检索结果-内蒙古大学图书馆

37th Conference on Neural Information Processing systems, NeurIPS 2023

作者： Ramponi, Giorgia Kolev, Pavel Laurière, Mathieu Pietquin, Olivier Geist, Matthieu He, Niao ETH AI Center Zurich Switzerland Max Planck Institute for Intelligent Systems Tübingen Germany Google DeepMind ETH Zurich Department of Computer Science Switzerland Shanghai Frontiers Science Center of Artificial Intelligence and Deep Learning NYU Shanghai China

ISBN: (纸本)9781713899921

We explore the problem of imitation learning (IL) in the context of mean-field games (MFGs), where the goal is to imitate the behavior of a population of agents following a Nash equilibrium policy according to some unknown payoff function. IL in MFGs presents new challenges compared to single-agent IL, particularly when both the reward function and the transition kernel depend on the population distribution. In this paper, departing from the existing literature on IL for MFGs, we introduce a new solution concept called the Nash imitation gap. Then we show that when only the reward depends on the population distribution, IL in MFGs can be reduced to single-agent IL with similar guarantees. However, when the dynamics is population-dependent, we provide a novel upper-bound that suggests IL is harder in this setting. To address this issue, we propose a new adversarial formulation where the reinforcement learning problem is replaced by a mean-field control (MFC) problem, suggesting progress in IL within MFGs may have to build upon MFC. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Population distribution

来源：评论

学校读者我要写书评

暂无评论

A Distributed Framework for Large-scale Protein-protein Interaction Data Analysis and Prediction Using MapReduce

引用

IEEE/CAA Journal of Automatica Sinica 2022年第1期9卷 160-172页

作者： Lun Hu Shicheng Yang Xin Luo Huaqiang Yuan Khaled Sedraoui MengChu Zhou School of Computer Science and Technology Dongguan University of TechnologyDongguan 523808China School of Computer Science and Technology Wuhan University of TechnologyWuhan 430070China Chongqing Engineering Research Center of Big Data Application for Smart Cities and Chongqing Key Laboratory of Big Data and Intelligent ComputingChongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Xinjiang Technical Institute of Physics and Chemistry Chinese Academy of SciencesUrumqi 830000China Center of Research Excellence in Renewable Energy and Power Systems and the Department of Electrical and Computer EngineeringFaculty of EngineeringKing Abdulaziz UniversityJeddah 21589Saudi Arabia Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07102 USA

Protein-protein interactions are of great significance for human to understand the functional mechanisms of *** the rapid development of high-throughput genomic technologies,massive protein-protein interaction(PPI)data have been generated,making it very difficult to analyze them *** address this problem,this paper presents a distributed framework by reimplementing one of state-of-the-art algorithms,i.e.,CoFex,using *** do so,an in-depth analysis of its limitations is conducted from the perspectives of efficiency and memory consumption when applying it for large-scale PPI data analysis and *** solutions are then devised to overcome these *** particular,we adopt a novel tree-based data structure to reduce the heavy memory consumption caused by the huge sequence information of *** that,its procedure is modified by following the MapReduce framework to take the prediction task distributively.A series of extensive experiments have been conducted to evaluate the performance of our framework in terms of both efficiency and *** results well demonstrate that the proposed framework can considerably improve its computational efficiency by more than two orders of magnitude while retaining the same high accuracy.

关键词： Distributed computing large-scale prediction machine learning MapReduce protein-protein interaction(PPI)

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of LLM-based Chatbots for Task Scheduling in Robot Operations 25

Exploring the Potential of LLM-based Chatbots for Task Sched...

引用

25th IEEE International Conference on Autonomous Robot systems and Competitions, ICARSC 2025

作者： Rema, Catarina Sousa, Armando Sobreira, Heber Costa, Pedro Silva, Manuel F. University of Porto (FEUP) Faculty of Engineering Porto 4200-465 Portugal INESC TEC - Institute for Systems and Computer Engineering Technology and Science CRIIS - Centre for Robotics in Industry and Intelligent Systems Porto 4200-465 Portugal ISEP Polytechnic of Porto rua Dr. António Bernardino de Almeida Porto 4249-015 Portugal

ISBN: (纸本)9798331538606

The rise of Industry 4.0 has revolutionized manufacturing by integrating real-time data analysis, artificial intelligence (AI), automation, and interconnected systems, enabling adaptive and resilient smart factories. Autonomous Mobile Robots (AMRs), with their advanced mobility and navigation capabilities, are a pillar of this transformation. However, their deployment in job shop environments adds complexity to the already challenging Job Shop Scheduling Problem (JSSP), expanding it to include task allocation, robot scheduling, and travel time optimization, creating a multi-faceted, non-deterministic polynomial-time hardness (NP-hard) problem. Traditional approaches such as heuristics, meta-heuristics, and mixed integer linear programming (MILP) are commonly used. Recent AI advancements, particularly large language models (LLM), have shown potential in addressing these scheduling challenges due to significant improvements in reasoning and decision-making from textual data. This paper examines the application of LLM to tackle scheduling complexities in smart job shops with mobile robots. Guided by tailored prompts inserted manually, LLM are employed to generate scheduling solutions, being these compared to an heuristic-based method. The results indicate that LLM currently have limitations in solving complex combinatorial problems, such as task scheduling with mobile robots. Due to issues with consistency and repeatability, they are not yet reliable enough for practical implementation in industrial environments. However, they offer a promising foundation for augmenting traditional approaches in the future. © 2025 IEEE.

关键词： Chatbots Large Language Model Mobile Robots Task Scheduling

来源：评论

学校读者我要写书评

暂无评论

Domain-Invariant Similarity Activation Map Contrastive Learning for Retrieval-Based Long-Term Visual Localization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 313-328页

作者： Hanjiang Hu Hesheng Wang Zhe Liu Weidong Chen Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China IEEE Department of Automation Institute of Medical RoboticsKey Laboratory of System Control and Information Processing of Ministry of EducationKey Laboratory of Marine Intelligent Equipment and System of Ministry of EducationShanghai Jiao Tong UniversityShanghai 200240China Department of Computer Science and Technology University of CambridgeCambridge CB30FDUnited Kingdom

Visual localization is a crucial component in the application of mobile robot and autonomous *** retrieval is an efficient and effective technique in image-based localization *** to the drastic variability of environmental conditions,e.g.,illumination changes,retrievalbased visual localization is severely affected and becomes a challenging *** this work,a general architecture is first formulated probabilistically to extract domain-invariant features through multi-domain image ***,a novel gradientweighted similarity activation mapping loss(Grad-SAM)is incorporated for finer localization with high *** also propose a new adaptive triplet loss to boost the contrastive learning of the embedding in a self-supervised *** final coarse-to-fine image retrieval pipeline is implemented as the sequential combination of models with and without Grad-SAM *** experiments have been conducted to validate the effectiveness of the proposed approach on the CMU-Seasons *** strong generalization ability of our approach is verified with the RobotCar dataset using models pre-trained on urban parts of the CMU-Seasons *** performance is on par with or even outperforms the state-of-the-art image-based localization baselines in medium or high precision,especially under challenging environments with illumination variance,vegetation,and night-time ***,real-site experiments have been conducted to validate the efficiency and effectiveness of the coarse-to-fine strategy for localization.

关键词： Deep representation learning place recognition visual localization

来源：评论

学校读者我要写书评

暂无评论

Verifying Nonlinear Neural Feedback systems using Polyhedral Enclosures

arXiv

引用

arXiv 2025年

作者： Akinwande, Samuel I. Sidrane, Chelsea Kochenderfer, Mykel J. Barrett, Clark Department of Aeronautical and Astronautical Engineering Stanford University StanfordCA94305 United States Department of Computer Science Stanford University StanfordCA94305 United States Division of Robotics Perception and Learning Intelligent Systems Department School of Electrical Engineering & Computer Science KTH Royal Institute of Technology Stockholm Sweden

As dynamical systems equipped with neural network controllers (neural feedback systems) become increasingly prevalent, it is critical to develop methods to ensure their safe operation. Verifying safety requires extending control theoretic analysis methods to these systems. Although existing techniques can efficiently handle linear neural feedback systems, relatively few scalable methods address the nonlinear case. We propose a novel algorithm for forward reachability analysis of nonlinear neural feedback systems. The approach leverages the structure of the nonlinear transition functions of the systems to compute tight polyhedral enclosures (i.e., abstractions). These enclosures, combined with the neural controller, are then encoded as a mixed-integer linear program (MILP). Optimizing this MILP yields a sound over-approximation of the forward-reachable set. We evaluate our algorithm on representative benchmarks and demonstrate an order of magnitude improvement over the current state of the art. Copyright © 2025, The Authors. All rights reserved.

关键词： Mixed-integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Based Vertical Scaling for Hybrid Deployment in Cloud Computing 1

引用

17th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2022

作者： Cao, Jianqi Li, Guiying Yang, Peng Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Data Science Southern University of Science and Technology Shenzhen518055 China

ISBN: (数字)9789819915491

ISBN: (纸本)9789819915484

To maximize the CPU utilization of the server, offline tasks are usually deployed to the same server where the online service is running. Considering the necessity to ensure the service quality of online services, it is common practice to isolate the resources of online services. How to set the resource quota for online services not only affects the service quality of online services, but also affects the number and the stability of offline tasks that can be run on the server. Traditional rule-based methods or prediction-based methods will cause over-provision and fail to consider the stability of offline tasks, which often cannot achieve stability and efficiency. In this paper, reinforcement learning is proposed for the first time to solve the hybrid deployment of online services and offline tasks and dynamically adjust the resource quota of online services more effectively. Compared with the original state of the server, our proposed method reduces CPU idleness rate by 35.32% and increases CPU resource utilization rate by 3.84%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Investigation on Thermal Analysis for Solar Panel using Fiber Bragg Grating Sensor

Experimental Investigation on Thermal Analysis for Solar Pan...

引用

OCEANS

作者： Tarun.N S.Sharvesh Shravan.P Bharathiraju R.Kumar Gerard Dooly Samiappan Dhanalakshmi Department of ECE SRM Institute of Science and Technology Chennai India Centre for Robotics and Intelligent Systems University of Limerick Limerick Ireland

Monitoring the temperature of the installed solar panels is crucial since the deployment of oceanic solar power plants is on the rise. The temperature variations due to solar radiation has an influence on the solar panel’s overall efficiency. Hence it is essential to oversee and regulate the solar panel temperature. For this purpose, the existing temperature sensor such as Resistance thermal detector, temperature gauge sensors etc., lack accuracy and have a long response time. Fiber optic sensors has an edge over conventional sensors in accuracy, sampling rate and response time. In this experimental study, we consider the Fiber Bragg grating which is inscribed on the solar panel to monitor the temperature fluctuations. Polymer coating is generally used for protection of the fiber optic sensors and improving elasticity. In this study, we primarily consider the acrylate polymer for sensitivity enhancement. The incident solar radiation with respect to temperature fluctuation and the angle of panel is quantitatively found and qualitatively plotted. The enhancement in the solar panel’s effectiveness due to the acrylate coating of the fiber bragg grating sensor compared to other coating are studied in a comprehensive manner. Temperature sensitivity of 7 pm/°C is achieved. The findings aid in dynamic panel temperature monitoring, the microscale comprehension of thermal interactions, and the streamlined measurement of many solar farm panels average temperatures. The suggested enhanced technique of FBG sensor based solar panel temperature monitoring may be advantageous for the design of a unified cooling system to increase the solar panel performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object-centric learning for real-world videos by predicting temporal feature similarities 23

Object-centric learning for real-world videos by predicting ...

引用

Proceedings of the 37th International Conference on Neural Information Processing systems

作者： Andrii Zadaianchuk Maximilian Seitzer Georg Martius Max Planck Institute for Intelligent Systems Tübingen Germany and Department of Computer Science ETH Zurich Max Planck Institute for Intelligent Systems Tübingen Germany

Unsupervised video-based object-centric learning is a promising avenue to learn structured representations from large, unlabeled video collections, but previous approaches have only managed to scale to real-world datasets in restricted domains. Recently, it was shown that the reconstruction of pre-trained self-supervised features leads to object-centric representations on unconstrained real-world image datasets. Building on this approach, we propose a novel way to use such pre-trained features in the form of a temporal feature similarity loss. This loss encodes semantic and temporal correlations between image patches and is a natural way to introduce a motion bias for object discovery. We demonstrate that this loss leads to state-of-the-art performance on the challenging synthetic MOVi datasets. When used in combination with the feature reconstruction loss, our model is the first object-centric video model that scales to unconstrained video datasets such as YouTube-VIS. https://***/videosaur/

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resilient Event-Triggered Model Predictive Control for Adaptive Cruise Control Under Sensor Attacks

引用

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 807-809页

作者： Zhijian Hu Rong Su Kai Zhang Zeyuan Xu Renjie Ma School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore Key Laboratory of Ultra-Precision Intelligent Instrumentation Ministry of Industry and Information Technologyand the Center of Ultra-Precision Optoelectronic Instrument EngineeringHarbin Institute of TechnologyHarbin 150001China Department of Control Science and Engineering Harbin Institute of TechnologyHarbin 150001China Department of Chemical and Biomolecular Engineering National University of SingaporeSingapore 117585Singapore State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin 150001China IEEE

Dear Editor,This letter addresses the resilient model predictive control(MPC)problems for adaptive cruise control(ACC)systems under sensor *** the light of vulnerabilities of ACC systems to sensor attacks,an intrusion detection mechanism is proposed at the controller side to distinguish abnormal ***,the robust control gains are derived to design the terminal region constraint for MPC.

关键词： Trigger Event constraint

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Representation Refinement Based on Convex Combination for 3-D Human Poses Estimation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6500-6508页

作者： Chen, Luefeng Cao, Wei Zheng, Biao Wu, Min Pedrycz, Witold Hirota, Kaoru China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Macau University of Science and Technology Institute of Systems Engineering Taipa999078 China Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Tokyo Institute of Technology Yokohama226-8502 Japan

In the human pose estimation task, on the one hand, 3-D pose always has difficulty in dividing different 2-D poses if the view is limited;on the other hand, it is hard to reduce the lifting ambiguity because of the lack of depth information, it is an important and challenging problem. Therefore, two-stage representation refinement based on the convex combination for 3-D human pose estimation is proposed, in which the two-stage method includes a dense-spatial-temporal convolutional network and a local-to-refine network. The former is applied to determine the features between each video frame;the latter is used to get the different scales of pose details. It aims to address the difficulty of estimating 3-D human pose from 2-D image sequences. In such a way, it can better use the relations between every frame in the sequence of the pose video to produce more accurate results. Finally, we combine the above network with a block called convex combination to help refine the 3-D pose location. We test the proposed approach on both Human3.6m and MPII datasets. The result confirms that our method can achieve better performance than improved CNN supervision, a simple yet effective baseline, and coarse-to-fine volumetric prediction. Besides, a robustness test experiment is carried out for the proposed method while the input is interrupted. The result verifies that our method shows better robustness. © 2024 IEEE.

关键词： Convolution

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：