检索结果-内蒙古大学图书馆

Distributed Online Convex Optimization with Time-Varying Constraints: Tighter Cumulative Constraint Violation Bounds under Slater's Condition

引用

IEEE Transactions on Automatic Control 2025年

作者： Yi, Xinlei Li, Xiuxian Yang, Tao Xie, Lihua Hong, Yiguang Chai, Tianyou Johansson, Karl H. National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai Institute of Intelligent Science and Technology China Ministry of Education Frontiers Science Center for Intelligent Autonomous Systems China Massachusetts Institute of Technology Lab for Information & Decision Systems CambridgeMA02139 United States Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Nanyang Technological University School of Electrical and Electronic Engineering 50 Nanyang Avenue 639798 Singapore Kth Royal Institute of Technology Division of Decision and Control Systems School of Electrical Engineering and Computer Science Sweden Digital Futures Stockholm10044 Sweden

This paper considers distributed online convex optimization with time-varying constraints. In this setting, a network of agents makes decisions at each round, and then only a portion of the loss function and a coordinate block of the constraint function are privately revealed to each agent. The loss and constraint functions are convex and can vary arbitrarily across rounds. The agents collaborate to minimize static network regret and network cumulative constraint violation. A novel distributed online algorithm with a vanishing stepsize is proposed and it achieves an O(Tmax {c,1-c}) static network regret bound and an O(T1-c/2) network cumulative constraint violation bound, where T is the number of rounds and c∈ (0,1) is a user-defined trade-off parameter. When Slater's condition holds (i.e, there is a point that strictly satisfies the inequality constraints), the network cumulative constraint violation bound is reduced to O(T1-c). Moreover, if the loss functions are strongly convex, then static network regret bound is reduced to O(log (T)), and the network cumulative constraint violation bound is reduced to O(√log (T)T) and O(log (T)) without and with Slater's condition, respectively. To the best of our knowledge, this paper is the first to achieve tighter (network) cumulative constraint violation bounds for (distributed) online convex optimization with time-varying constraints under Slater's condition. Finally, the theoretical results are verified through numerical simulations. © 1963-2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Navigation Aids Based on Optical Flow and Convolutional Neural Network

Navigation Aids Based on Optical Flow and Convolutional Neur...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Leonardo Silveira Mateus Rodrigues Bruno S. Faiçal Alexandre S. Quirino da Silva Cesar Marcondes Marcos R. O. A. Maximo Filipe A. N. Verri Computer Science Division Aeronautics Institute of Technology - ITA São José dos Campos SP Brazil Embraer São José dos Campos SP Brazil Autonomous Computational Systems Lab - LAB-SCA Computer Science Division Aeronautics Institute of Technology - ITA São José dos Campos SP Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

Unmanned Aerial Vehicles (UAV) have been employed in various activities, such as search and rescue missions. Global Navigation Satellite System (GNSS) is the main tool used by UAVs to identify their global location and to be able to complete flights safely. However, UAVs can suffer attacks that invalidate the global positioning information or simply loose for a period the GNSS signal. The lack of the aircraft's global positioning information can result in incomplete missions and accidents. In this paper we propose an Image-Based Localization System (IBLS), which allows the global position of the aircraft to be inferred based on images captured by a camera pointed at the ground. Our proposal is based on the concepts of optical flow to infer the displacement between two images captured sequentially with a CNN. Based on the displacement, we use the haversine formula to estimate the new global position (latitude and longitude) of the UAV. IBLS uses a calibration step learned during flight with available GNSS signal, which allows to reduce the error in inferring the new position. The results achieved on simulated and real data sets demonstrate that our proposal is able to infer the position of the UAV with lower error than in GNSS. The main contribution of this work is the investigation of a system based on the concept of Optical Flow and Convolutional Neural Network to estimate the geographical coordinate during UAV flight.

关键词： Global navigation satellite system Robot kinematics computer architecture autonomous aerial vehicles Cameras Calibration Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems

arXiv

引用

arXiv 2022年

作者： Prudencio, Rafael Figueiredo Maximo, Marcos R.O.A. Colombini, Esther Luna The Laboratory of Robotics and Cognitive Systems Computing Institute University of Campinas Campinas13083-852 Brazil The Autonomous Computational Systems Laboratory Computer Science Division Aeronautics Institute of Technology São José dos Campos12228-900 Brazil

With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games from pixel observations, sustaining conversations with humans, and controlling robotic agents. However, there is still a wide range of domains inaccessible to RL due to the high cost and danger of interacting with the environment. Offline RL is a paradigm that learns exclusively from static datasets of previously collected interactions, making it feasible to extract policies from large and diverse training datasets. Effective offline RL algorithms have a much wider range of applications than online RL, being particularly appealing for real-world applications, such as education, healthcare, and robotics. In this work, we contribute with a unifying taxonomy to classify offline RL methods. Furthermore, we provide a comprehensive review of the latest algorithmic breakthroughs in the field using a unified notation as well as a review of existing benchmarks' properties and shortcomings. Additionally, we provide a figure that summarizes the performance of each method and class of methods on different dataset properties, equipping researchers with the tools to decide which type of algorithm is best suited for the problem at hand and identify which classes of algorithms look the most promising. Finally, we provide our perspective on open problems and propose future research directions for this rapidly growing field. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Algorithm to Control a Curved Kicking Mechanism in RoboCup Small Size League

Deep Neural Network Algorithm to Control a Curved Kicking Me...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Francisco A. B. Azevedo Guilherme P. C. Leão Marcos R. O. A. Maximo Aeronautics Engineering Division Aeronautics Institute of Technology São José dos Campos Brazil Electronic Engineering Division Aeronautics Institute of Technology São José dos Campos Brazil Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology São José dos Campos Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

Small Size League (SSL) is a robotics soccer league at the Robotics World Cup, RoboCup. In this league, the proposition of a mechanism capable of performing unpredictable kicks and passes inspired works of both the physical mechanism to implement this and the algorithms to extract the most of this mechanism. The present work's contribution is an improvement on a previously algorithm that aims to perform a real-time inversion of the non-linear ordinary differential equation that models the ball's trajectory to find the parameters to hit a target with the curved kick mechanism, by adding new concepts and by using a Deep Neural Network. New strategies are added to improve the efficiency of the algorithm and to make it easier to be integrated with other algorithms on the robot and also make it capable of finding a trajectory that avoids enemies on the field.

关键词： Deep learning Conferences Neural networks Education Ordinary differential equations Real-time systems Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Comparison of Encoder-Decoder Networks for Soccer Field Segmentation

Comparison of Encoder-Decoder Networks for Soccer Field Segm...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Otávio H. R. Guimarães Marcos R. O. A. Maximo Jose Maria Parente de Oliveira École polytechnique Institut Polytechnique de Paris Route de Saclay Palaiseau Île-de-France France Autonomous Computational Systems Lab Computer Science Division Aeronautics Institute of Technology Praça Marechal Eduardo Gomes 50 Vila das Acaciás São José dos Campos SP Brazil Computer Science Division Aeronautics Institute of Technology Praça Marechal Eduardo Gomes 50 Vila das Acaciás São José dos Campos SP Brazil

Convolutional neural networks consist of state-of the-art models used for the solution of computer vision problems. This paper contributes by evaluating the efficiency of several encoder-decoder neural networks, trained to perform the segmentation of the soccer field in Humanoid KidSize Robot Soccer competitions. To compare the efficiency of several encoders, a total of fourteen neural network models, based on the U-Net and SegNet architectures, were tested and compared in terms of accuracy, cost function value, IoU, and average inference time. Based on that, the networks based on U-Net that utilized the MobileNetv3Small or the ResNet18 for the encoding process were found to be the optimal solution among the considered alternatives to segment the soccer field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HCIlab at Memotion 2.0 2022: Analysis of Sentiment, Emotion and Intensity of Emotion Classes from Meme Images using Single and Multi Modalities 1

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion ...

引用

1st Workshop on Multimodal Fact-Checking and Hate Speech Detection, DE-FACTIFY 2022

作者： Nguyen, Thanh Tin Pham, Nhat Truong Nguyen, Ngoc Duy Nguyen, Hai Nguyen, Long H. Kim, Yong-Guk Human Computer Interaction Lab Department of Computer Engineering Sejong University Seoul Korea Republic of Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Institute for Intelligent Systems Research and Innovation Deakin University Victoria Australia Khoury College of Computer Sciences Northeastern University Boston United States Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam

Nowadays, memes found on internet are overwhelming. Although they are innocuous and sometimes entertaining, there exist memes that contain sarcasm, offensive, or motivational feelings. In this study, several approaches are proposed to solve the multiple modality problem in analysing the given meme dataset. The imbalance issue has been addressed by using a new Auto Augmentation method and the uncorrelation issue has been mitigated by adopting deep Canonical Correlation Analysis to find the most correlated projections of visual and textual feature embedding. In addition, both stacked attention and multi-hop attention network are employed to efficiently generate aggregated features. As a result, our team, i.e. HCIlab, achieved a weighted F1 score of 0.4995 for sentiment analysis, 0.7414 for emotion classification, and 0.5301 for scale/intensity of emotion classes on the leaderboard. This results are obtained by using concatenation between image and text model and our code can be found at https://***/JMRa8. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Ionospheric scintillation simulation based on neural networks

Ionospheric scintillation simulation based on neural network...

引用

Eurocon

作者： Moisés J. S. Freitas Alison O. Moraes Emanoel Costa Marcos R. O. A. Máximo Clodoaldo De S. Faria Instituto Tecnològico de Aeronáutica (ITA) São José dos Campos Brazil Centro de Estudos em Telecomunicações Pontificia Universidade Catélica do Rio de Janeiro (PUC-Rio) Rio de Janeiro Brazil Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Instituto Tecnológico de Aeronáutica (ITA) São José dos Campos Brazil Universidade Estadual Paulista (UNESP) Presidente Prudente Brazil

Thereis a demand for the development of GNSS positioning processing techniques that are more tolerant to the effects of the low latitude ionosphere (in particular, scintillation). The possibility of simulating scintillating channels supports the development of more sophisticated test benches and receivers. This paper proposes a neural network-based simulator of ionospheric amplitude scintillation. This synthetic scintillation simulator uses autoencoders and generative adversarial networks (GANs) to generate time series that follow the statistical characteristics of the $\alpha-\mu$ fading model. A part of the proposed network tries to create a synthetic signal, similar to the field data. The proposed neural network was trained and validated with scintillation data acquired in Sao Jose dos Campos, Brazil, in February 2012 and November 2014. The results of the proposed method show that the simulator yields the correct values of the scintillation index, and the estimated fading coefficients are also close to the specified values. These aspects show that this kind of approach can be promising in the simulation of fading channels. Future improvements of the model are also be discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network for Respiratory Mechanics Estimation during Pressure Support Ventilation

引用

IFAC-PapersOnLine 2021年第15期54卷 406-411页

作者： Adriano S. Rodrigues Marcos R.O.A. Maximo Marcus H. Victor Aeronautics Institute of Technology São José dos Campos SP BR Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology São José dos Campos SP BR Aeronautics Institute of Technology Electronics Engineering São José dos Campos SP BR

In mechanically ventilated patients, some lung injuries can be reduced or avoided with therapy individualization, while the lung function is evaluated continuously, breath by breath. However, obtaining information on respiratory mechanics (respiratory system resistance and compliance) in the presence of respiratory effort is challenging, even if using invasive and complex procedures. The contribution of this work is to predict both respiratory system resistance and compliance over time using a convolutional neural network (CNN) and estimate the respiratory effort profile using the respiratory dynamics. Therefore, the approach used in this work was to generate a large amount of simulated data to feed a CNN so it could learn how to predict the correct values of the respiratory system resistance and compliance. Then, the respiratory effort was estimated by solving a first-order linear model. The main results showed a normalized mean squared error of 5.7% for the respiratory system resistance and 11.56% for compliance from Bland-Altman plots derived from the computational simulator. Finally, the method was validated using real data from an active lung simulator within which respiratory mechanics varied, and some ventilator settings were adjusted to mimic actual patient situations. The active lung simulator effort profile was obtained with a normalized mean squared error of 8.31% considering the use of an active lung simulator. The results have shown that the simulated data were valuable for the CNN training, while the performance over the real data suggested that the network was generalized accordingly for estimating respiratory parameters and effort profile.

关键词： Mechanical Ventilation Respiratory Mechanics Respiratory Effort Deep Learning Convolutional Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Comparison of Sampling-based Path Planners for Robocup Small Size League

Comparison of Sampling-based Path Planners for Robocup Small...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Felipe C.R. Pinheiro Marcos R. O. A. Máximo Takashi Yoneyama Autonomous Computational Systems Lab (LAB-SCA) Computer Science Division Aeronautics Institute of Technology Săo José dos Campos SP Brazil Electronics Division Aeronautics

ISBN: (数字)9780738111537

ISBN: (纸本)9781665419857

The path planning problem is an important issue in robotics. In the context of the Small Size Soccer league, a widely used algorithm for path planning is the Rapidly-Exploring Random Tree (RRT), which is a single-query planner. However, properties such as asymptotic optimality and anytime resolution may not be achieved by some of the algorithms used in the competition. Some of the possible path planning solvers with some of these properties are the Batch Informed Trees (BIT*), Fast Marching Trees (FMT*), and other RRT implementations (such as Extended Execution RRT - ERRT and RRT*). The contribution of this paper is to carry out a benchmark comparative investigation with a selected set of path planners found in the literature, evaluating their performance in the context of Robocup Small Size League Competition. The results show good convergence properties of BIT* when the planning time requirement is larger. ERRT performs well to find a solution, but it falls short concerning the solution quality. RRT* did not have a good convergence to optimal paths, but succeeded to find paths with short planning time. Since FMT* does not present anytime resolution, the algorithm did not present a satisfactory convergence with larger planning time. To improve the performance of the planners, it may be interesting to conceive heuristic strategies to allow trivial problems to be solved faster.

关键词： Path planning Robot kinematics Planning Sports Search problems Convergence computational modeling

来源：评论

学校读者我要写书评

暂无评论

A Communication-Efficient Decentralized Newton's Method with Provably Faster Convergence

arXiv

引用

arXiv 2022年

作者： Liu, Huikang Zhang, Jiaojiao So, Anthony Man-Cho Ling, Qing The Research Institute for Interdisciplinary Sciences School of Information Management and Engineering Shanghai University of Finance and Economics China The Division of Decision and Control Systems School of Electrical Engineering and Computer Science Kth Royal Institute of Technology Sweden The Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong The School of Computer Science and Engineering Guangdong Province Key Laboratory of Computational Science Sun Yat-Sen University China The Pazhou Lab China

In this paper, we consider a strongly convex finite-sum minimization problem over a decentralized network and propose a communication-efficient decentralized Newton's method for solving it. The main challenges in designing such an algorithm come from three aspects: (i) mismatch between local gradients/ Hessians and the global ones;(ii) cost of sharing second-order information;(iii) tradeoff among computation and communication. To handle these challenges, we first apply dynamic average consensus (DAC) so that each node is able to use a local gradient approximation and a local Hessian approximation to track the global gradient and Hessian, respectively. Second, since exchanging Hessian approximations is far from communication-efficient, we require the nodes to exchange the compressed ones instead and then apply an error compensation mechanism to correct for the compression noise. Third, we introduce multistep consensus for exchanging local variables and local gradient approximations to balance between computation and communication. With novel analysis, we establish the globally linear (resp., asymptotically super-linear) convergence rate of the proposed method when m is constant (resp., tends to infinity), where m ≥ 1 is the number of consensus inner steps. To the best of our knowledge, this is the first super-linear convergence result for a communication-efficient decentralized Newton's method. Moreover, the rate we establish is provably faster than those of first-order methods. Our numerical results on various applications corroborate the theoretical findings. Copyright © 2022, The Authors. All rights reserved.

关键词： Newton-Raphson method

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：