This suggests that T-linear behavior in 1/T 1 arises from the impurity-robust bulk gapless excitation inherent in YbCuS2 rather than from sample issues such as the sample quality or geometry. © Published under licence by IOP Publishing Ltd.

关键词： Copper compounds

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Assessment of the Role of Rain Barrels and Rain Gardens in Densely Built-Up Residential Areas Near Tokyo

SSRN

引用

SSRN 2024年

作者： Lin, Jiajing Taguchi, Hiroyuki Nakamura, Hitoshi Graduate School of Engineering and Science Shibaura Institute of Technology Japan Department of Planning Architecture and Environmental Systems Shibaura Institute of Technology Japan

AbstractRecently, flooding in densely built-up residential areas has increased because of heavy rains and climate change. Urban pluvial flooding mitigation is therefore required by reducing the runoff of sewer systems with green infrastructure solutions. Rain barrels (RBs) and rain gardens (RGs) are effective stormwater management methods to reduce urban pluvial flooding, but no quantifying evaluation criteria have been set for their comprehensive assessment and to determine the best scenario. The purpose of this study is to comprehensively assess the role of RBs and RGs in densely built-up residential areas near Tokyo using the analytical hierarchy process (AHP). This AHP method represents an accurate approach to quantify the weights of decision *** chose three locations in Saitama city as the study area. These are all densely built-up residential areas, and their elevations are lower than those of surrounding areas and are prone to flood damage. The scenarios of RBs and RGs are analyzed based on three established criteria on benefits: flood control (peak time, flood condition, and total runoff), economic (life expectancy, implementation costs, project management costs, and maintenance costs), and social (aesthetic value, education, biodiversity, and carbon reduction). The weights of these criteria are determined using AHP. Moreover, the social and environmental benefits of RBs and RGs are analyzed with the analyzed with the Construction Industry Research and Information Association benefits estimation tool (B£ST) and the United States Environmental Protection Agency (EPA) stormwater management model (SWMM) Version 5.1. Based on the results, decision-makers and government departments can make better stormwater management decisions in densely built-up residential areas. © 2024, The Authors. All rights reserved.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

A Doughnut Shaped Soft Gripper Based on 4D Printed Hydrogels

A Doughnut Shaped Soft Gripper Based on 4D Printed Hydrogels

引用

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

作者： Zhe Qiu Zaiyang Liu Yitong Xue Qinshang Xie Takuto Chihara Yuma Sakurai Tatsuya Kobayashi Tsubasa Honma Hidemitsu Furukawa Zhongkui Wang Research Organization of Science and Technology Ritsumeikan University Japan Graduate School of Science and Engineering Ritsumeikan University Japan Department of Mechanical Systems Engineering Yamagata University Japan Department of Robotics Ritsumeikan University Japan

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

Soft grippers have recently been implemented to various applications due to their flexibility and compliance. They are conventionally actuated by electric and pneumatic systems. However, it is difficult to apply electric- and pneumatic-driven grippers to underwater applications thanks to the lack of waterproof ability. In this paper, we propose a doughnut shaped soft gripper based on four dimensional (4D) printing of hydrogels. The 4D printed hydrogels is capable of deforming when exposing to water stimuli. According to the property analysis of 4D printed hydrogels, such as deformation and force calibration, design parameters of the doughnut shaped gripper was determined. Underwater handling experiments were successfully conducted using the proposed soft gripper for grasping various objects with different shapes.

关键词： Printing Shape Deformation Hydrogels Force Grasping Pneumatic systems

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：