检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Schmidt, Fabian Blessing, Constantin Enzweiler, Markus Valada, Abhinav Institute for Intelligent Systems Esslingen University of Applied Sciences Esslingen Germany Department of Computer Science University of Freiburg Freiburg Germany

Simultaneous Localization and Mapping (SLAM) is essential for mobile robotics, enabling autonomous navigation in dynamic, unstructured outdoor environments without relying on external positioning systems. In agricultural applications, where environmental conditions can be particularly challenging due to variable lighting or weather conditions, Visual‐Inertial SLAM has emerged as a potential solution. This paper benchmarks several open‐source Visual‐Inertial SLAM systems, including ORB‐SLAM3, VINS‐Fusion, OpenVINS, Kimera, and SVO Pro, to evaluate their performance in agricultural settings. We focus on the impact of loop closing on localization accuracy and computational demands, providing a comprehensive analysis of these systems’ effectiveness in real-world environments and especially their application to embedded systems in agricultural robotics. Our contributions further include an assessment of varying frame rates on localization accuracy and computational load. The findings highlight the importance of loop closing in improving localization accuracy while managing computational resources efficiently, offering valuable insights for optimizing Visual‐Inertial SLAM systems for practical outdoor applications in mobile robotics. Copyright © 2024, The Authors. All rights reserved.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

Application of Deep Learning Method to Estimate Bottomhole Pressure Dynamics of Oil Wells 32

Application of Deep Learning Method to Estimate Bottomhole P...

引用

32nd IeeE International Symposium on Industrial Electronics, ISIE 2023

作者： Cheng, Haibo Li, Shichao Zeng, Peng Vyatkin, Valeriy State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Luleå University of Technology Electrical and Space Engineering Department of Computer Science Luleå Sweden Aalto University Department of Electrical Engineering and Automation Helsinki Finland

ISBN: (纸本)9798350399714

Surrogate models, which have become an effective and popular method to close loop reservoir management problems, use a data-driven approach to predict dynamic injection and production wells parameters and optimize waterflooding development. In this study, a deep learning-based surrogate model method is proposed to estimate bottomhole pressure (BHP) of production wells in waterflooding reservoirs. Bidirectional long short-term memory (BiLSTM) network, as an efficient deep learning approach, is applied to BHP estimation using fluctuation data. Extended Fourier amplitude sensitivity test (EFAST) method is employed to analyse the influence of different input factors on BHP dynamics, and a reduced dataset is rebuilt to predict BHP parameter based on BiLSTM-EFAST algorithm. The estimation results are tested on a dataset from Volve oilfield in North Sea, and compared with other deep learning methods. The test results indicate that the proposed method can achieve higher prediction accuracy. A reduced dataset-based approach provides a new attempt to reduce model complexity and improve calculation speed for big data-driven surrogate model in oil and gas industry. © 2023 IeeE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Retinal disorder diagnosis based on hybrid deep learning models

引用

Multimedia Tools and Applications 2025年 1-25页

作者： Sedik, Ahmed El-Shafai, Walid El-Hag, Noha A. El-Banby, Ghada M. Abd El-Samie, Fathi E. Smart Systems Engineering Laboratory College of Engineering Prince Sultan University Riyadh11586 Saudi Arabia Department of the Robotics and Intelligent Machines Faculty of Artificial Intelligence Kafrelsheikh University Kafr el-Sheikh Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt The Higher Institute of Commercial Sciences Algarbia Al Mahalla Al Kubra31951 Egypt Department of Industrial Electronics and Control Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Anomaly detection from medical images is badly needed for automated diagnosis. For example, medical images obtained with several modalities, such as magnetic resonance (MR) and confocal microscopy, need to be classified for anomaly detection. The MR images may contain tumors that need to be detected with anomaly detection techniques. In MR imaging, brain tumors are represented as areas composed of abnormal cells that need to be detected. On the other hand, confocal microscopy can be used for retinal imaging. Hence, there is a need to apply classification techniques for diagnosing diseases of the eye, such as Diabetic Retinopathy (DR), which leads to exudates in different regions of the retina. The detection of exudates is necessary for the diagnosis of DR. In this paper, two models are presented for the classification of MR and retinal images. Much research has been done in this area, but it did not achieve high accuracy of classification in an acceptable time. In addition, the previous models did not consider both types of image modalities considered in this paper. The suggested models are Convolutional Neural Network (CNN) and Convolutional Long Short-Term Memory (Conv-LSTM). They are used to classify normal and abnormal cases of both brain tumor and DR diseases. The CNN model is composed of six convolutional layers and six max-pooling layers. A soft-max activation function takes the classification decision. The proposed Conv-LSTM model is composed of three stages: pre-processing, feature extraction, and classification. The deep learning model performance is better than those of traditional networks. The CNN gives an accuracy of 94.26% for DR classification and 95.8% for brain tumor classification, while the Conv-LSTM gives the maximum accuracy of 96.41% for DR classification and 97.4% for brain tumor classification. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Confocal microscopy

来源：评论

学校读者我要写书评

暂无评论

Entropy Maximization in High Dimensional Multiagent State Spaces

Entropy Maximization in High Dimensional Multiagent State Sp...

引用

International Symposium on Multi-Robot and Multi-Agent systems (MRS)

作者： Ayhan Alp Aydeniz Enrico Marchesini Robert Loftin Kagan Tumer Collaborative Robotics and Intelligent Systems Institute Oregon State University Corvallis Oregon USA Laboratory for Information & Decision Systems Massachusetts Institute of Technology Cambridge Massachusetts USA Department of Computer Science University of Sheffield Sheffield United Kingdom

Underwater or planetary exploration are prime examples of missions that can benefit from autonomous agents working together. However, discovering effective team-level behaviors (i.e., coordinated joint actions) is challenging in these domains as agents typically receive a sparse reward (zero-or constant-for the majority of the interactions). To address this issue, intrinsic rewards encourage agents to explore diverse policies to visit the state space more effectively. Unfortunately, as the agents’ state space grows, intrinsic reward-based (i.e., curiosity) approaches become less effective as they cannot effectively distinguish a diverse set of states. In this direction, we introduce state entropy maximization for multiagent learning where agents explore using local (dense) rewards and learn to solve the coordination task by leveraging global (sparse) rewards. Because of the intrinsic ability to balance local and global rewards, our approach enables the state entropy function to remain effective in high dimensional state spaces. Experiments in tightly coupled tasks requiring complex joint actions, show that local entropy-based rewards enable agents to discover successful team behaviors in high dimensional spaces where previous hand-tuned count-based rewards fail.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Training Variational Autoencoders for Population Synthesis in Public Health with Missing Data

Training Variational Autoencoders for Population Synthesis i...

引用

IeeE International Conference on Big Data

作者： Nathan Blackthorn Andrew Arash Mahyari Ashok Srinivasan Department of Computer Science University of West Florida Pensacola FL USA Florida Institute For Human and Machine Cognition (IHMC) Pensacola FL USA Department of Intelligent Systems and Robotics University of West Florida Pensacola FL USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

The importance of social determinants of health in shaping equitable public health policies is gaining increasing recognition. Emerging data sources, such as mobility and social media data, are becoming key to public health models. However, privacy concerns often limit access to these sensitive data, as even anonymized datasets are vulnerable to deductive disclosure. A promising solution to this challenge is the use of synthetic populations, which not only safeguard privacy but also enable the exploration of various "what-if" scenarios. Most existing studies on synthetic populations assume full access to complete datasets for training. However, in many public health applications, such as census data, this assumption is unrealistic due to incomplete responses, especially regarding sensitive questions like wealth or education. This paper introduces a novel approach for training Variational AutoEncoders (VAEs) with incomplete data, without resorting to missing value imputation. Instead, the VAEs are trained solely on the observed data. Using the 2019 PUMS dataset for Florida, we successfully train VAEs to generate diverse and flexible synthetic populations. By comparing marginal distributions and utilizing t-SNE for analysis, the results highlight the effectiveness of this method in addressing missing data challenges. This work demonstrates the potential of VAEs in generating synthetic populations for health research, even when complete datasets are unavailable, thereby offering a robust solution to advance public health studies while preserving data privacy.

关键词： Training Data privacy Privacy Social networking (online) Soft sensors Autoencoders Refining Imputation Data models Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Targeted Image Transformation for Improving Robustness in Long Range Aircraft Detection

Targeted Image Transformation for Improving Robustness in Lo...

引用

IeeE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Rebecca Martin Clement Fung Nikhil Keetha Lujo Bauer Sebastian Scherer School of Computer Science Robotics Institute Carnegie Mellon University Pittsburgh PA USA School of Computer Science Software and Societal Systems Department Carnegie Mellon University Pittsburgh PA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

In the field of aviation, the Detect and Avoid (DAA) problem deals with incorporating collision avoidance capabilities into current autopilot navigation systems. As an application of the Small Object Detection (SOD) problem, DAA presents the difficulties of a low signal-to-noise ratio and far range detection. Visual DAA is also susceptible to changing weather and lighting conditions at deployment. While current literature has presented many solutions for this, prior work has yet to study the robustness of the learning-based models for DAA. In this work, we show that standard techniques for improving robustness for object detection do not produce the desired results for DAA given the SOD constraints. We present targeted transformations, a zero-shot technique that can significantly improve robustness with minimal impact on accuracy. We demonstrate how to construct these transformations and evaluate our method on the current SOTA model for DAA, showing a 53.6% increase in recall. This makes our pipeline more robust to changes in lighting and environmental factors, and better able to detect potential threats. In the future, we hope to automate the transformation selection process, making it easier to adopt in different use cases.

关键词： Visualization Navigation Pipelines Lighting LoRa Object detection Robustness Standards Signal to noise ratio Meteorology

来源：评论

学校读者我要写书评

暂无评论

Efficient Learning of High Level Plans from Play

Efficient Learning of High Level Plans from Play

引用

IeeE International Conference on robotics and Automation (ICRA)

作者： Núria Armengol Urpí Marco Bagatella Otmar Hilliges Georg Martius Stelian Coros Department of Computer Science ETH Zurich Switzerland Max Planck Institute for Intelligent Systems Tübingen Germany

Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goals. Although deep reinforcement learning (RL) methods have shown encouraging results when planning end-to-end in high-dimensional environments, they remain fundamentally limited by poor sample efficiency due to inefficient exploration, and by the complexity of credit assignment over long horizons. In this work, we present Efficient Learning of High-Level Plans from Play (ELF-P), a framework for robotic learning that bridges motion planning and deep RL to achieve long-horizon complex manipulation tasks. We leverage task-agnostic play data to learn a discrete behavioral prior over object-centric primitives, modeling their feasibility given the current context. We then design a high-level goal-conditioned policy which (1) uses primitives as building blocks to scaffold complex long-horizon tasks and (2) leverages the behavioral prior to accelerate learning. We demonstrate that ELF-P has significantly better sample efficiency than relevant baselines over multiple realistic manipulation tasks and learns policies that can be easily transferred to physical hardware.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interaction-aware Maneuver Prediction for Autonomous Vehicles using Interaction Graphs

Interaction-aware Maneuver Prediction for Autonomous Vehicle...

引用

IeeE Symposium on intelligent Vehicle

作者： Iago Pachêco Gomes Cristiano Premebida Denis Fernando Wolf Institute of Mathematics and Computer Science University of São Paulo Brazil Department of Electrical and Computer Engineering Institute of Systems and Robotics University of Coimbra Portugal

Intention prediction (IP) is a challenging task for intelligent vehicle’s perception systems. IP provides the likelihood, or probability, of a target vehicle to perform a maneuver subjected to a finite set of possibilities. There are many factors that influence the decision-making process of a driver, which should be considered in a prediction framework. In addition, the lack of labeled large-scale dataset with maneuver annotation imposes another challenge to the task. This paper proposes an Interaction-aware Maneuver Prediction framework, called IAMP, using interaction graphs to extract complex interaction features from traffic scenes. In addition, we explored a semi-supervised approach called Noisy Student to take advantage of unlabeled data in the training step. Experimental results show relevant improvement when using unlabeled data, increasing the average performance of a classifier by 7.17% of accuracy. Moreover, this approach also made it possible to obtain an intention predictor with similar results to a classifier., even when using a shorter observation horizon.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Safe Multiagent Coordination via Entropic Exploration

arXiv

引用

arXiv 2024年

作者： Aydeniz, Ayhan Alp Marchesini, Enrico Loftin, Robert Amato, Christopher Tumer, Kagan Khoury College of Computer Sciences Northeastern University BostonMA United States Laboratory for Information & Decision Systems Massachusetts Institute of Technology CambridgeMA United States Department of Computer Science University of Sheffield Sheffield United Kingdom Collaborative Robotics and Intelligent Systems Institute Oregon State University CorvallisOR United States

Many real-world multiagent learning problems involve safety concerns. In these setups, typical safe reinforcement learning algorithms constrain agents’ behavior, limiting exploration—a crucial component for discovering effective cooperative multiagent behaviors. Moreover, the multiagent literature typically models individual constraints for each agent and has yet to investigate the benefits of using joint (team) constraints. In this work, we analyze these team constraints from a theoretical and practical perspective and propose entropic exploration for constrained multiagent reinforcement learning (E2C) to address the exploration issue. E2C leverages observation entropy maximization to incentivize exploration and facilitate learning safe and effective cooperative behaviors. Experiments across increasingly complex domains show that E2C agents match or surpass common unconstrained and constrained baselines in task performance while reducing unsafe behaviors by up to 50%. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Interaction-Aware Maneuver Intention Prediction Using Gated Mixture-of-Experts Attention Mechanism

Interaction-Aware Maneuver Intention Prediction Using Gated ...

引用

International Conference on intelligent Transportation

This paper addresses the task of predicting the behavior of traffic participants, which involves complexities such as road geometry and agent interactions. To overcome these challenges, this paper presents a novel framework called AIMP (Attention-based Interaction-aware Maneuver Prediction). AIMP utilizes interaction graphs to extract intricate interaction features from traffic scenes. The framework incorporates a Gated Mixture-of-Experts Attention Mechanism, which combines information from road geometry, interaction patterns, and motion dynamics. This fusion process also considers prior maneuver intention estimations, enhancing both explainability and informativeness. Experimental results highlight a performance enhancement (approximately 2% ∼ 9% of accuracy) of the proposed AIMP framework compared to alternative fusion methods.

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：