检索结果-内蒙古大学图书馆

Multi-robot Task Allocation Optimizer Using Seeding Genetic Algorithm Based on A* Algorithm and DBSCAN Clustering

Transactions of the Korean Institute of Electrical Engineers 2025年第4期74卷 683-690页

作者： Seo, JangHo Lee, Joonwoo School of Electronic and Electrical Engineering Kyungpook National University Korea Republic of Department of Electrical Engineering Kyungpook National University Korea Republic of Department of Robot and Smart System Engineering Kyungpook National University Korea Republic of Department of Smart Mobility Engineering Kyungpook National University Korea Republic of School of Aerospace Engineering Sciences Kyungpook National University Korea Republic of

In recent years, robotics technology has made significant advancements, particularly in multi-robot systems where efficient task allocation plays a crucial role in maximizing productivity and minimizing operational time. Previous research has explored various approaches to solving the Multi-robot Task Allocation problem, but many have faced challenges in task distribution efficiency. To address this issue, we propose a Seeding Genetic Algorithm based on the A* algorithm and DBSCAN clustering. The A* algorithm performs path optimization in a grid environment with obstacles, while DBSCAN clusters tasks to enhance efficient task allocation. By seeding GA with these optimized solutions, the algorithm achieves faster convergence and higher solution quality. Simulations conducted on two maps with different robot configurations show that the A*-DBSCAN Seeding GA outperforms traditional GA and Greedy methods. The proposed method reduced the makespan, and its statistical significance was verified through ANOVA tests. This research contributes to improving multi-robot collaboration in industrial applications, offering an effective solution to the MRTA problem, reducing task completion time, and enhancing system efficiency. © The Korean Institute of Electrical Engineers.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Keyframe Selection for Acoustic Odometry Estimation Using Forward Looking Sonar

Keyframe Selection for Acoustic Odometry Estimation Using Fo...

引用

2023 MTS/IEEE U.S. Gulf Coast, OCEANS 2023

作者： Yoon, Eunchul Joe, Hangil Kyungpook National University Department of Robot and Smart System Engineering Daegu Korea Republic of

ISBN: (纸本)9798218142186

This study proposes a method to improve the accuracy of acoustic odometry using keyframe selection. The acoustic odometry was estimated based on Fourier-based image registration using images acquired from forward-looking sonar (FLS). The odometry estimation error increases when image registration fails due to spurious peaks and high similarity image pairs. The image pair selection must be adjusted prior to image registration in order to reduce the effects of spurious peaks and high similarity image pairs. We proposed a method for the adaptive frame interval by analyzing the factors affecting phase correlation for the accuracy of odometry. The odometry errors were reduced by using keyframe selection using adaptive frame intervals. The proposed method of verification using real-sea data is presented by comparing the odometry estimation results of USBL and a fixed frame interval using UUV cyclops. © 2023 The Marine Technology Society (MTS).

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Curve Monitoring and Alert system for smart Transportation 1

Curve Monitoring and Alert System for Smart Transportation

引用

1st IEEE International Conference on Cognitive robotics and Intelligent systems, ICC - ROBINS 2024

作者： Natarajan, Yuvaraj Sri Preethaa K, R. Viswanathan, Shrinithi Jayarathinam, Sandhiya Balasubramaniam, Vikas Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Kyungpook National University Department of Robot and Smart System Engineering Daegu Korea Republic of

ISBN: (纸本)9798350372748

The proposed IoT-based smart Curve Monitoring and Alert system is designed to improve road safety through the fusion of embedded systems, machine learning and edge computing technologies. The proposed system is primarily powered by ESP32 microcontroller, continuously gathers data from an array of sensors, including accelerometers, gyroscopes and a potentiometer to set the speed limit. This collected data is then subjected to analysis by a Convolutional Neural Network (CNN) model, which has been trained to recognize driving patterns, especially when navigating curves. Here, CNN classifies the vehicle's behavior as safe and risky, and if a risky behavior is identified, it triggers an alert and dispatches relevant data to a NodeMCU device. The NodeMCU plays a crucial role in the system by monitoring the communication tasks. It receives the alert from the ESP32, validates the vehicle's speed against the preset limit, and, if necessary, activates a GSM module to send an immediate notification to designated guardian. To ensure real-time monitoring and awareness, all pertinent information will be displayed on the LCD screen, including the vehicle's behavior classification, current speed, speed limit and alert status. By addressing reckless driving behaviors, particularly on curves, the system contributes significantly to safer roads and reinforces the importance of responsible driving practices. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Enhancing Medical Information Retrieval with a Language Model 1

Enhancing Medical Information Retrieval with a Language Mode...

引用

1st IEEE International Conference on Cognitive robotics and Intelligent systems, ICC - ROBINS 2024

作者： Natarajan, Yuvaraj Sri Preethaa, K.R. Pandian, Sasikumar Geetha, Shruti Umapathi Senthilkumar, Sujadharshini Kpr Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Kyungpook National University Department of Robot and Smart System Engineering Daegu41566 Korea Republic of

ISBN: (纸本)9798350372748

In this ever-evolving healthcare landscape, with the integration of cutting-edge technology, this study has exemplified a medical chatbot by harnessing the advanced Llama2 model. This chatbot places significant emphasis on instance training by changing and adding the meta, which enables it to continuously adapt and stay updated with the latest medical developments. Its adaptability also encompasses capabilities such as question-answering and mining knowledge from an extensive meta dataset. By leveraging its extensive ability to learn medical terminology, the chatbot provides precise and real-time responses to medical inquiries by establishing itself as a reliable information source. Access to a specially collected meta dataset further enhances its ability to deliver comprehensive medical insights while self-supervised learning techniques enhance the model efficacy. Consequently, this chatbot reshapes the way individuals access precise medical information by enabling a new era of advanced digital healthcare assistants in the digital age. © 2024 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Large-Scale Benchmark Dataset for Remote Sensing Object Detection on Battlefield

Towards Large-Scale Benchmark Dataset for Remote Sensing Obj...

引用

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Kim, Yechan Park, JongHyun Kim, Sihyun Kim, Sungheon Kim, SooYeon Ko, YeongMin Oh, Junggyun Jeon, Moongu School of Electrical Engineering and Computer Science GIST Korea Republic of Kyungpook National University Department of Robot and Smart System Engineering Korea Republic of HDC Labs Korea Republic of

ISBN: (纸本)9798331530839

Precise object detection allows military personnel to clearly understand their surroundings, leading to planning effective military strategies. Particularly, satellites and drones allow real-time surveillance over large areas, which is crucial for military operations. Collaboration among military, academic, and industrial institutions is required to promote innovation in military target detection. However, potential security concerns usually restrict access to real data from the military. To mitigate this issue, this paper proposes a novel approach to generate synthetic data for remote sensing object detection on the battlefield with ARMA3, one of the renowned military tactic games. With our method, the data for model training can be easily generated without any manpower. To demonstrate the efficacy of our approach, we provide a detailed analysis of the examples from our method. As ARMA3 is well-known for its realistic military combat simulation, we believe our method can effectively contribute to military object detection in remote sensing. © 2024 IEEE.

关键词： Military satellites

来源：评论

学校读者我要写书评

暂无评论

Vision-based Vertiport Marking Detection system for Precision Landing on a Vertiport

引用

Journal of Institute of Control, robotics and systems 2024年第2期30卷 93-98页

作者： Heo, Hyeonjeong Lee, Kyuman Department of Robot and Smart System Engineering Kyungpook National University Korea Republic of

Contrary to existing airports in the suburbs, a vertiport is located in a complex urban area and has space limitations. Precision landing technology at a vertiport is essential for safe urban air mobility (UAM) operations in limited spaces. The U.S. Federal Aviation Administration (FAA) has recently released a symbol design for vertiport identification. However, research on the precision landing of a UAM vehicle using this symbol is still insufficient. We propose a vision-based system for detecting the FAA vertiport marking to ensure precision landing on a vertiport. After the existing fiducial marker detectors have been benchmarked, we establish a methodology that recognizes the vertiport marking, estimates the relative position and attitude through transformation, and visualizes the pose estimation results to instruments similar to the instrument landing system. Marking detection and pose estimation are validated experimentally by using cameras and drone flight tests. The results show the applicability of the proposed approach under the operating conditions for UAM. © ICROS 2024.

关键词： Air mobility

来源：评论

学校读者我要写书评

暂无评论

DC Motor Current Control Based on Inverse Model Using Recurrent Neural Network

引用

Journal of Institute of Control, robotics and systems 2024年第1期30卷 27-32页

作者： Baek, Dong-Min Joe, Hyun-Min Department of Robot and Smart System Engineering Kyungpook National University Korea Republic of

This paper presents a method for microcontrollers control using a recurrent neural network-based inverse model. Limited computational power in microcontrollers makes applying complex neural network structures challenging. We use the Elman network with a simple structure as an inverse model to address this issue. Elman network was used to model nonlinear control systems. The proposed method constructs a recurrent neural network-based inverse model in parallel to enhance the performance of the PID controller. The recurrent neural network uses the output generated by the PID controller as the past control input and compensates for the control inputs generated by the PID controller. We applied the proposed controller to a DC motor current control system and compared its performance with the PID controller that uses a deep neural network as an inverse model. We evaluated the control performance by applying a sine wave. The results show that the proposed controller has better tracking performance at 1, 3, and 5 Hz than the other controllers. © ICROS 2024.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Mobile Crane for Path Tracking of Humanoid robots

引用

Journal of Institute of Control, robotics and systems 2023年第9期29卷 734-739页

作者： Park, Shinwoo Joe, Hyun-Min Department of Robot and Smart System Engineering Kyungpook National University Korea Republic of Department of Robot and Smart System Engineering Department of Artificial Intelligence Kyungpook National University Korea Republic of

This paper describes the design and control of a mobile crane used for walking experiments conducted on humanoid robots. To prevent humanoid robots from overturning, experiments are conducted while they are connected to a crane. To conduct the walking experiment, a minimum of one operator each is required for controlling the robot and moving the crane. Thus far, an automated mobile crane that can perform the function of a crane operator has not been developed. To obtain high stability and efficiency during the walking experiment, we propose a mobile crane that moves according to the locomotion of humanoid robots. Considering the locomotive property of humanoid robots, the mobile crane was designed to be able to move omnidirectionally, and a control algorithm was developed for the mobile crane to track the position and orientation of the humanoid robot being studied. The performance of the developed mobile crane was evaluated through a walking experiment conducted using a humanoid robot. © ICROS 2023.

关键词： Anthropomorphic robots

来源：评论

学校读者我要写书评

暂无评论

A Study on Unmanned Water-Powered Aerial Vehicle Equipped with Nozzle Rotation Mechanism and Propeller Module 24

A Study on Unmanned Water-Powered Aerial Vehicle Equipped wi...

引用

24th International Conference on Control, Automation and systems, ICCAS 2024

作者： Nguyen, Thien-Dinh Dinh, Cao-Tri Huynh, Thinh Lee, Dong-Hun Kim, Young-Bok Pukyong National University Department of Smart Mobility Engineering College of Information Technology and Convergence Busan48513 Korea Republic of Pukyong National University Department of Intelligent Robot Engineering Busan48513 Korea Republic of Pukyong National University Division of Energy Transport System Engineering Department of Mechanical System Engineering Busan48513 Korea Republic of

ISBN: (纸本)9788993215380

Water-powered aerial vehicles have been widely applied in various fields such as entertainment, rescue and transportation. However, they require an operator to have an expert technique to govern. In order to enhance the skillful applications of these vehicles in specialized missions such as firefighting, rescue, and exploration, this study proposed a novel unmanned water-powered aerial vehicle actuating nozzle rotation mechanism and propellers module. In particular, by changing the water force direction through the nozzle rotation modules and air force of propeller modules, the proposed vehicle can achieve comprehensive 6-degree-of-freedom motion under the constant mass flow rate condition. As a first step to investigate the effectiveness of the proposed system, the following steps are being taken. Firstly, a mathematical model of the vehicle is derived in detail to describe system dynamics. Secondly, a well-known proportional-integral- derivative controller is then applied to regulate its full motion. Finally, the simulation studies are conducted to validate the feasibility of the proposed vehicle. © 2024 ICROS.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Active Heading Planning for Improving Visual-Inertial Odometry

Active Heading Planning for Improving Visual-Inertial Odomet...

引用

International Conference on Unmanned Aircraft systems (ICUAS)

作者： Joohyuk Lee Kyuman Lee Department of Robot and Smart System Engineering Kyungpook National University Daegu Korea

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

Visual-inertial odometry (VIO) is a technique to estimate the motion of a vehicle platform by fusing camera and inertial sensor data. It operates effectively in GPS-denied environments such as indoors and is widely utilized in applications like autonomous navigation of unmanned aerial vehicles (UAVs) due to its real-time performance and high localization accuracy. However, since VIO relies on textures in the environment or features extracted from image frames, localization may easily fail if the number of feature points in the image is insufficient or the U AV faces a low-texture environment. To address these issues, we propose an active VIO algorithm by planning heading angles autonomously. This algorithm improves VIO accuracy and maintains robust localization even in an unknown environment by employing heading planning to acquire more feature points in the subsequent image frames. To achieve this, we first divide an image frame into several sections and count the number of feature points in each section. Next, we determine the desired heading angle based on the feature-occupied ratio of each section. The proposed approach is validated in various cases in a simulation environment that mimics an indoor warehouse.

关键词： Location awareness Accuracy Inertial sensors MIMICs Feature extraction Autonomous aerial vehicles Real-time systems

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：