检索结果-内蒙古大学图书馆

Generative Curricula for Multi-Agent Path Finding via Unsupervised and Reinforcement learning

Journal of Artificial Intelligence Research 2025年 82卷 2471-2534页

作者： Phan, Thomy Phan, Timy Koenig, Sven University of Southern California Thomas Lord Department of Computer Science Los AngelesCA90089 United States LMU Munich Computer Vision & Learning Group School of Arts Munich80799 Germany University of California Irvine Department of Computer Science IrvineCA92697 United States

Multi-Agent Path Finding (MAPF) is the challenging problem of finding collision-free paths for multiple agents, which has a wide range of applications, such as automated warehouses, smart manufacturing, and traffic management. Recently, machine learning-based approaches have become popular in addressing MAPF problems in a decentralized and potentially generalizing way. Most learning-based MAPF approaches use reinforcement and imitation learning to train agent policies for decentralized execution under partial observability. However, current state-of-the-art approaches suffer from a prevalent bias to micro-aspects of particular MAPF problems, such as congestions in corridors and potential delays caused by single agents, leading to tight specializations through extensive engineering via oversized models, reward shaping, path finding algorithms, and communication. These specializations are generally detrimental to the sample efficiency, i.e., the learning progress given a certain amount of experience, and generalization to previously unseen scenarios. In contrast, curriculum learning offers an elegant and much simpler way of training agent policies in a step-by-step manner to master all aspects implicitly without extensive engineering. In this paper, we propose a generative curriculum approach to learning-based MAPF using Variational Autoencoder Utilized learning of Terrains (VAULT). We introduce a two-stage framework to (I) train the VAULT via unsupervised learning to obtain a latent space representation of maps and (II) use the VAULT to generate curricula in order to improve sample efficiency and generalization of learning-based MAPF methods. For the second stage, we propose a bi-level curriculum scheme by combining our VAULT curriculum with a low-level curriculum method to improve sample efficiency further. Our framework is designed in a modular and general way, where each proposed component serves its purpose in a black-box manner without considering specific micro

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Achachay App: a community-driven innovation for flood data collection in urban and rural areas

Achachay App: a community-driven innovation for flood data c...

引用

International Conference on Technological Innovation and AI Research (ICTIAIR 2025)

作者： Ariana Deyaneira Jiménez-Narváez Jonathan Javier Loor-Duque Diego Josue Andrade-Pelaez Manuel Eugenio Morocho-Cayamcela Raisa Torres-Ramírez Deep Learning for Autonomous Driving Robotics and Computer Vision Research Group (DeepARC) School of Mathematical and Computational Sciences Yachay Tech University San Miguel de Urcuquí Ecuador Applied Geology and Research Group School of Geological Sciences Energy and Environment Yachay Tech University San Miguel de Urcuquí Ecuador

ISBN: (数字)9781837243235

Floods are among the most frequent and devastating natural disasters, significantly impacting urban and rural communities worldwide. Achachay App is a mobile application designed to enhance flood data collection and analysis through direct community engagement. The app enables users to report real-time flood events by sharing detailed descriptions, geographic coordinates, and multimedia evidence such as photos or videos. Researchers use these community-sourced data to analyze and reconstruct watercourse behaviors that lead to flooding. Ecuador was selected for implementation as a pilot initiative, where the app successfully mapped flood-prone areas and secondary flows. These features aim to deepen understanding of the interplay between geological and climatic phenomena, supporting disaster preparedness and prevention. By bridging technology and community collaboration, the Achachay Appoffers valuable insights for policymakers to design sustainable public policies that mitigate risks and promote social and economic development in Ecuador.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AI-based predictive and detection models for Avian Pox caused by Avipoxvirus Spp in the Galápagos Islands

AI-based predictive and detection models for Avian Pox cause...

引用

International Conference on Technological Innovation and AI Research (ICTIAIR 2025)

作者： Jonathan Javier Loor-Duque Grace Rodríguez Ariana Deyaneira Jiménez-Narváez Juan David Moromenacho-Aguirre Fernando Patricio Carranco-Avila Clayanela Zambrano-Caicedo Iván Galo Reyes-Chacón Paulina Vizcaíno Manuel Eugenio Morocho-Cayamcela Yachay Tech University School of Mathematical and Computational Sciences Deep Learning for Autonomous Driving Robotics and Computer Vision Research Group DeepARC Research Urcuquí 100119 Ecuador Pontificia Universidad Católica del Ecuador Faculty of Exact and Natural Sciences Biology Quito Ecuador Universidad Internacional del Ecuador Faculty of Technical Sciences School of Computer Science Quito Ecuador

ISBN: (数字)9781837243235

Predicting infection by Avipoxvirus spp, the causative agent of avian pox, in endemic Galápagos Islands species such as the Geospiza fuliginosafinches, represents an innovative approach to controlling viral diseases in vulnerable ecosystems. This study uses artificial intelligence-based predictive models trained on a database compiled from previous research. The database was balanced and subjected to data augmentation like synthetic minority oversampling and tablediffusion. Compared with alternative studies, where the data is converted from tabular data into an image achieving a recall of 85%; our results achieve a recall of near 100% using a multi-state analysis over susceptible-infectious-recovered models in infectious diseases for populations of the European serins ( Serinus serinus), highlighting the anticipatory capacity for early identification of outbreaks and risk factors. This predictive tool not only strengthens biodiversity protection in the archipelago but also supports the development of targeted vaccines and treatments, ensuring the preservation of this unique ecosystem and providing a model applicable for monitoring other infectious diseases in bird populations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FrontierNet: learning Visual Cues to Explore

引用

IEEE Robotics and Automation Letters 2025年第7期10卷 6576-6583页

作者： Sun, Boyang Chen, Hanzhi Leutenegger, Stefan Cadena, Cesar Pollefeys, Marc Blum, Hermann ETH Zurich Computer Vision and Geometry Group Zurich 8092 Switzerland Technical University of Munich Mobile Robotics Lab München 80333 Germany ETH Zurich Mobile Robotics Lab Zurich 8092 Switzerland ETH Zurich Robotic Systems Lab Zurich 8092 Switzerland AI Lab Microsoft Mixed Reality Zurich 8038 Switzerland University of Bonn Lamarr Institute for ML and AI Robot Perception and Learning Lab Bonn 53115 Germany

Exploration of unknown environments is crucial for autonomous robots;it allows them to actively reason and decide on what new data to acquire for different tasks, such as mapping, object discovery, and environmental assessment. Existing solutions, such as frontier-based exploration approaches, rely heavily on 3D map operations, which are limited by map quality and, more critically, often overlook valuable context from visual cues. This work aims at leveraging 2D visual cues for efficient autonomous exploration, addressing the limitations of extracting goal poses from a 3D map. We propose a visual-only frontier-based exploration system, with FrontierNet as its core component. FrontierNet is a learning-based model that (i) proposes frontiers, and (ii) predicts their information gain, from posed RGB images enhanced by monocular depth priors. Our approach provides an alternative to existing 3D-dependent goal-extraction approaches, achieving a 15% improvement in early-stage exploration efficiency, as validated through extensive simulations and real-world experiments. © 2016 IEEE.

关键词： Deep learning Motion and Path Planning Perception and Autonomy

来源：评论

学校读者我要写书评

暂无评论

On the Identification of Self-Adjoint Linear Time-Varying State Models

引用

IFAC-PapersOnLine 2018年第15期51卷 251-256页

作者： Rapisarda, P. Vision Learning and Control Group School of Electronics and Computer Science University of Southampton United Kingdom

A novel approach to the identification of linear time-varying (LTV) systems is illustrated, based on the concept of duality. Generically, if N input-output trajectories (uk, yk), k = 1,…,N of a self-adjoint LTV system are known, then the duality relation can be used to derive state trajectories xk, k = 1,… N corresponding to such data. Such state trajectories are computed by factorizing a matrix directly constructed from input-output data of the primal and the dual system. From such input-state-output trajectories an “unfalsified” linear time-varying model can be obtained solving a system of functional equations. © 2018

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

An evaluation of synthetic data for deep learning stereo depth algorithms 2017

An evaluation of synthetic data for deep learning stereo dep...

引用

2017 International Conference on Watermarking and Image Processing, ICWIP 2017

作者： Lee, Kevin Moloney, David Computer Vision and Machine Learning Group Intel/Movidius United States

ISBN: (纸本)9781450353076

Stereo vision is a very active field in the realm of computer vision and in recent years Convolutional Neural Networks (CNNs) have proven to be very competitive against the state-of-the-art. However, the performance of these networks are limited by the quality of the data that is used when training the CNNs. Data acquisition of high quality labeled images is a time-consuming and expensive process. By exploiting the power of modern-day powerful GPUs, we present a synthetic data-set with fully rectified stereo image pairs and accompanying accurate ground truth information that can be used for training and testing stereo algorithms. We provide validation of the quality of our dataset by performing quantitative experiments that suggest pre-training deep learning algorithms on synthetic data can perform competitively against networks trained on real life data. Testing on a real-world data-set, we found the accuracy performance difference between the real and synthetically trained networks was within a margin of 1.8%. We also illustrate the functionality synthetic data can provide, by conducting a key performance index on a selection of conventional and deep learning stereo algorithms available on embedded platforms and compared them under common metrics. © 2017 Association for Computing Machinery.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

A Gröbner Basis Approach to Solve a Rank Minimization Problem Arising in 2D-identification

引用

IFAC-PapersOnLine 2017年第1期50卷 1834-1839页

作者： Rapisarda P. Vision Learning and Control Group School of Electronics and Computer Science University of Southampton United Kingdom

The problem of state-space modelling of 2D-trajectories from exponential data can be solved using a duality approach. Finding a minimal complexity model, i.e. one having the minimal number of state variables among those unfalsified by the data, can be transformed to a rank-minimization problem involving constant matrices computed from the data. We illustrate a Gröbner basis approach to solve such problem. © 2017

关键词： 2D matrix Sylvester equation 2D systems 2D-identification rank-minimization problems Roesser models

来源：评论

学校读者我要写书评

暂无评论

Cross-dimensional weighting for aggregated deep convolutional features 14

Cross-dimensional weighting for aggregated deep convolutiona...

引用

computer vision - ECCV 2016 Workshops, Proceedings

作者： Kalantidis, Yannis Mellina, Clayton Osindero, Simon Computer Vision and Machine Learning Group Flickr Yahoo San Francisco United States

ISBN: (纸本)9783319466033

We propose a simple and straightforward way of creating powerful image representations via cross-dimensional weighting and aggregation of deep convolutional neural network layer outputs. We first present a generalized framework that encompasses a broad family of approaches and includes cross-dimensional pooling and weighting steps. We then propose specific non-parametric schemes for both spatial-and channel-wise weighting that boost the effect of highly active spatial responses and at the same time regulate burstiness effects. We experiment on different public datasets for image search and show that our approach outperforms the current state-of-the-art for approaches based on pre-trained networks. We also provide an easy-to-use, open source implementation that reproduces our results. © Springer International Publishing Switzerland 2016.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Depth Estimation for a Single Omnidirectional Image with Reversed-Gradient Warming-up Thresholds Discriminator 48

Depth Estimation for a Single Omnidirectional Image with Rev...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Wu, Yihong Heng, Yuwen Niranjan, Mahesan Kim, Hansung University of Southampton Vision Learning and Control Research Group School of Electronics and Computer Science United Kingdom

ISBN: (纸本)9781728163277

Depth estimation for single image using deep learning requires a large labelled depth dataset with various scenes for training. However, currently published omnidirectional depth datasets cover limited types of scenes and are not suitable for depth estimation for various real-world scenes. With the challenge of labelled real-world datasets generation and stability of the performance, we propose an architecture with the Reverse-gradient Warming-up Threshold Discriminator (RWTD) to estimate real-world depth maps from the synthetic ground truth. It takes labelled synthetic scenes of a source domain and unlabelled real-world scenes of a target domain as inputs to predict the corresponding depth maps. Compared with state-of-the-art encoder-decoder models, the proposed architecture shows an 11% points improvement on the testing dataset for depth accuracy. © 2023 IEEE.

关键词： Depth estimation domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Bilkent University at TRECVID 2007

Bilkent University at TRECVID 2007

引用

TREC Video Retrieval Evaluation, TRECVID 2007

作者： Aksoy, S. Duygulu, P. Aksoy, C. Aydin, E. Günaydin, D. Hadimli, K. Koç, L. Olgun, Y. Orhan, C. Yakin, G. RETINA Vision and Learning Group Department of Computer Engineering Bilkent University Bilkent 06800 Ankara Turkey

We describe our fourth participation, that includes two high-level feature extraction runs, and one manual search run, to the TRECVID video retrieval evaluation. All of these runs have used a system trained on the common development collection. Only visual information, consisting of color, texture and edge-based low-level features, was used.

关键词：

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：