Cognitive Robotics最新文献_第3页

Zero-dynamics attack detection based on data association in feedback pathway 基于反馈路径数据关联的零动态攻击检测

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2025.03.003

Zeyu Zhang , Hongran Li , Yuki Todo

This paper considers the security of non-minimum phase systems, a typical kind of cyber-physical systems. Non-minimum phase systems are characterized by unstable zeros in their transfer functions, making them particularly susceptible to disturbances and attacks. The non-minimum phase systems are more vulnerable to zero-dynamics attack (ZDA) than minimum phase systems. ZDA is a stealthy attack strategy that exploits the internal dynamics of a system, remaining undetectable while causing gradual system destabilization. Recent cyber incidents have demonstrated the increasing risk of such hidden attacks in critical infrastructures, such as power grids and transportation systems. This paper first demonstrates that the existing ZDA has the limitation of falling into local convergence, and then proposes an enhanced zero-dynamics attack (EZDA), which overcomes local convergence by diverging system data. Furthermore, this paper presents an autoregressive model which can build the data association between the original data and the forged data. By observing the fluctuations in state values, the presented model can detect not only ZDA, but also EZDA. Finally, numerical simulations and an application example are provided to verify the theoretical results.

本文研究了非最小相位系统的安全性问题，这是一种典型的网络物理系统。非最小相位系统的特征是其传递函数中存在不稳定的零，这使得它们特别容易受到干扰和攻击。非最小相位系统比最小相位系统更容易受到零动态攻击（ZDA）。ZDA是一种隐蔽的攻击策略，它利用系统的内部动态，在导致系统逐渐不稳定的同时保持不可检测。最近的网络事件表明，在电网和交通系统等关键基础设施中，这种隐性攻击的风险越来越大。本文首先论证了现有的零动态攻击算法存在陷入局部收敛的局限性，然后提出了一种增强的零动态攻击算法（EZDA），该算法通过发散系统数据来克服局部收敛问题。在此基础上，提出了一种自回归模型，可以在原始数据和伪造数据之间建立数据关联。通过观察状态值的波动，该模型不仅可以检测到ZDA，还可以检测到EZDA。最后通过数值模拟和应用实例对理论结果进行了验证。

{"title":"Zero-dynamics attack detection based on data association in feedback pathway","authors":"Zeyu Zhang , Hongran Li , Yuki Todo","doi":"10.1016/j.cogr.2025.03.003","DOIUrl":"10.1016/j.cogr.2025.03.003","url":null,"abstract":"<div><div>This paper considers the security of non-minimum phase systems, a typical kind of cyber-physical systems. Non-minimum phase systems are characterized by unstable zeros in their transfer functions, making them particularly susceptible to disturbances and attacks. The non-minimum phase systems are more vulnerable to zero-dynamics attack (ZDA) than minimum phase systems. ZDA is a stealthy attack strategy that exploits the internal dynamics of a system, remaining undetectable while causing gradual system destabilization. Recent cyber incidents have demonstrated the increasing risk of such hidden attacks in critical infrastructures, such as power grids and transportation systems. This paper first demonstrates that the existing ZDA has the limitation of falling into local convergence, and then proposes an enhanced zero-dynamics attack (EZDA), which overcomes local convergence by diverging system data. Furthermore, this paper presents an autoregressive model which can build the data association between the original data and the forged data. By observing the fluctuations in state values, the presented model can detect not only ZDA, but also EZDA. Finally, numerical simulations and an application example are provided to verify the theoretical results.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 126-139"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A transformation model for vision-based navigation of agricultural robots 农业机器人视觉导航的转换模型

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2025.03.002

Abdelkrim Abanay , Lhoussaine Masmoudi , Dirar Benkhedra , Khalid El Amraoui , Mouataz Lghoul , Javier-Gonzalez Jimenez , Francisco-Angel Moreno

This paper presents a Top-view Transformation Model (TTM) for a vision-based autonomous navigation of an agricultural mobile robot. The TTM transforms images captured by an onboard camera into a virtual Top-view, eliminating perspective distortions such as the vanishing point effect and ensuring uniform pixel distribution. The transformed images are analyzed to ensure an autonomous navigation of the robot between crop rows. The navigation method involves real-time estimation of the robot's position relative to crop rows and the control low is derived from the estimated robot's heading and lateral offset for steering the robot along the crop rows. A simulated scenario has been generated in Gazebo in order to implement the developed approach using the Robot Operating System (ROS), while an evaluation on a real agricultural mobile robot has also been performed. The experimental results demonstrate the feasibility of the TTM approach and its implementation for autonomous navigation, reaching good performance.

提出了一种基于视觉的农业移动机器人自主导航俯视图转换模型。TTM将机载摄像机拍摄的图像转换为虚拟顶视图，消除了视角失真，如消失点效应，并确保均匀的像素分布。对变换后的图像进行分析，以确保机器人在作物行之间自主导航。导航方法包括实时估计机器人相对于作物行的位置，并且根据估计的机器人的航向和横向偏移量推导出控制低，以便沿着作物行的方向操纵机器人。为了利用机器人操作系统（ROS）实现所开发的方法，在Gazebo中生成了一个模拟场景，同时对一个真实的农业移动机器人进行了评估。实验结果证明了TTM方法及其在自主导航中的可行性，取得了良好的性能。

引用次数: 0

A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries 基于磁共振成像的膝关节损伤诊断的多视图神经网络方法

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2025.05.001

Biyong Deng , Jiashan Pan , Xiaoyu Tang , Haitao Fu , Shushan Hu

The knee plays a pivotal role in the human anatomy, serving as a cornerstone for support, mobility, shock attenuation, and balance. Currently, magnetic resonance imaging (MRI) remains the preferred method for diagnosing knee injuries, including anterior cruciate ligament (ACL) tears and meniscal tears, due to its efficiency and accuracy in medical imaging. However, the interpretation and understanding of knee MRI images are time-consuming, laborious, require sufficient expertise, and are also prone to diagnostic errors. Thus, it is imperative to devise a computational method employing knee MRI for intelligent diagnosis of knee injuries, as this could expedite medical assessments by physicians, reduce costs, and substantially reduce the risk of misdiagnosis. Although several computational methods have been proposed to diagnose knee injuries, most rely heavily on local features in MRI images and exhibit low prediction accuracy. In this paper, we proposed a novel multi-view graph neural network, abbreviated as MVGNN, to identify knee injuries (specifically ACL tears and meniscal tears) by leveraging graph representations derived from multiple MRI views. Comprehensive experiments demonstrate that MVGNN achieves state-of-the-art results for diagnosing knee injuries, with a 5.9% improvement in accuracy on ACL data and a 6.5% improvement on Men data, compared to the second-best method, MVCNN.

膝关节在人体解剖学中扮演着关键的角色，是支撑、活动、减震和平衡的基石。目前，磁共振成像（MRI）仍然是诊断膝关节损伤的首选方法，包括前交叉韧带（ACL）撕裂和半月板撕裂，由于其在医学成像中的效率和准确性。然而，膝关节MRI图像的解释和理解是费时费力的，需要足够的专业知识，也容易出现诊断错误。因此，设计一种利用膝关节MRI对膝关节损伤进行智能诊断的计算方法势在必行，因为这可以加快医生的医疗评估，降低成本，并大大降低误诊的风险。虽然已经提出了几种计算方法来诊断膝关节损伤，但大多数方法严重依赖于MRI图像中的局部特征，预测精度较低。在本文中，我们提出了一种新的多视图图神经网络，简称为MVGNN，通过利用来自多个MRI视图的图表示来识别膝关节损伤（特别是ACL撕裂和半月板撕裂）。综合实验表明，与第二好的方法MVCNN相比，MVGNN在诊断膝关节损伤方面取得了最先进的结果，ACL数据的准确率提高了5.9%，Men数据的准确率提高了6.5%。

{"title":"A multi-view graph neural network approach for magnetic resonance imaging-based diagnosis of knee injuries","authors":"Biyong Deng , Jiashan Pan , Xiaoyu Tang , Haitao Fu , Shushan Hu","doi":"10.1016/j.cogr.2025.05.001","DOIUrl":"10.1016/j.cogr.2025.05.001","url":null,"abstract":"<div><div>The knee plays a pivotal role in the human anatomy, serving as a cornerstone for support, mobility, shock attenuation, and balance. Currently, magnetic resonance imaging (MRI) remains the preferred method for diagnosing knee injuries, including anterior cruciate ligament (ACL) tears and meniscal tears, due to its efficiency and accuracy in medical imaging. However, the interpretation and understanding of knee MRI images are time-consuming, laborious, require sufficient expertise, and are also prone to diagnostic errors. Thus, it is imperative to devise a computational method employing knee MRI for intelligent diagnosis of knee injuries, as this could expedite medical assessments by physicians, reduce costs, and substantially reduce the risk of misdiagnosis. Although several computational methods have been proposed to diagnose knee injuries, most rely heavily on local features in MRI images and exhibit low prediction accuracy. In this paper, we proposed a novel multi-view graph neural network, abbreviated as MVGNN, to identify knee injuries (specifically ACL tears and meniscal tears) by leveraging graph representations derived from multiple MRI views. Comprehensive experiments demonstrate that MVGNN achieves state-of-the-art results for diagnosing knee injuries, with a 5.9% improvement in accuracy on ACL data and a 6.5% improvement on Men data, compared to the second-best method, MVCNN.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 201-210"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144106866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrated model for segmentation of glomeruli in kidney images 肾脏图像中肾小球分割的集成模型

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2024.11.007

Gurjinder Kaur, Meenu Garg, Sheifali Gupta

Kidney diseases, especially those that affect the glomeruli, have become more common worldwide in recent years. Accurate and early detection of glomeruli is critical for accurately diagnosing kidney problems and determining the most effective treatment options. Our study proposed an advanced model, FResMRCNN, an enhanced version of Mask R-CNN, for automatically detecting and segmenting the glomeruli in PAS-stained human kidney images. The model integrates the power of FPN with a ResNet101 backbone, which was selected after assessing seven different backbone architectures. The integration of FPN and ResNet101 into the FResMRCNN model improves glomeruli detection, segmentation accuracy and stability by representing multi-scale features. We trained and tested our model using the HuBMAP Kidney dataset, which contains high-resolution PAS-stained microscopy images. During the study, the effectiveness of our proposed model is examined by generating bounding boxes and predicted masks of glomeruli. The performance of the FResMRCNN model is evaluated using three performance metrics, including the Dice coefficient, Jaccard index, and binary cross-entropy loss, which show promising results in accurately segmenting glomeruli.

肾脏疾病，特别是影响肾小球的疾病，近年来在世界范围内变得越来越常见。准确和早期发现肾小球对于准确诊断肾脏问题和确定最有效的治疗方案至关重要。我们的研究提出了一种先进的模型，FResMRCNN，一种增强版的Mask R-CNN，用于自动检测和分割pas染色的人肾脏图像中的肾小球。该模型将FPN的功能与ResNet101骨干网集成在一起，在评估了七种不同的骨干网架构后选择了ResNet101骨干网。将FPN和ResNet101集成到FResMRCNN模型中，通过表示多尺度特征，提高了肾小球的检测、分割精度和稳定性。我们使用HuBMAP肾脏数据集来训练和测试我们的模型，该数据集包含高分辨率pas染色显微镜图像。在研究过程中，我们提出的模型的有效性是通过生成边界框和肾小球的预测掩膜来检验的。使用Dice系数、Jaccard指数和二元交叉熵损失三个性能指标来评估FResMRCNN模型的性能，这些指标在准确分割肾小球方面显示出很好的效果。

{"title":"Integrated model for segmentation of glomeruli in kidney images","authors":"Gurjinder Kaur, Meenu Garg, Sheifali Gupta","doi":"10.1016/j.cogr.2024.11.007","DOIUrl":"10.1016/j.cogr.2024.11.007","url":null,"abstract":"<div><div>Kidney diseases, especially those that affect the glomeruli, have become more common worldwide in recent years. Accurate and early detection of glomeruli is critical for accurately diagnosing kidney problems and determining the most effective treatment options. Our study proposed an advanced model, FResMRCNN, an enhanced version of Mask R-CNN, for automatically detecting and segmenting the glomeruli in PAS-stained human kidney images. The model integrates the power of FPN with a ResNet101 backbone, which was selected after assessing seven different backbone architectures. The integration of FPN and ResNet101 into the FResMRCNN model improves glomeruli detection, segmentation accuracy and stability by representing multi-scale features. We trained and tested our model using the HuBMAP Kidney dataset, which contains high-resolution PAS-stained microscopy images. During the study, the effectiveness of our proposed model is examined by generating bounding boxes and predicted masks of glomeruli. The performance of the FResMRCNN model is evaluated using three performance metrics, including the Dice coefficient, Jaccard index, and binary cross-entropy loss, which show promising results in accurately segmenting glomeruli.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 1-13"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hybrid machine learning-based 3-dimensional UAV node localization for UAV-assisted wireless networks 基于混合机器学习的无人机辅助无线网络三维无人机节点定位

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2025.01.002

Workeneh Geleta Negassa, Demissie J. Gelmecha, Ram Sewak Singh, Davinder Singh Rathee

This paper presents a hybrid machine-learning framework for optimizing 3-Dimensional (3D) Unmanned Aerial Vehicles (UAV) node localization and resource distribution in UAV-assisted THz 6G networks to ensure efficient coverage in dynamic, high-density environments. The proposed model efficiently managed interference, adapted to UAV mobility, and ensured optimal throughput by dynamically optimizing UAV trajectories. The hybrid framework combined the strengths of Graph Neural Networks (GNN) for feature aggregation, Deep Neural Networks (DNN) for efficient resource allocation, and Double Deep Q-Networks (DDQN) for distributed decision-making. Simulation results demonstrated that the proposed model outperformed traditional machine learning models, significantly improving energy efficiency, latency, and throughput. The hybrid model achieved an optimized energy efficiency of 90 Tbps/J, reduced latency to 0.0105 ms, and delivered a network throughput of approximately 96 Tbps. The model adapts to varying link densities, maintaining stable performance even in high-density scenarios. These findings underscore the framework's potential to address key challenges in UAV-assisted 6G networks, paving the way for scalable and efficient communication in next-generation wireless systems.

本文提出了一种混合机器学习框架，用于优化无人机辅助太赫兹6G网络中的三维（3D）无人机（UAV）节点定位和资源分配，以确保在动态、高密度环境中有效覆盖。该模型有效地管理了干扰，适应了无人机的移动性，并通过动态优化无人机轨迹来保证最优吞吐量。该混合框架结合了用于特征聚合的图神经网络（GNN）、用于有效资源分配的深度神经网络（DNN）和用于分布式决策的双深度q网络（DDQN）的优势。仿真结果表明，该模型优于传统的机器学习模型，显著提高了能量效率、延迟和吞吐量。该混合模型实现了90 Tbps/J的优化能效，将延迟降低到0.0105 ms，并提供了约96 Tbps的网络吞吐量。该模型可以适应不同的链路密度，即使在高密度场景下也能保持稳定的性能。这些发现强调了该框架在解决无人机辅助6G网络关键挑战方面的潜力，为下一代无线系统的可扩展和高效通信铺平了道路。

{"title":"Hybrid machine learning-based 3-dimensional UAV node localization for UAV-assisted wireless networks","authors":"Workeneh Geleta Negassa, Demissie J. Gelmecha, Ram Sewak Singh, Davinder Singh Rathee","doi":"10.1016/j.cogr.2025.01.002","DOIUrl":"10.1016/j.cogr.2025.01.002","url":null,"abstract":"<div><div>This paper presents a hybrid machine-learning framework for optimizing 3-Dimensional (3D) Unmanned Aerial Vehicles (UAV) node localization and resource distribution in UAV-assisted THz 6G networks to ensure efficient coverage in dynamic, high-density environments. The proposed model efficiently managed interference, adapted to UAV mobility, and ensured optimal throughput by dynamically optimizing UAV trajectories. The hybrid framework combined the strengths of Graph Neural Networks (GNN) for feature aggregation, Deep Neural Networks (DNN) for efficient resource allocation, and Double Deep Q-Networks (DDQN) for distributed decision-making. Simulation results demonstrated that the proposed model outperformed traditional machine learning models, significantly improving energy efficiency, latency, and throughput. The hybrid model achieved an optimized energy efficiency of 90 Tbps/J, reduced latency to 0.0105 ms, and delivered a network throughput of approximately 96 Tbps. The model adapts to varying link densities, maintaining stable performance even in high-density scenarios. These findings underscore the framework's potential to address key challenges in UAV-assisted 6G networks, paving the way for scalable and efficient communication in next-generation wireless systems.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 61-76"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143143956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improvement of multi-parameter anomaly detection method: Addition of a relational token between parameters 改进多参数异常检测方法：在参数之间添加关系标记

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2025.03.004

Hironori Uchida , Keitaro Tominaga , Hideki Itai , Yujie Li , Yoshihisa Nakatoh

In the continuous development of systems, the increasing volume and complexity of data that engineers must analyze have become significant challenges. To address this issue, extensive research has been conducted on automated anomaly detection in logs. However, due to the limited variety of available datasets, most studies have focused on sequence-based anomalies in logs, with relatively little attention paid to parameter-based anomaly detection. To bridge this gap, we prepared a labeled dataset specifically designed for parameter-based anomaly detection and propose a novel method utilizing BERTMaskedLM. Since continuously changing logs in system development are difficult to label, we also propose a method that enables learning without labeled data. Previous studies have employed BERTMaskedLM to capture relationships between parameters in multi-parameter logs for anomaly detection. However, a known issue arises when the ranges of numerical parameters overlap, resulting in reduced detection accuracy. To mitigate this, we introduced tokens that encode the relationships between parameters, improving the independence of parameter combinations and enhancing anomaly detection accuracy (increasing the F1-score by more than 0.002). In this study, we employed a simple yet effective approach by using the total value of each token as the added token. Since only the parameter portions vary within the same log template structure, these proposed tokens effectively capture the relationships between parameters. Additionally, we visualized the influence of the added tokens and conducted experiments using a new dataset to assess the reliability of our proposed method.

在系统的不断发展中，工程师必须分析的数据量和复杂性的增加已经成为重大挑战。为了解决这个问题，人们对日志中的自动异常检测进行了广泛的研究。然而，由于可用数据集的种类有限，大多数研究都集中在基于序列的测井异常上，而对基于参数的异常检测的关注相对较少。为了弥补这一差距，我们准备了一个专门用于基于参数的异常检测的标记数据集，并提出了一种利用BERTMaskedLM的新方法。由于系统开发中不断变化的日志很难标记，我们还提出了一种方法，可以在没有标记数据的情况下进行学习。以前的研究使用BERTMaskedLM捕获多参数日志中参数之间的关系，用于异常检测。然而，当数值参数的范围重叠时，会出现一个已知的问题，导致检测精度降低。为了缓解这种情况，我们引入了对参数之间的关系进行编码的令牌，提高了参数组合的独立性，提高了异常检测的准确性（将f1分数提高了0.002以上）。在本研究中，我们采用了一种简单而有效的方法，即使用每个令牌的总价值作为添加的令牌。由于在相同的日志模板结构中只有参数部分不同，因此这些建议的令牌有效地捕获了参数之间的关系。此外，我们可视化了添加令牌的影响，并使用新的数据集进行了实验，以评估我们提出的方法的可靠性。

{"title":"Improvement of multi-parameter anomaly detection method: Addition of a relational token between parameters","authors":"Hironori Uchida , Keitaro Tominaga , Hideki Itai , Yujie Li , Yoshihisa Nakatoh","doi":"10.1016/j.cogr.2025.03.004","DOIUrl":"10.1016/j.cogr.2025.03.004","url":null,"abstract":"<div><div>In the continuous development of systems, the increasing volume and complexity of data that engineers must analyze have become significant challenges. To address this issue, extensive research has been conducted on automated anomaly detection in logs. However, due to the limited variety of available datasets, most studies have focused on sequence-based anomalies in logs, with relatively little attention paid to parameter-based anomaly detection. To bridge this gap, we prepared a labeled dataset specifically designed for parameter-based anomaly detection and propose a novel method utilizing BERTMaskedLM. Since continuously changing logs in system development are difficult to label, we also propose a method that enables learning without labeled data. Previous studies have employed BERTMaskedLM to capture relationships between parameters in multi-parameter logs for anomaly detection. However, a known issue arises when the ranges of numerical parameters overlap, resulting in reduced detection accuracy. To mitigate this, we introduced tokens that encode the relationships between parameters, improving the independence of parameter combinations and enhancing anomaly detection accuracy (increasing the F1-score by more than 0.002). In this study, we employed a simple yet effective approach by using the total value of each token as the added token. Since only the parameter portions vary within the same log template structure, these proposed tokens effectively capture the relationships between parameters. Additionally, we visualized the influence of the added tokens and conducted experiments using a new dataset to assess the reliability of our proposed method.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 176-191"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robotic terrain classification based on convolutional and long short-term memory neural networks 基于卷积和长短期记忆神经网络的机器人地形分类

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2025.04.002

YiGe Hu

Robotic mobility remains constrained by complex terrains and technological limitations, hindering real-world applications. This study presents a terrain classification framework integrating Fourier transform, adaptive filtering, and deep learning to enhance adaptability. Leveraging CNNs, LSTMs, and an attention mechanism, the approach improves feature fusion and classification accuracy. Evaluations on the Tampere University dataset demonstrate an 81 % classification accuracy, validating its effectiveness in terrain perception and autonomous navigation. The findings contribute to advancing robotic mobility in unstructured environments.

机器人的移动性仍然受到复杂地形和技术限制的制约，阻碍了现实世界的应用。本文提出了一种融合傅里叶变换、自适应滤波和深度学习的地形分类框架，以增强其自适应能力。该方法利用cnn、lstm和注意机制，提高了特征融合和分类精度。对坦佩雷大学数据集的评估表明，分类准确率达到81%，验证了其在地形感知和自主导航方面的有效性。这一发现有助于提高机器人在非结构化环境中的机动性。

引用次数: 0

Design cloud computing to monitor and controller for high voltage networks 400 KV 设计了400千伏高压电网的云计算监控和控制器

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2025.03.005

Hamed Khudair Khalil, Laith Ali Abdul Rahaim, Shamam Fadhil Alwash

A high-voltage network (400 kV) is a system that has multiple control and communication elements and acts as a link between generating stations and transmission lines; it is considered one of the smart networks. The advantage of a smart grid over a traditional utility grid is that it uses a two-way communication mechanism. The monitoring and control system for this network utilizes SCADA and RTU, but it comes at a high cost. Nonetheless, it is preferable to have a system that is economical, intelligent, and dependable. In this research, we will design a remote monitoring and control system for high-voltage networks using cloud computing technology with IoT applications that support the above-mentioned systems and can be developed in case of any expansion in electrical networks. We use this system to remotely monitor smart network equipment and control the closing and opening of breakers using protection relays and sensors. This proposed system uses the ESP 32 microcontroller to send warning signals to remote operators via the Internet, utilizing the MQTT protocol. This system utilizes the Thing Board platform in conjunction with Quick Set (5030) software, enabling control via a laptop and smartphone.

高压电网（400千伏）是一个具有多个控制和通信元件的系统，是发电厂和输电线路之间的纽带；它被认为是智能网络之一。与传统电网相比，智能电网的优势在于它使用双向通信机制。该网络的监控系统采用SCADA和RTU技术，但成本较高。尽管如此，拥有一个经济、智能和可靠的系统是可取的。在本研究中，我们将利用云计算技术和物联网应用设计一个高压网络远程监控系统，该系统支持上述系统，并且可以在电网扩容时进行开发。我们使用该系统对智能网络设备进行远程监控，并利用保护继电器和传感器控制断路器的合闸和开断。该系统采用ESP 32微控制器，利用MQTT协议，通过Internet向远程操作人员发送报警信号。该系统利用Thing Board平台与Quick Set（5030）软件相结合，通过笔记本电脑和智能手机进行控制。

{"title":"Design cloud computing to monitor and controller for high voltage networks 400 KV","authors":"Hamed Khudair Khalil, Laith Ali Abdul Rahaim, Shamam Fadhil Alwash","doi":"10.1016/j.cogr.2025.03.005","DOIUrl":"10.1016/j.cogr.2025.03.005","url":null,"abstract":"<div><div>A high-voltage network (400 kV) is a system that has multiple control and communication elements and acts as a link between generating stations and transmission lines; it is considered one of the smart networks. The advantage of a smart grid over a traditional utility grid is that it uses a two-way communication mechanism. The monitoring and control system for this network utilizes SCADA and RTU, but it comes at a high cost. Nonetheless, it is preferable to have a system that is economical, intelligent, and dependable. In this research, we will design a remote monitoring and control system for high-voltage networks using cloud computing technology with IoT applications that support the above-mentioned systems and can be developed in case of any expansion in electrical networks. We use this system to remotely monitor smart network equipment and control the closing and opening of breakers using protection relays and sensors. This proposed system uses the ESP 32 microcontroller to send warning signals to remote operators via the Internet, utilizing the MQTT protocol. This system utilizes the Thing Board platform in conjunction with Quick Set (5030) software, enabling control via a laptop and smartphone.</div></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"5 ","pages":"Pages 192-200"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143922363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

LiPE: Lightweight human pose estimator for mobile applications towards automated pose analysis LiPE：用于移动应用程序的轻量级人体姿势估计器，用于自动姿势分析

Cognitive Robotics

Pub Date : 2025-01-01 DOI: 10.1016/j.cogr.2024.11.005

Chengxiu Li , Ni Duan

Current human pose estimation models adopt heavy backbones and complex feature enhance- ment modules to pursue higher accuracy. However, they ignore the need for model efficiency in real-world applications. In real-world scenarios such as sports teaching and automated sports analysis for better preservation of traditional folk sports, human pose estimation often needs to be performed on mobile devices with limited computing resources. In this paper, we propose a lightweight human pose estimator termed LiPE. LiPE adopts a lightweight MobileNetV2 backbone for feature extraction and lightweight depthwise separable deconvolution modules for upsampling. Predictions are made at a high resolution with a lightweight prediction head. Compared with the baseline, our model reduces MACs by 93.2 %, and reduces the number of parameters by 93.9 %, while the accuracy drops by only 3.2 %. Based on LiPE, we develop a real- time human pose estimation and evaluation system for automated pose analysis. Experimental results show that our LiPE achieves high computational efficiency and good accuracy for application on mobile devices.

目前的人体姿态估计模型采用重型骨架和复杂的特征增强模块来追求更高的精度。然而，它们忽略了实际应用中对模型效率的需求。在体育教学和自动化体育分析等现实场景中，为了更好地保存传统民间体育，通常需要在计算资源有限的移动设备上进行人体姿势估计。在本文中，我们提出了一个轻量级的人体姿态估计器LiPE。LiPE采用轻量级的MobileNetV2主干进行特征提取，轻量级的深度可分离反卷积模块进行上采样。预测是在一个轻量级的预测头的高分辨率。与基线相比，我们的模型减少了93.2%的mac，减少了93.9%的参数数量，而准确率仅下降了3.2%。基于LiPE，我们开发了一个实时人体姿态估计和评估系统，用于自动姿态分析。实验结果表明，该算法具有较高的计算效率和较好的精度，适用于移动设备。

引用次数: 0

Mobile robot path planning using deep deterministic policy gradient with differential gaming (DDPG-DG) exploration 利用深度确定性策略梯度与微分博弈（DDPG-DG）探索移动机器人路径规划

Cognitive Robotics

Pub Date : 2024-01-01 DOI: 10.1016/j.cogr.2024.08.002

Shripad V. Deshpande , Harikrishnan R , Babul Salam KSM Kader Ibrahim , Mahesh Datta Sai Ponnuru

Mobile robot path planning involves decision-making in uncertain, dynamic conditions, where Reinforcement Learning (RL) algorithms excel in generating safe and optimal paths. The Deep Deterministic Policy Gradient (DDPG) is an RL technique focused on mobile robot navigation. RL algorithms must balance exploitation and exploration to enable effective learning. The balance between these actions directly impacts learning efficiency.

This research proposes a method combining the DDPG strategy for exploitation with the Differential Gaming (DG) strategy for exploration. The DG algorithm ensures the mobile robot always reaches its target without collisions, thereby adding positive learning episodes to the memory buffer. An epsilon-greedy strategy determines whether to explore or exploit. When exploration is chosen, the DG algorithm is employed. The combination of DG strategy with DDPG facilitates faster learning by increasing the number of successful episodes and reducing the number of failure episodes in the experience buffer. The DDPG algorithm supports continuous state and action spaces, resulting in smoother, non-jerky movements and improved control over the turns when navigating obstacles. Reward shaping considers finer details, ensuring even small advantages in each iteration contribute to learning.

Through diverse test scenarios, it is demonstrated that DG exploration, compared to random exploration, results in an average increase of 389% in successful target reaches and a 39% decrease in collisions. Additionally, DG exploration shows a 69% improvement in the number of episodes where convergence is achieved within a maximum of 2000 steps.

移动机器人路径规划涉及在不确定的动态条件下进行决策，而强化学习（RL）算法在生成安全和最优路径方面表现出色。深度确定性策略梯度（DDPG）是一种专注于移动机器人导航的 RL 技术。RL 算法必须兼顾利用和探索，才能实现有效学习。本研究提出了一种方法，将用于开发的 DDPG 策略与用于探索的差分博弈（DG）策略相结合。DG 算法可确保移动机器人始终在无碰撞的情况下到达目标，从而为记忆缓冲区增加积极的学习事件。ε-贪婪策略决定是探索还是利用。当选择探索时，则采用 DG 算法。将 DG 策略与 DDPG 算法相结合，可以增加经验缓冲区中成功事件的数量，减少失败事件的数量，从而加快学习速度。DDPG 算法支持连续的状态和动作空间，从而使动作更平滑、不生涩，并改善了导航障碍物时对转弯的控制。奖励塑造考虑到了更精细的细节，确保每次迭代中的微小优势也能促进学习。通过各种测试场景证明，与随机探索相比，DG 探索使成功到达目标的次数平均增加了 389%，碰撞次数减少了 39%。此外，DG探索在最多2000步内实现收敛的次数提高了69%。

{"title":"Mobile robot path planning using deep deterministic policy gradient with differential gaming (DDPG-DG) exploration","authors":"Shripad V. Deshpande , Harikrishnan R , Babul Salam KSM Kader Ibrahim , Mahesh Datta Sai Ponnuru","doi":"10.1016/j.cogr.2024.08.002","DOIUrl":"10.1016/j.cogr.2024.08.002","url":null,"abstract":"<div><p>Mobile robot path planning involves decision-making in uncertain, dynamic conditions, where Reinforcement Learning (RL) algorithms excel in generating safe and optimal paths. The Deep Deterministic Policy Gradient (DDPG) is an RL technique focused on mobile robot navigation. RL algorithms must balance exploitation and exploration to enable effective learning. The balance between these actions directly impacts learning efficiency.</p><p>This research proposes a method combining the DDPG strategy for exploitation with the Differential Gaming (DG) strategy for exploration. The DG algorithm ensures the mobile robot always reaches its target without collisions, thereby adding positive learning episodes to the memory buffer. An epsilon-greedy strategy determines whether to explore or exploit. When exploration is chosen, the DG algorithm is employed. The combination of DG strategy with DDPG facilitates faster learning by increasing the number of successful episodes and reducing the number of failure episodes in the experience buffer. The DDPG algorithm supports continuous state and action spaces, resulting in smoother, non-jerky movements and improved control over the turns when navigating obstacles. Reward shaping considers finer details, ensuring even small advantages in each iteration contribute to learning.</p><p>Through diverse test scenarios, it is demonstrated that DG exploration, compared to random exploration, results in an average increase of 389% in successful target reaches and a 39% decrease in collisions. Additionally, DG exploration shows a 69% improvement in the number of episodes where convergence is achieved within a maximum of 2000 steps.</p></div>","PeriodicalId":100288,"journal":{"name":"Cognitive Robotics","volume":"4 ","pages":"Pages 156-173"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2667241324000119/pdfft?md5=8c083de5d6ac1af9d3cedcb0733a30fa&pid=1-s2.0-S2667241324000119-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142271646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0