检索结果-内蒙古大学图书馆

Autonomous parking method based on improved A* a*algorithm and model predictive control

NONLINEAR DYNAMICS 2025年第7期113卷 6839-6862页

作者： Meng, Qinghua Qian, Chunjiang Sun, Zong-Yao Zhao, Shencheng Hangzhou Dianzi Univ Sch Mech Engn Hangzhou Peoples R China Univ Texas San Antonio Coll Engn San Antonio TX 78249 USA Qufu Normal Univ Inst Automat Qufu Peoples R China

To improve the search efficiency, smoothness, and parking path tracking accuracy of the existing parking methods, we propose a novel autonomous parking method based on A* a*algorithm, Bezier curve, and model predictive control (MPC) method. Firstly, a vehicle's low-speed kinematics model is constructed which describes the relationship between the front wheel and rear wheel to obtain the velocity of the rear wheel and the heading angle which is necessary for parking. Then, the vehicle parking environment is introduced for constructing three parking scenarios. An improved A* autonomous parking path planning a*algorithm is presented. This a*algorithm adopts a novel cost evaluation function to address the issue of excessive search nodes to enhance search efficiency. Meanwhile, to ensure the continuity and comfort of the planned path curvature, a third-order Bezier curve is used to smooth the planned path. Based on the established vehicle kinematics model, a first-order holder-based MPC method for autonomous parking path tracking control is proposed to realize autonomous parking with higher tracking accuracy. Finally, simulations and tests are conducted to certify the proposed autonomous parking method. The results verify that our method has significant improvement in theory and practice.

关键词： Motion control A* a*algorithm Autonomous parking Model predictive control Bezier curve

来源：评论

学校读者我要写书评

暂无评论

Adaptive multivariable super-twisting a*algorithm for trajectory tracking of AUV under unknown disturbances

引用

OCEAN ENGINEERING 2025年 317卷

作者： Shi, Wendian Yang, Gang Tian, Haichuan Lu, Lu Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan 430074 Hubei Peoples R China Naval Univ Engn Natl Key Lab Electromagnet Energy Wuhan 430030 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China

Autonomous underwater vehicles (AUV) have been widely used in underwater missions. The motion model of AUV is affected by factors such as parameter uncertainty and disturbances from ocean environment. How to accurately track trajectories under unknown disturbances is a crucial issue. In this paper, an adaptive multivariable super-twisting a*algorithm (AMSTA) with a nonlinear extended state observer (NLESO) is developed for autonomous underwater vehicles (AUV) to reduce the trajectory tracking error and address the problem of unknown disturbance. First, a novel finite-time extended state observer is designed to estimate and compensate the uncertain nonlinear disturbance. Second, this research presents an improved adaptive multivariable super-twisting a*algorithm via Lyapunov theory to address the trajectory tracking problem. Finally, simulation results demonstrated the effectiveness and superiority of the proposed scheme.

关键词： Nonlinear extended state observer Adaptive super-twisting a*algorithm Sliding mode control Trajectory tracking Nonlinear disturbance compensation

来源：评论

学校读者我要写书评

暂无评论

Multi-AGV multitask collaborative scheduling based on an improved ant colony a*algorithm

引用

INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS 2025年第1期22卷

作者： Zhu, Yazhen Song, Qing Li, Meng Univ Jinan Sch Elect Engn 336 Nanxinzhuang West Rd Jinan 250022 Peoples R China

Research on multitask scheduling systems in factory environments is a popular topic in the field of intelligent manufacturing. Existing research mainly focuses on the optimization of automated guided vehicle (AGV) path planning and scheduling, emphasizing on the minimization of conflicts and deadlocks, multi-objective task scheduling, and metaheuristic a*algorithm optimization, while ignoring path stability and real-time path planning in dynamic environments. Therefore, this paper aims to address these issues to better handle dynamic changes in actual operating environments. This paper establishes a mathematical model with the optimization objective of minimizing the overall running time of material distribution tasks and proposes an improved ant colony a*algorithm to optimize the model. First, the concept of prior time is introduced to improve the traditional ant colony a*algorithm. The path of the ongoing task is introduced with a time calculation, and the occupancy time window of each grid point on the path is calculated. Based on this, the initial pheromone distribution on subsequent paths is altered dynamically, which accelerates the convergence of the ants to a collision-free path. Second, in the pheromone update stage, the method of calculating the pheromone increment in the traditional ant colony a*algorithm is modified. The original distance influence factor is changed to a time influence factor, which ensures that all tasks still have the minimum running time when calculating a collision-free path. Finally, through 30 sets of simulation experiments on material distribution tasks, it is shown that the proposed a*algorithm shortens the total running time by 15.14%, 12.87%, and 10.59% compared to two ant colony a*algorithms and one strategic multi-AGV scheduling a*algorithm, respectively, thus verifying the effectiveness of the proposed method.

关键词： Multiple automated guided vehicles multitask scheduling ant colony a*algorithm prior time optimization

来源：评论

学校读者我要写书评

暂无评论

Fractional Order PID Controller Design for an AVR System Using the Artificial Hummingbird Optimizer a*algorithm

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 2025年第0期 3919-3943页

作者： Bouguenna, Elouahab Ladaci, Samir Lekouaghet, Badis Merrouche, Walid Benghanem, Mohamed CDER Renewable Energy Dev Ctr Algiers Algeria Natl Polytech Sch Dept Elect Algiers Algeria Res Ctr Ind Technol CRTI Algiers Algeria Islamic Univ Madinah Fac Sci Dept Phys Madinah Saudi Arabia

Optimizing the fractional-order PID (FOPID) controller using metaheuristic a*algorithms has gained significant popularity across various engineering domains. This paper introduces a novel approach by employing the artificial hummingbird a*algorithm (AHA), an innovative optimization technique inspired by the unique flight and foraging behaviors of hummingbirds, to fine-tune the FOPID controller for the automatic voltage regulator (AVR) system in synchronous generators, a critical component in maintaining voltage stability. The proposed method is rigorously tested using MATLAB/Simulink simulations under challenging conditions, including nonsmoothed higher-order dynamics of the control plant, parameter variations, time delays, and nonlinearities. The effectiveness of the AHA-based FOPID control strategy on the AVR system is comprehensively evaluated through extensive tests and analyses, focusing on aspects such as transient response, robustness, stability, and trajectory tracking. Moreover, a comparative assessment against established optimization a*algorithms, namely particle swarm optimization (PSO), genetic a*algorithm (GA), gray wolf optimizer (GWO), and artificial bee colony (ABC) is conducted. The results demonstrate the superiority of the proposed AHA-based FOPID control strategy, which significantly increases convergence speed. This is evidenced by a 25% faster rise time and a 45.74% shorter settling time compared to the GA-FOPID controller, the closest in performance for these metrics. Additionally, the AHA-based FOPID controller achieves a 92% reduction in steady-state oscillations compared to the ABC-FOPID controller, the nearest competitor in this aspect. These improvements highlight the AHA-based FOPID controller's superior efficiency and rapid response in achieving optimal performance. Hence, the proposed method shows remarkable success in enhancing stability and robustness, making it highly suitable for the design of practical high-performance applications.

关键词： artificial hummingbird a*algorithm automatic voltage regulator fractional order PID controller metaheuristic a*algorithm optimization

来源：评论

学校读者我要写书评

暂无评论

An adaptive IRS adjusting a*algorithm aids communication in heterogeneous cognitive radio networks

引用

AIN SHAMS ENGINEERING JOURNAL 2025年第5期16卷

作者： Zhu, Xiaoying Wang, Shi Xu, Xiaohui Lou, Yi Sun, Hao Liaoning Tech Univ Sch Elect & Informat Engn Fuxin Liaoning Peoples R China Harbin Inst Technol Weihai Coll Informat Sci & Engn Weihai Peoples R China

In this paper, we present an adaptive intelligent reflecting surfaces (IRS) adjusting a*algorithm designed to enhance the communication quality of secondary users (SUs) within heterogeneous cognitive radio networks (CRNs), using a cross-layer analysis approach. Initially, a Markov model is established based on queue analysis of SUs' buffer. Subsequently, to optimize the diagonal reflection coefficient matrix of the IRS, we derive the key objectives of the established multi-objective optimization problem, including potential throughput, data packet rejection rate, and data packet queue length of SUs, into closed-form expressions. Thereafter, the optimal solution guides the dynamic pre-adjustment of IRS by the station. Simulation results verify the superior performance of the proposed a*algorithm, particularly in terms of spectral efficiency and bit error rate, compared to existing methods.

关键词： Intelligent reflecting surface Cognitive radio Adaptive adjusting a*algorithm Markov model Queue theory Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

Emperor Yu Tames the Flood: Water Surface Garbage Cleaning Robot Using Improved A a*algorithm in Dynamic Environments

引用

IEEE ACCESS 2025年 13卷 48888-48903页

作者： Li, Ronghao Zhang, Bingying Lin, Di Tsai, Rong-Guei Zou, Wenwen He, Shanna Lin, Ziqi Chen, Xinxin Yao, Yating Putina Univ Putian Elect Informat Ind Technol Res Inst New Engn Ind Coll Putian 351100 Fujian Peoples R China Guangdong Univ Sci & Technol Coll Comp Sci Dongguan 523083 Guangdong Peoples R China Xiamen Huatian Int Vocat Inst Sch Informat Technol Xiamen 361000 Fujian Peoples R China Zhangzhou Inst Sci & Technol Sch Mech & Elect Engn & Informat Zhangzhou 363000 Fujian Peoples R China Fuzhou Technol & Business Univ Dept Digital Media Art Fuzhou 350715 Fujian Peoples R China

Every year, the global production of marine debris reaches a staggering 400 million tons, and the amount of garbage continues to increase. Among this, about 14 million tons will eventually flow into the oceans, posing a significant threat to marine ecosystems. Apart from endangering marine ecology, this waste will ultimately come back to affect humans. To address the increasingly severe issue of marine debris, our team independently developed a surface garbage cleaning robot, DaYu No. 1, and designed a path planning a*algorithm specifically for DaYu No. 1, called DyNav. DaYu No. 1 aims to increase garbage cleaning efficiency and adaptability. The traditional A (& lowast;) a*algorithm performs well in static environments, but the ocean is a dynamic environment where marine debris constantly shifts due to ocean currents or tides, making it extremely challenging for robots to collect marine debris. Therefore, our proposed DyNav a*algorithm can adaptively adjust paths to cope with environmental changes. We proposed DyNav, a new path planning a*algorithm that takes ocean currents into account, and the DaYu No. 1 robot with YOLOv7 and IMA a*algorithms built in. These will make cleaning up marine debris much more efficient and flexible. Compared to traditional path planning a*algorithms, DyNav demonstrates superior performance. We have validated the effectiveness of the DyNav a*algorithm through practical experiments. The results show that in dynamic environments, the robot can clean surface debris more quickly and flexibly while avoiding obstacles. This not only contributes to environmental protection, but also improves cleaning efficiency, offering an innovative solution for water environment management.

关键词： Heuristic a*algorithms Robots Path planning Surface cleaning Sea surface Genetic a*algorithms Vehicle dynamics Prediction a*algorithms Costs Collision avoidance Water surface garbage cleaning robots A* a*algorithm path planning Greedy RRT

来源：评论

学校读者我要写书评

暂无评论

Sparse compressed deep echo state network with improved arithmetic optimization a*algorithm for chaotic time series prediction

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 259卷

作者： Wang, Hongbo Mo, Yuanbin Guangxi Minzu Univ Sch Artificial Intelligence Nanning 530006 Guangxi Peoples R China Guangxi Key Lab Hybrid Computat & IC Design Anal Nanning 530006 Guangxi Peoples R China

A sparse compressed deep echo state network (SCDESN) incorporating sparse input units, compressed sampling and principal component analysis (PCA) units is proposed in this paper, and theoretically proved the sufficient and necessary conditions to ensure the echo state characteristics of the proposed scheme. In addition, a hybrid arithmetic optimization a*algorithm based on matrix design strategy and boundary selection strategy (SVD-HAOA) was proposed to optimize the hyper-parameters of the SCDESN model, taking into account the characteristics of the SCDESN model. The steps and process for optimizing the hyper parameters of the SCDESN model using SVDHAOA were presented. Finally, the SCDESN model optimized by SVD-HAOA was experimentally and summarized on a classic benchmark dataset and two real-world chaotic time series. The outcomes of the simulation indicated that the suggested model surpassed alternative models in performance and enhanced computational efficiency while maintaining prediction accuracy. This model may serve as a viable alternative for real-world applications.

关键词： Echo state networks Hierarchical structure Deep learning Arithmetic optimization a*algorithm Chaotic time series prediction

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in IoT Network Traffic Using Bidirectional 3D Quasi-Recurrent Neural Network Optimize With Coati Optimization a*algorithm

引用

TRANSACTIONS ON EMERGING TELECOMMUNICATIONS TECHNOLOGIES 2025年第1期36卷

作者： Deivakani, M. PSNA Coll Engn & Technol Dept Elect & Commun Engn Dindigul Tamil Nadu India

Anomaly detection in Internet of Things (IOT) network traffic involves identifying abnormal patterns or behaviors, enabling early detection of potential security threats or system malfunctions in the IOT ecosystem. IoT encompasses a variety of networks, addressing not only security challenges within sensor networks, the internet, and mobile communication networks but also specifically focusing on issues related to privacy protection, information management, network authentication, and access control. In this manuscript, Anomaly Detection in IoT Network Traffic using a Bidirectional 3D Quasi-Recurrent Neural Network with Coati Optimization a*algorithm (ADIOT-B3DQRNN-COA) is proposed. Initially, the input data are collected from the DS2OS Dataset. Then, the collected data is fed into pre-processing utilizing an Implicit Unscented Particle Filter (IUPF). The IUPF is used to remove the invalid data. Subsequently, the preprocessed data are sent into the Archimedes optimization a*algorithm (AOA) to select features. Seven characteristics from the DS2OS dataset are chosen using AOA. The selected features are then fed into a Bidirectional 3D Quasi-Recurrent Neural Network (Bi-3DQRNN) to classify anomaly detection in an Internet of Things network into the following categories: data probing, malicious control, malicious operation, scan, spying, incorrect configuration, DOS attack, and normal. To guarantee accurate classification of anomaly detection in IoT networks, Bi-3DQRNN generally does not express any adaptation of optimization a*algorithms for figuring out the best parameters. Hence, the Coati Optimization a*algorithm (COA) to optimize Bi-3DQRNN accurately classifies anomaly detection in the IOT network. The proposed ADIOT-B3DQRNN-COA approach is implemented in MATLAB. The performance of the proposed method was examined utilizing performance metrics like Accuracy, Computational Time, F-measure, Precision, Recall, and ROC. The proposed ADIOT-B3DQRNN-COA approach contains 32.15%,

关键词： anomaly detection Archimedes optimization a*algorithm bidirectional 3D quasi-recurrent neural network coati optimization a*algorithm and implicit unscented particle filter

来源：评论

学校读者我要写书评

暂无评论

A robust federated learning a*algorithm for partially trusted environments

引用

COMPUTERS & SECURITY 2025年 148卷

作者： Li, Yong Liu, TongTong Ling, HaiChao Du, Wei Ren, XiangLin Changchun Univ Technol Sch Comp Sci & Engn Changchun 130012 Peoples R China Changchun Univ Technol AI Res Inst Changchun 130012 Peoples R China Jilin Univ Sch Comp Sci & Technol Changchun 130012 Peoples R China Shandong Xiehe Univ Coll Comp Jinan 250107 Peoples R China

Due to the distributed nature of federated learning, it is vulnerable to poisoning attacks during the training process. The model's resistance to poisoning attacks can be improved using robust aggregation a*algorithms. Current research on federated learning to resist poisoning attacks is mainly based on two settings: No trust or Byzantine robustness. However, both settings are not close enough to reality in practical scenarios. In many practical applications, some participants in federated learning are trustworthy. For example, participants who have participated in the training of this model before and performed very well, or participants with strong compliance and credibility such as governments and some national agencies participate in the training. In existing research, these trusted participants still have to accept the judgment of the aggregation node, which generates unnecessary computation, increases overhead, and does not take advantage of a trusted environment. Since there is no attack behavior on the trusted client, its training results are used to classify the trustworthiness of other untrusted clients and identify attack nodes with higher accuracy. Therefore, this paper proposes a robust federated learning a*algorithm for partially trusted environments. The proposed scheme uses the experimental results of trusted clients to judge the behavior of untrustworthy clients by the cosine similarity and the Local Outlier Factor and further identify and detect malicious clients. Experiments are performed on MNIST and CIFAR datasets. Comparison with other six aggregation a*algorithms under 30% attack scenario. And compared with the other four aggregation a*algorithms under 70% attack conditions. Our a*algorithm is more accurate than almost all of the other aggregation a*algorithms. The paper is the first to conduct robust research on federated learning in a partially trusted environment, and the proposed a*algorithm can more effectively resist poisoning attacks.

关键词： Federated learning Robustness Aggregation a*algorithm Partially trusted environments Poisoning attack

来源：评论

学校读者我要写书评

暂无评论

An autoencoder-based arithmetic optimization clustering a*algorithm to enhance principal component analysis to study the relations between industrial market stock indices in real estate

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 266卷

作者： Yang, Cheng-Hong Lee, Borcy Lee, Yi-In Chung, Yu-Fang Lin, Yu-Da Tainan Univ Technol Dept Informat Management Tainan Taiwan Natl Kaohsiung Univ Sci & Technol Dept Elect Engn Kaohsiung Taiwan Kaohsiung Med Univ Ph D Program Biomed Engn Kaohsiung Taiwan Kaohsiung Med Univ Sch Dent Kaohsiung Taiwan Kaohsiung Med Univ Drug Dev & Value Creat Res Ctr Kaohsiung Taiwan Tunghai Univ Dept Int Business Taichung Taiwan Tunghai Univ Dept Elect Engn Taichung Taiwan Natl Penghu Univ Sci & Technol Dept Comp Sci & Informat Engn Penghu Taiwan

Traditional methods of forecasting and analyzing property trends using statistical analysis and questionnaires are limited;in particular, they are too slow to provide insights based on complex, extensive, and multidimensional real estate data. To address these challenges, we developed a sophisticated analytical pipeline integrating an autoencoder with an arithmetic optimization clustering a*algorithm (AOCA) and principal component analysis (PCA). An autoencoder was used to reduce the dimensionality of data sourced from public government databases to accelerate clustering. A tailored AOCA was then applied, and these clusters were examined with PCA to uncover deep relationships between different industrial market stock indices and real estate prices in Taiwan. We identified the following five critical clusters for 98 industrial market stock indices related to real estate from the Taiwan Stock Exchange between 2009 and 2020: 1) industrial and biomedical activity, 2) computers and computer peripherals, 3) shipping and transportation, 4) construction salaries, and 5) construction and economic activity. We performed a temporal clustering of these factors for in-depth insights. This granular insight into the factors driving house prices provides actionable information for policymakers. Our precise and focused pipeline allows researchers and government authorities to concentrate on the pivotal aspects of property development and market regulation. This approach paves the way for more targeted and effective interventions in the real estate market.

关键词： Machine learning Real estate Arithmetic optimization a*algorithm Economy

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：