Engineering Applications of Artificial Intelligence最新文献_第2页

Coordinated deep policy learning for frequency-Constrained energy management for second-to-second energy balancing of microgrids 微电网秒到秒能量平衡中频率约束能量管理的协调深度策略学习

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-19 DOI: 10.1016/j.engappai.2025.111479

Kiavash Parhizkar, Borzou Yousefi, Mohammad Rezvani, Abdolreza Noori Shirazi

{"title":"Coordinated deep policy learning for frequency-Constrained energy management for second-to-second energy balancing of microgrids","authors":"Kiavash Parhizkar, Borzou Yousefi, Mohammad Rezvani, Abdolreza Noori Shirazi","doi":"10.1016/j.engappai.2025.111479","DOIUrl":"10.1016/j.engappai.2025.111479","url":null,"abstract":"<div><div>Hybrid microgrids (HMGs) are susceptible to frequency distractions due to their low-inertia and randomness of renewable resources. The traditional energy management systems (EMSs) and linear controllers have difficulty dealing with the uncertainty prevalent within the system due to nonlinearity and time-based conditions. This necessitates considering short-term imbalances in HMGs while the intermittency of renewable resources can highly affect the second-to-second time frame of the power system. To address this issue, this work proposes two stage frameworks for an HMG with second-to-second power imbalances: <em>i</em>) an efficient energy management system is developed to reduce costs and to improve reliability of microgrids. The proximal policy optimization (PPO) with actor and critic neural networks is utilized to solve EMS problem, <em>ii</em>) a secondary controller based on the non-linear backstepping controller (NBC) is developed to mitigate the dynamic fluctuations of frequency deviation. In this application, the IEEE 39-bus is considered as the benchmark system to study second-to-second power imbalances in the HMGs. The risk of bottlenecks for the test-system with various risk indices is calculated. Transient simulations of the HMG reveal the improvement of operation of the power system from security and stability point of view. The comparison analysis with the prevalent scheme demonstrates the suggested NBC scheme can provide a higher level of stability than prevalent state-of-the-art controllers.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"158 ","pages":"Article 111479"},"PeriodicalIF":7.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144312543","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Graph diffusion network for multi-agent reinforcement learning in drone swarm exploration 无人机群探索中多智能体强化学习的图扩散网络

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-19 DOI: 10.1016/j.engappai.2025.111322

Zhiling Jiang, Chenyang Zhang, Zhan Shi, Guanghua Song

{"title":"Graph diffusion network for multi-agent reinforcement learning in drone swarm exploration","authors":"Zhiling Jiang, Chenyang Zhang, Zhan Shi, Guanghua Song","doi":"10.1016/j.engappai.2025.111322","DOIUrl":"10.1016/j.engappai.2025.111322","url":null,"abstract":"<div><div>Drone swarm exploration has wide applications in rescue operations and engineering surveying. A drone swarm is a multi-agent system, and applying multi-agent reinforcement learning to such a system is an attractive topic in the field of robotics. In this paper, we propose a multi-agent reinforcement learning model that can chain-aggregate information from agents and apply it to the drone swarm via the Robot Operating System (ROS2). This model not only helps agents aggregate information with their neighbors but also enables the swarm to establish an organized structure, facilitating better cooperation and improving overall swarm performance. The model performs well in multi-drone exploration tasks, even in the presence of instability within the swarm. Experimental results demonstrate that the model enables effective cooperation among drones and achieves better global performance. Furthermore, we implemented the strategy based on our model on a physical platform to realize drone swarm exploration tasks. Although the cameras mounted on the drones have limited resolution, the swarm’s numerical advantage allows for high-quality exploration images, and the system outperforms other methods in terms of exploration efficiency and real-time data performance.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"158 ","pages":"Article 111322"},"PeriodicalIF":7.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research, application, and challenges of causal inference in industrial fault diagnosis: A survey 因果推理在工业故障诊断中的研究、应用与挑战综述

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-19 DOI: 10.1016/j.engappai.2025.111376

Bo Li , Qiang Li , Tingfeng Du , Dong Liu , Qiang Yang , Tianxiang Chen , Jing Xiong , Bo Peng , Junxiao Ren , Ji Zhao

{"title":"Research, application, and challenges of causal inference in industrial fault diagnosis: A survey","authors":"Bo Li , Qiang Li , Tingfeng Du , Dong Liu , Qiang Yang , Tianxiang Chen , Jing Xiong , Bo Peng , Junxiao Ren , Ji Zhao","doi":"10.1016/j.engappai.2025.111376","DOIUrl":"10.1016/j.engappai.2025.111376","url":null,"abstract":"<div><div>Industrial fault diagnosis technologies leveraging convolutional neural networks and other advanced neural network architectures are pivotal for ensuring stable equipment operation, enhancing production efficiency, and minimizing maintenance costs. Nevertheless, these methods encounter inherent challenges due to data constraints and the complexity of production environments, particularly in identifying fault root causes and ensuring the interpretability of models. The integration of causal inference into industrial fault diagnosis offers significant promise for elucidating fault propagation pathways, revealing causal interrelations within complex systems, and advancing model interpretability. This survey presents a holistic review of research trajectories, pivotal technologies, and methodological advancements in causal inference for industrial fault diagnosis while systematically delineating the advantages and prospective challenges in this domain. First, this paper examines the limitations of conventional machine-learning approaches in fault diagnosis and traces the evolutionary trajectory of causal inference development in this context. Subsequently, the core theories and foundational technologies underpinning causal inference in industrial fault diagnosis are comprehensively discussed. Following this, the survey categorizes the existing literature according to different causal inferences to solve specific problems in industrial fault diagnosis and delves into detailed case studies, underscoring their utility in addressing distinct challenges. Finally, this survey synthesizes insights from existing literature to encapsulate the merits of causal inference in industrial fault diagnosis and to elucidate the prospective challenges it may encounter.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"158 ","pages":"Article 111376"},"PeriodicalIF":7.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A novel facial expression recognition method based on cross direction attention network 一种基于交叉方向注意网络的面部表情识别方法

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-19 DOI: 10.1016/j.engappai.2025.111229

Cheng Peng , Guodong Li , Likang Lin , Bowen Zhang , Kun Zou , Sio Long Lo , Ah Chung Tsoi

{"title":"A novel facial expression recognition method based on cross direction attention network","authors":"Cheng Peng , Guodong Li , Likang Lin , Bowen Zhang , Kun Zou , Sio Long Lo , Ah Chung Tsoi","doi":"10.1016/j.engappai.2025.111229","DOIUrl":"10.1016/j.engappai.2025.111229","url":null,"abstract":"<div><div>Facial expression recognition (FER) is an area of growing interest in computer vision research. This paper extends the framework provided by the ‘Distract your Attention Network’ (DAN) which consists of multiple parallel branches, each branch composes of a spatial attention (SA) module followed by a channel attention (CA) module, and then these multiple branches are fused together before being passed into a classifier module. The spatial attention module of DAN has an internal channel dimension of 1, while our proposed Cross Directional Attention Network (CDAN)-I and CDAN-II contain respectively an internal channel dimension of 512 (same as the channel dimension of the input), and internal channel dimension of 1024 (double that of the channel dimension of the input). These increases in internal channel dimension allow extraction of more features, before they are being made to conform with the input channel dimension. Despite these seemingly simple modifications from that of DAN, both CDAN-I and CDAN-II are found to outperform those of DAN, a state-of-the-art FER method, on four popular FER benchmark datasets: RAF-DB (Real world Affective Face-database), AffectNet-7 (AffectNet with Seven Categories) AffectNet-8 ( AffectNet with Eight Categories), and CK+ (Cohn–Kanada Extended). Moreover, we make use of three statistical indexes for clustering analysis, and verified that the CDAN-I and CDAN-II modules have been able to increase the inter-cluster distances, and decrease the intra-cluster distances, when compared with those obtained by the backbone ResNet-18 network (Residual Network with 18 Layers) , thus providing a quantitative analysis technique in this area.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"157 ","pages":"Article 111229"},"PeriodicalIF":7.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321619","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generative Agent-Based Modeling with Large Language Models for insider threat detection 基于生成代理的大型语言模型内部威胁检测建模

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-19 DOI: 10.1016/j.engappai.2025.111343

Antonino Ferraro , Gian Marco Orlando , Diego Russo

{"title":"Generative Agent-Based Modeling with Large Language Models for insider threat detection","authors":"Antonino Ferraro , Gian Marco Orlando , Diego Russo","doi":"10.1016/j.engappai.2025.111343","DOIUrl":"10.1016/j.engappai.2025.111343","url":null,"abstract":"<div><div>Insider threats pose a critical challenge in cybersecurity, as individuals within organizations misuse legitimate access to compromise sensitive systems and data. Traditional detection methods often struggle with the complexity of such threats, while Deep Learning (DL) approaches face issues like overfitting and lack of interpretability. To address these limitations, we propose a Generative Agent-Based Modeling (GABM) framework that integrates Large Language Models (LLMs) with a hierarchical multi-agent system.</div><div>Our framework employs Specialized Agents to process categorized log files and generate detailed reports, which are synthesized by a Supervisor Agent for final activity classification. We validated this approach on both network-centric (PicoDomain) and behavior-rich (CERT r5.2) datasets, demonstrating its ability to handle diverse logs, model complex threats, and generalize across insider risk scenarios.</div><div>The framework outperformed existing baselines, prioritizing high recall to minimize false negatives—crucial in cybersecurity contexts. While precision was comparatively lower, this trade-off supports early threat detection. An ablation study highlighted the importance of the Supervisor Agent, whose removal led to a significant drop in performance and increased false positives.</div><div>These results demonstrate the potential of LLM-powered hierarchical multi-agent frameworks for scalable, interpretable, and reliable insider threat detection. Our contributions include the integration of GABM and LLMs, a hierarchical system for log analysis, and the use of Chain-of-Thought reasoning for enhanced interpretability.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"157 ","pages":"Article 111343"},"PeriodicalIF":7.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cascaded dimensionality reduction nonnegative matrix factorization for data representation 数据表示的级联降维非负矩阵分解

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-19 DOI: 10.1016/j.engappai.2025.111264

Yulei Huang , Jinlin Ma , Ziping Ma , Ke Lu

{"title":"Cascaded dimensionality reduction nonnegative matrix factorization for data representation","authors":"Yulei Huang , Jinlin Ma , Ziping Ma , Ke Lu","doi":"10.1016/j.engappai.2025.111264","DOIUrl":"10.1016/j.engappai.2025.111264","url":null,"abstract":"<div><div>Nonnegative matrix factorization (NMF), as a powerful dimensionality reduction technique, has attracted considerable attention for its excellent interpretability by utilizing relatively few linear combinations of basis vectors to represent the original data. The performance of its dimensionality reduction is affected by the quality and efficiency of finding a suitable collection of basis vectors. However, traditional NMF methods focus more on mining discriminative features rather than the quantity and quality of basis vectors. This may result in uncontrolled dimensionality and make it difficult to identify suitable basis vector sets, which can effectively capture the latent structure in the data. To alleviate these issues, we propose a cascaded dimensionality reduction nonnegative matrix factorization (CDRNMF) method. CDRNMF demonstrates distinctive attributes that differ from existing work as follows. (1) It subtly incorporates a feature selection mechanism into NMF, thereby establishing a novel cascaded dimensionality reduction framework that effectively retains the most representative features. (2) The dimensionality uncontrollability is effectively alleviated by constructing a feature selection matrix to assess and select basis vectors. (3) An optimization method is designed for solving CDRNMF efficiently. Numerical experiments validate that the performance of CDRNMF outperforms other state-of-the-art algorithms.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"158 ","pages":"Article 111264"},"PeriodicalIF":7.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A semi-supervised dual-path model for underground defect detection 地下缺陷检测的半监督双路径模型

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-19 DOI: 10.1016/j.engappai.2025.111493

Shaoxiang Zeng , Gengxin Wang , Honglei Sun , Yuanqin Tao , Xiaodong Pan

{"title":"A semi-supervised dual-path model for underground defect detection","authors":"Shaoxiang Zeng , Gengxin Wang , Honglei Sun , Yuanqin Tao , Xiaodong Pan","doi":"10.1016/j.engappai.2025.111493","DOIUrl":"10.1016/j.engappai.2025.111493","url":null,"abstract":"<div><div>Ground penetrating radar (GPR) is widely used for detecting underground cavities due to its continuous, non-destructive, and high-precision capabilities. However, the interpretation of GPR images largely relies on manual efforts, which are inefficient and subjective. This study proposes a semi-supervised deep learning model based on You Only Look Once version 8 (YOLOv8) for detecting underground targets, particularly voids and cavities. The proposed YOLOv8 model features a dual-path architecture. Specifically, the attention-enhanced path integrates a convolutional block attention module (CBAM) to focus on key features for precision, while the lightweight path utilizes the MobileNet to reduce model parameters for efficiency. A two-stage data augmentation method is proposed. First, the dual-path YOLOv8 model is pre-trained using real radar images and simulated images generated from physics-based numerical simulations. Then, the pre-trained model assigns pseudo-labels to unlabeled data produced by a cycle-consistent generative adversarial network (CycleGAN). These pseudo-labeled data are then incorporated into the training dataset to further enhance the proposed YOLOv8 model. An engineering example from Hangzhou, China, validates the effectiveness of the proposed model. The results show that the proposed YOLOv8 model outperforms alternative models in terms of accuracy and efficiency. The detection accuracy of the proposed model is improved by incorporating numerical simulation data and is further enhanced when pseudo-labeled data are added. In addition, the high-quality dataset established in this study provides valuable resources for future research on underground target detection.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"158 ","pages":"Article 111493"},"PeriodicalIF":7.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144312542","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust broad learning system with parametrized variational mode decomposition for schizophrenia diagnosis 用于精神分裂症诊断的参数化变分模分解鲁棒广义学习系统

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-19 DOI: 10.1016/j.engappai.2025.111294

Sebamai Parija , Mrutyunjaya Sahani , Susanta Kumar Rout

{"title":"Robust broad learning system with parametrized variational mode decomposition for schizophrenia diagnosis","authors":"Sebamai Parija , Mrutyunjaya Sahani , Susanta Kumar Rout","doi":"10.1016/j.engappai.2025.111294","DOIUrl":"10.1016/j.engappai.2025.111294","url":null,"abstract":"<div><div>Schizophrenia (SZ) is a significant mental disorder characterized by various neurophysiological and cognitive impairments. Early diagnosis remains challenging due to its reliance on symptom detection. However, advance signal processing algorithm is combined with machine learning technique for early detection of schizophrenia using electroencephalogram (EEG) signals efficaciously. To optimize results from biomedical signals, effective feature extraction (FE) and feature engineering are essential. In this study, parametrized variational mode decomposition (PVMD) is applied to electroencephalogram (EEG) signals to extract band-limited intrinsic mode functions (BLIMFs), which are selected using fuzzy dispersion entropy (FDE). The extracted BLIMFs are fed into deep stack autoencoder (DSAE) with a minimum reconstruction error, utilizing root mean square (RMS) as the cost function. We also demonstrate how to apply the robust broad learning system (RBLS) to classify neuro-disorders, comparing it with various broad learning system (BLS) methods for schizophrenia classification. Building on RBLS’s success, we propose a novel VMD-based BLS (VMD-BLS) technique. To address VMD-BLS’s limitations, we introduce a PVMD-DSAE based RBLS (PVMD-DSAE-RBLS). The effectiveness of PVMD-DSAE-RBLS is tested on three datasets, with results showing accuracies of 99.98%, 96.91% and 99.29% for the Poland, Kaggle, and Moscow datasets, respectively. The performance of the proposed PVMD-DSAE-RBLS method significantly outperforms compared to similar learning algorithms and state-of-the-art techniques. Finally, a reconfigurable high-speed field-programmable gate array (FPGA) embedded processor is implemented to design a computer-aided diagnosis (CAD) system, providing efficient automated diagnosis for schizophrenia patients.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"158 ","pages":"Article 111294"},"PeriodicalIF":7.5,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313670","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

An explainable artificial intelligence driven fall system for sensor data analysis enhanced by butterworth filtering 一个可解释的人工智能驱动的传感器数据分析下降系统，由巴特沃斯滤波增强

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-18 DOI: 10.1016/j.engappai.2025.111364

Shalini J., Ashok Kumar L.

{"title":"An explainable artificial intelligence driven fall system for sensor data analysis enhanced by butterworth filtering","authors":"Shalini J., Ashok Kumar L.","doi":"10.1016/j.engappai.2025.111364","DOIUrl":"10.1016/j.engappai.2025.111364","url":null,"abstract":"<div><div>The detection of falls is an essential component of healthcare monitoring systems, especially for older people at a greater risk of falling than younger people. To address the shortcomings of previously established methodologies, this research proposes a unique Artificial Intelligence driven sensor-based methodology that utilizes the SisFall dataset in conjunction with a Recurrent Neural Network - Long Short-Term Memory model. Two methods were considered: one using a Butterworth filter and the other without filtering. The results emphasize the significance of noise reduction in enhancing model performance. Additionally, the integration of Explainable Artificial Intelligence techniques brings transparency and interpretability to the model’s predictions, enhancing its dependability and trustworthiness in healthcare applications. Using Artificial Intelligence driven fall detection with Explainable Artificial Intelligence for transparent decision-making, this methodology presents a robust approach to improving accuracy and reducing false alarms in real-world healthcare settings. The study demonstrates that combining advanced filtering techniques with Explainable Artificial Intelligence algorithms successfully overcomes the challenges associated with traditional fall detection systems. The findings further confirm that the application of an Artificial Intelligence based Butterworth filter significantly enhances model accuracy, achieving 98.96% compared to 79.77% without filtering. These findings highlight the potential of Artificial Intelligence driven fall detection systems in healthcare, paving the way for more accurate, interpretable, and reliable monitoring solutions that can enhance elderly safety and improve real-time clinical decision-making.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"158 ","pages":"Article 111364"},"PeriodicalIF":7.5,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Formal verification for multi-agent path execution in stochastic environments 随机环境下多智能体路径执行的形式化验证

IF 7.5 2区计算机科学

Engineering Applications of Artificial Intelligence Pub Date : 2025-06-18 DOI: 10.1016/j.engappai.2025.111266

Xia Wang , Jun Liu , Chris D. Nugent , Shaobing Xu , Yang Xu

{"title":"Formal verification for multi-agent path execution in stochastic environments","authors":"Xia Wang , Jun Liu , Chris D. Nugent , Shaobing Xu , Yang Xu","doi":"10.1016/j.engappai.2025.111266","DOIUrl":"10.1016/j.engappai.2025.111266","url":null,"abstract":"<div><div>Multi-agent pathfinding aims to determine conflict-free paths for multiple agents in a shared environment. However, real-world uncertainties can disrupt preplanned paths, leading to delays and new conflicts. Addressing these challenges requires robust strategies for path execution and adjustment. While many multi-agent pathfinding algorithms have been proposed, this work does not introduce a new algorithm. Instead, it presents an adjustment solution based on a set of constraint rules and a priority strategy to avoid conflicts and deadlocks. Additionally, a Markov decision process model is developed, derived from the preplanned paths, and integrated with the adjustment solution to account for stochastic environmental uncertainties. A novel integrated framework is proposed for formally analyze and verify the reliability of multi-agent path execution and the robustness of the adjustment solution in stochastic environments, with formal verification achieved through a logic-based probabilistic model checker. The performance of the proposed framework is validated through various scenarios on the Flatland platform. Results demonstrate that the adjustment solution, based on the constraint rules, effectively mitigates conflicts and deadlocks, improving robustness. Furthermore, formal verification proves effective in assessing the reliability and robustness of multi-agent path execution under uncertainty.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"158 ","pages":"Article 111266"},"PeriodicalIF":7.5,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0