检索结果-内蒙古大学图书馆

Localization Method in dense Smoke Scenarios Using radar-thermal Stereo Sensor Fusion

Journal of Institute of Control, robotics and Systems 2024年第8期30卷 871-878页

作者： Lee, Meungsuk Kang, Minseok Shin, dong Gwan Pyo, Juhyun Kim, Jinwon Song, Hyeongseok Kim, Murim Human-Centered Robotics R&D Division Korea Institute of Robotics & Technology Convergence Korea Republic of

In this study, we overcome the challenges of robot localization in environments filled with dense smoke, which significantly reduce visibility and hinder traditional SLAM methods. Our approach introduces a novel fusion technology combining radar and thermal stereo sensors for such extreme conditions. Leveraging the complementary strengths of the two sensor types, our algorithm significantly enhances the localization accuracy of robots in firefighting scenarios. We conducted experimental evaluations under dense fog conditions to validate the efficiency of our proposed method. The results demonstrate an improvement in robot localization performance and confirm the potential applicability of our approach for use in firefighting robots. Furthermore, the sensor fusion not only augments the mapping accuracy but also provides crucial additional feature points for better operational control and environmental perception, thus paving the way for a more effective deployment of robots in disaster response situations. © ICrOS 2024.

关键词： Fire extinguishers

来源：评论

学校读者我要写书评

暂无评论

derivation and Analysis of System requirements for a robust Antarctic Exploration robot in Harsh driving Conditions Based on Antarctic Application Experiments

引用

Journal of Institute of Control, robotics and Systems 2024年第7期30卷 710-717页

作者： Kwon, Ji-Wook Lee, Hyoujun Uhm, Taeyoung Lee, Jongdeuk Kim, Jong Chan Choi, Young-Ho Smart Mobility R&D Division Korea Institute of Robotics and Technology Convergence Korea Republic of

This paper presents the initial operational results of the Antarctic exploration robot KArEX on the Antarctic continent. It analyzes various phenomena encountered during autonomous navigation in Antarctic conditions and derives the necessary requirements for operating autonomous robots in such environments. KArEX navigated surfaces such as snow, ice, glaciers, gravel, and soil around the Jangbogo Station in Antarctica, covering a distance of about 10 Km. Activities included navigating around structures, glacier areas, snow hills, and water puddles. The robot was also stored outside overnight. remote monitoring and control of KArEX from a distance was conducted to verify the robot's effectiveness. This process led to the analysis and verification of pre-planned specifications before real-environment testing and the identification of additional operational and system requirements to withstand the harsh Antarctic operational conditions. © ICrOS 2024.

关键词： robots

来源：评论

学校读者我要写书评

暂无评论

Mobile robot Using Unbalanced road Adaption device

引用

Journal of Institute of Control, robotics and Systems 2024年第1期30卷 20-26页

作者： Lim, Ji-Ho Lee, Sang-Yeob Shin, dongwon Department of Mechanical System Engineering Kumoh National Institute of Technology Korea Republic of AI Robotics R&D Division Korea Institute of Robotics & Technology Convergence Korea Republic of

This study investigated a mobile robot capable of navigating unbalanced road surfaces solely via its mechanical structure, utilizing an unbalanced road adaptation device. This adaptation device was designed by introducing a height adaptor to the existing suspension mechanism, with each component consisting of links and shock absorbers. With these components, the robot excelled in adapting to unbalanced road surfaces. To validate the performance of the designed robot, a degree-of-freedom analysis was conducted, and the robot’s driving stability was evaluated through driving simulations. © ICrOS 2024.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

development of a personal mobility scooter with autonomous driving and safety features

引用

Journal of Institute of Control, robotics and Systems 2023年第5期29卷 404-411页

作者： Eui-Jung, Jung Kwang-Woo, Jeon Juhyun, Kim Jong-Il, Lee Min-Gyu, Kim Hyo-Jeong, Cha Human-Robot Interaction R&D Center Korea Institute of Robotics & Technology Convergence Korea Republic of AI Robotics R&D Division Korea Institute of Robotics & Technology Convergence Korea Republic of Department of Medical Robotics Korea Institute of Machinery & Materials Korea Republic of

This study developed a personal mobility scooter with autonomous driving and safety functions. The scooter can recognize indoor and outdoor environmental conditions by applying various sensor systems similar to semi-autonomous vehicles. The addition of an autonomous driving function ensures user convenience. The mobility scooter was developed to provide user safety by preventing collisions and rollover accidents. First, the system configuration and functions of the personal mobility scooter have been introduced, followed by the application of algorithms to implement each function. In terms of convenience, the main features of personal mobility scooters include indoor autonomous driving, outdoor semi-autonomous driving, and guardian-following driving. In terms of safety, the salient features are collision prevention and rollover prevention. The functions proposed here were incorporated in an actual mobility scooter, and its efficacy was verified through experiments. © 2023, Institute of Control, robotics and Systems. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Operational Space Fomulation of Time delay Control for Underwater Vehicles and its Extension to diver Guidance

Operational Space Fomulation of Time Delay Control for Under...

引用

2025 IEEE Underwater Technology, UT 2025

作者： Cho, Gun rae Kang, Hyungjoo Kim, Min-Gyu Park, Sungho Jin, Hansol Jin, Seongho Korea Institute of Robotics and Techonology Convergence Autonomous Systems R&D Division Pohang Korea Republic of

ISBN: (纸本)9798331534189

In this study, we propose a method for designing a robust controller for underwater vehicles when the control input space and workspace differ. To achieve this, we formulate the Time delay Control (TdC) in operational space, which is efficient yet has a simple structure. The proposed controller maintains the robustness against disturbances and structural simplicity inherent in the conventional TdC while effectively addressing the situation where the workspace differs from the control input space. Additionally, we propose a method for applying the proposed controller to the task of guiding divers to their destinations using underwater vehicles. Underwater environments often have limited visibility due to issues such as turbidity, so we design the controller and reference trajectories based on the diver's field of view. Through simulations, we demonstrate that the proposed control method effectively operates in various workspaces, including world-coordinate-based workspaces and diver's field of view-based workspaces. © 2025 IEEE.

关键词： delay control systems

来源：评论

学校读者我要写书评

暂无评论

Tracking Error Based Fault Tolerant Scheme for Marine Vehicles with Thruster redundancy

Tracking Error Based Fault Tolerant Scheme for Marine Vehicl...

引用

2025 IEEE Underwater Technology, UT 2025

作者： Li, Ji-Hong Kang, Hyungjoo Kim, Min-Gyu Lee, Mun-Jik Jin, Han-Sol Cho, Gun rae Korea Institute of Robotics and Technology Convergence Autonomous Systems R&D Division KIRO Pohang Korea Republic of

ISBN: (纸本)9798331534189

This paper proposes an active model-based fault and failure tolerant control scheme for a class of marine vehicles with thruster redundancy. Unlike widely used state and parameter estimation methods, where the estimation errors are utilized to generate residual, in this paper we directly apply the trajectory tracking error terms to construct residual and detect thruster fault and failure in the steady state of the tracking system. As for identification or diagnosis, this paper proposes a novel scheme through a detailed examination of the tracking error trends and the combinations of thruster configurations. Since this fault detection and identification operates within the same closed-loop of the tracking control system, control reconfiguration can be easily achieved by adjusting the weight parameter of the isolated thruster to minimize tracking errors or residual. Numerical studies with the real world vehicle model is also carried out to verify the effectiveness of the proposed method. © 2025 IEEE.

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

OGM Based real-time Obstacle detection and Avoidance using Multibeam FLS 2

OGM Based Real-time Obstacle Detection and Avoidance using M...

引用

2nd International Conference on Mechatronics, Control and robotics, ICMCr 2024

作者： Jin, Han-Sol Kang, Hyungjoo Kim, Min-Gyu Lee, Mun-Jik Jin, Seongho Cho, Gun rae Li, Ji-Hong Korea Institute of Robotics & Technology Convergence Autonomous Systems R&d Division Pohang37666 Korea Republic of

ISBN: (纸本)9798350396096

This paper presents an obstacle detection and avoidance algorithm based on OGM (occupancy grid map) method and its experimental studies. At each time step (5Hz), given the current frame of FLS (forward looking sonar) image, each of its cloud point is transformed into the reference frame and upgrade the density of the grid where the point is located. during this upgrade, weights were applied to both the current density of the grid and the cloud point intensity. With this OGM, each grid whose density surpass certain threshold is taken as obstacle and counted in the path planning using general potential field method. A series of experimental studies have been carried out in the sea port environment, whereas we can investigate and analysis the effects of the design parameters in both of OGM construction and obstacle avoidance algorithms. This paper shows some of these preliminary results. © 2024 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement Method for detection in Logistics Loading and Unloading robots

引用

IEEE Access 2024年 1-1页

作者： Kang, Jeon-Seong Kang, Jin Kyu Son, Soeun Park, Sung Ho Jung, Eui-Jung Cho, Gun rae AI Robotics R&D Division Korea Institute of Robotics & Technology Convergence Seoul Republic of Korea Independent Researcher Seoul Republic of Korea Autonomous Systems R&D Division Korea Institute of Robotics & Technology Convergence Pohang Republic of Korea

This paper presents a novel method in the field of robotic vision, specifically designed to operate effectively under various lighting conditions. We propose an Image Enhancement Method for parcel loading status recognition, which addresses the challenge of insufficient lighting inside freight trucks without requiring lighting adjustments. Our approach integrates GAN and YOLO v5 into an end-to-end structure, where the detection network’s outputs influence the training of the generative network. Unlike traditional methods that focus solely on enhancing low-light image visibility, our method is optimized to maximize detection accuracy. To demonstrate the superiority of our approach, we constructed a setup resembling a freight truck, collected a dataset under varying lighting conditions, and conducted extensive experiments. The latter sections of the paper review relevant studies on vision data control in computer vision, provide a detailed explanation of our method, describe the experimental setup and database acquisition process, and discuss the results and analyses. The conclusion is presented in Section 6. Authors

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

Multimodal layer surveillance map based on anomaly detection using multi-agents for smart city security

Multimodal layer surveillance map based on anomaly detection...

引用

作者： Shin, Hochul Na, Ki-In Chang, Jiho Uhm, Taeyoung Department of Intelligent Robotics Electronics and Telecommunications of Research Institute Daejeon Korea Republic of Intelligent Robotics R&D Division Korea Institute of Robotics and Technology Convergence Pohang Korea Republic of

Smart cities are expected to provide residents with convenience via various agents such as CCTV, delivery robots, security robots, and unmanned shuttles. Environmental data collected by various agents can be used for various purposes, including advertising and security monitoring. This study suggests a surveillance map data framework for efficient and integrated multimodal data representation from multi-agents. The suggested surveillance map is a multi-layered global information grid, which is integrated from the multimodal data of each agent. To confirm this, we collected surveillance map data for 4 months, and the behavior patterns of humans and vehicles, distribution changes of elevation, and temperature were analyzed. Moreover, we represent an anomaly detection algorithm based on a surveillance map for security service. A two-stage anomaly detection algorithm for unusual situations was developed. With this, abnormal situations such as unusual crowds and pedestrians, vehicle movement, unusual objects, and temperature change were detected. Because the surveillance map enables efficient and integrated processing of large multimodal data from a multi-agent, the suggested data framework can be used for various applications in the smart city. 1225-6463/$ © 2022 ETrI.

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing GAN-Based Motion data Augmentation Through dynamic Time Warping distance Filtering

Enhancing GAN-Based Motion Data Augmentation Through Dynamic...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Junwon Yoon Hyun-Joon Chung Jeon-Seong Kang Jung-Jun Kim Kwang-Woo Jeon SeungWoo Kim Myounghoon Shim Jae-Kwan ryu AI Robotics R&D Division Korea Institute of Robotics & Technology Convergence Seoul Republic of Korea Unmanned/Intelligent Robotic Systems R&D LIG Nexl Seongnam Republic of Korea

Motion capture data is crucial but creating a large dataset can be challenging due to complexities in acquisition. Generative Adversarial Network (GAN)-based motion data augmentation offers a potential solution to this issue. However, GANs often struggle with learning from limited data, resulting in poor quality output. In this study, we propose a dynamic Time Warping (dTW) filtering method that filters out generated data significantly deviating from real-world examples. Through this approach, we have achieved an improvement in the fidelity of the generated data, even with dataset size constraints, as evidenced by an increase in action recognition accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：