检索结果-内蒙古大学图书馆

2023 International Conference on robotics and Automation in Industry, ICRAI 2023

作者： Ullah, Syed Izzat Mahmood, Tallat Anayatullah A&M University-Corpus Christi Department of Computing Sciences Texas Pakistan National Centre of Robotics and Automation Control Automotive and Robotics Lab Rawalpindi Pakistan

ISBN: (纸本)9781665464727

In an Urban Search and Rescue situation, under extreme time pressure, rescue workers have to locate and extract the trapped people in collapsed structures. Due to the lack of medical treatment, food, and water, the victim's mortality rate dramatically increases over time. Rescue operations for both rescue workers and victims might be as dangerous as the initial event. For such situations, snake robots which are inspired by their biological counterparts, are shown to be a good option in the literature, to help the rescue workers in positioning the victims or delivering life-saving drugs to extend the life of the victims for some time. However, current research mainly focuses on mechanical design, control mechanisms, and gait generation. To alleviate this concern, we have integrated state-of-the-art methods to develop an autonomous snake robot that can navigate in an unknown environment while also generating a 3D map, to provide a better idea of the environment to the rescue workers. A simulated maze environment is implemented and demonstrated by using the CoppeliaSim simulation, running on Robot Operation System (ROS) and Linux OS. The simulation result shows the effectiveness of the proposed autonomous navigation system for the snake robot to plan an obstacle-free path from the robot's current position to the goal position without an apriori knowledge of the environment. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Odometry and Inertial Sensor-based Localization of a Snake Robot

Odometry and Inertial Sensor-based Localization of a Snake R...

引用

2023 International Conference on robotics and Automation in Industry, ICRAI 2023

作者： Shahid, Ramsha Baloch, Anam Tahir, Humayun Ullah, Anayat National Centre of Robotics and Automation Control Automotive and Robotics Lab Rawalpindi Pakistan Balochistan University of IT Engineering and Management Sciences Department of Electronic Engineering Quetta Pakistan

ISBN: (纸本)9781665464727

Terrain adaptability gives snake robots an edge over wheeled mobile robots. Snake robot's applications expansion to disaster management is due to its limbless and modular design. Replicating the navigation and locomotion of a biological snake have been in the spotlight for many researchers. In this study, a robust localization algorithm of a snake robot is developed. A sensor fusion-based algorithm using probabilistic approaches: UKF (Unscented Kalman Filter) and EKF (Extended Kalman Filter) has been proposed. Odometry is fused with one and two IMUs (Inertial Measurement Units) with both probabilistic approaches. Evaluation of results in a simulation environment showed that the fusion of two IMUs and odometry using EKF outer performs in terms of accuracy when odometry is fused with one IMU using EKF. Furthermore, the fusion of two IMUs and odometry with UKF is computationally expensive resulting in a large convergence time which is not the best suitable approach that can be utilized for the snake robot. © 2023 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive State Estimation Methodology for Multimachine Power Systems

A Comprehensive State Estimation Methodology for Multimachin...

引用

2023 IEEE PES Generation, Transmission and Distribution International Conference and Exposition, GTD 2023

作者： Vieyra, Natanael Maya-Ortiz, Paul Angeles-Camacho, Cesar CDMX Mexico04510 Mexico Dpt. Control and Robotics CDMX Mexico04510 Mexico

ISBN: (纸本)9781728170251

The state estimation problem of Multimachine Power Systems (MPSs) is addressed in this paper. Firstly, the classical third-order MPS dynamic model was changed to include the transmission line losses effect on generator dynamics. Afterward, a decentralized estimation model is constructed by including a set of quickly observed states for each machine, which show how the machine interacts with other generators, unknown disturbances, transmission losses, and model errors. And, by assuming the load angle as measured output, the dynamic state variables of generators with terminal voltage magnitudes are estimated in a distributed fashion through a geometric estimator (GE). The proposed state estimation scheme is demonstrated under different operational conditions in a 3-machine power system. © 2023 IEEE.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Real-Time Multi-object Tracking Using YOLOv8 and SORT on a SoC FPGA 21st

Real-Time Multi-object Tracking Using YOLOv8 and SORT on a...

引用

21st International Symposium on Applied Reconfigurable Computing, ARC 2025

作者： Danilowicz, Michal Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031879944

Multi-object tracking (MOT) is one of the most important problems in computer vision and a key component of any vision-based perception system used in advanced autonomous mobile robotics. Therefore, its implementation on low-power and real-time embedded platforms is highly desirable. Modern MOT algorithms should be able to track objects of a given class (e.g. people or vehicles). In addition, the number of objects to be tracked is not known in advance, and they may appear and disappear at any time, as well as be obscured. For these reasons, the most popular and successful approaches have recently been based on the tracking paradigm. Therefore, the presence of a high quality object detector is essential, which in practice accounts for the vast majority of the computational and memory complexity of the whole MOT system. In this paper, we propose an FPGA (Field-Programmable Gate Array) implementation of an embedded MOT system based on a quantized YOLOv8 detector and the SORT (Simple Online Realtime Tracker) tracker. We use a modified version of the FINN framework to utilize external memory for model parameters and to support operations necessary required by YOLOv8. We discuss the evaluation of detection and tracking performance using the COCO and MOT15 datasets, where we achieve 0.21 mAP and 38.9 MOTA respectively. As the computational platform, we use an MPSoC system (Zynq UltraScale+ device from AMD/Xilinx) where the detector is deployed in reprogrammable logic and the tracking algorithm is implemented in the processor system. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Towards backward compatibility of ADRC: revisiting classical state-feedback control with integral compensator

引用

Bulletin of the Polish Academy of Sciences: Technical Sciences 2025年第2期73卷

作者： Mrotek, Mikolaj Michalski, Jacek Madonski, Rafal Pazderski, Dariusz Retinger, Marek Faculty of Control Robotics and Electrical Engineering Institute of Robotics and Machine Intelligence Poznan University of Technology Piotrowo 3a Poznan60-965 Poland Faculty of Automatic Control Electronics and Computer Science Department of Automatic Control and Robotics Silesian University of Technology Akademicka 16 Gliwice44-100 Poland Faculty of Control Robotics and Electrical Engineering Institute of Automatic Control and Robotics Poznan University of Technology Piotrowo 3a Poznan60-965 Poland

In this paper, the problem of backward compatibility of active disturbance rejection control (ADRC) is investigated. The goal is to contextualize ADRC to deliver its interpretations from the established field of linear control systems. For this study, a control algorithm, denoted here as integral disturbance rejection control (IDRC), is considered that combines classical state-feedback control with an integral compensator. At first, an interpretation of ADRC is involved in terms of existing state-space control approaches. Next, a transition to the frequency domain is performed, which is justified as a significant part of practical control engineering is conducted in that domain. For assumed specific plant structures, both ADRC and IDRC are then holistically compared in terms of transfer function representation and frequency characteristics, as well as steady-state convergence conditions. Such a juxtaposition helps to highlight the similarities and differences of both approaches, whereas the utilized bandwidth parameterization is shown to bring the control system to the same form, thus indicating some interesting practical aspects. Finally, the theoretical results concerning both considered control structures are validated in a set of numerical simulations and experiments conducted on a laboratory hardware testbed. © 2025 The Author(s).

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Bebop 2 Quadrotor as a Platform for Research and Education in robotics and control Engineering

Bebop 2 Quadrotor as a Platform for Research and Education i...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Wojciech Giernacki Piotr Kozierski Jacek Michalski Marek Retinger Rafal Madonski Pascual Campoy Institute of Robotics and Machine Intelligence Faculty of Control Robotics and Electrical Engineering of Poznan University of Technology Poznań Poland Institute of Computing Science (Faculty of Computing and Telecommunications) and with the Institute of Robotics and Machine Intelligence (Faculty of Control Robotics and Electrical Engineering) Poznan University of Technology Poznań Poland International Energy College Energy Electricity Research Center Jinan University Zhuhai China Computer Vision and Aerial Robotics (CVAR) Centre for Automation and Robotics Technical University of Madrid (UPM) Madrid Spain

ISBN: (数字)9781728142784

ISBN: (纸本)9781728142791

In conducting research and teaching in fields related to unmanned aerial vehicles (UAVs), it is particularly important to select a universal, safe, open research platform and tools for rapid prototyping. Ready-to-use, low-cost micro-class UAVs such as Bebop 2 are successfully used in that regard. This article presents how to use the potential of this flying robot with Robot Operating System (ROS). The most important software solutions for the developed experimental testbed FlyBebop are characterized here. Their capabilities in research and education are exemplified using three distinct cases: 1) research results on the method of optimal, in-flight, iterative self-tuning of UAV position controller parameters (based only on current measurements), 2) the use of the reinforcement learning method in the autonomous landing of a single drone on a moving vehicle, 3) planning the movement of UAVs for autonomous video recording along the planned path in the arrangement: "cameraman drone" and "lighting technician drones".

关键词： Drones Robots Education Cameras Sensors Tools

来源：评论

学校读者我要写书评

暂无评论

A surface defect detection method for steel pipe based on improved YOLO

引用

Mathematical Biosciences and Engineering 2024年第2期21卷 3016-3036页

作者： Wang, Lili Song, Chunhe Wan, Guangxi Cui, Shijie State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China College of Information Liaoning University Shenyang110036 China

Surface defect detection is of great significance as a tool to ensure the quality of steel pipes. The surface defects of steel pipes are charactered by insufficient texture, high similarity between different types of defects, large size differences, and high proportions of small targets, posing great challenges to defect detection algorithms. To overcome the above issues, we propose a novel steel pipe surface defect detection method based on the YOLO framework. First, for the problem of a low detection rate caused by insufficient texture and high similarity among different types of defects of steel pipes, a new backbone block is proposed. By increasing high-order spatial interaction and enhancing the capture of internal correlations of data features, different feature information for similar defects is extracted, thereby alleviating the false detection rate. Second, to enhance the detection performance for small defects, a new neck block is proposed. By fusing multiple features, the accuracy of steel pipe defect detection is improved. Third, for the problem of a low detection rate causing large size differences in steel pipe surface defects, a novel regression loss function that considers the aspect ratio and scale is proposed, and the focal loss is introduced to further solve the sample imbalance problem in steel pipe defect datasets. The experimental results show that the proposed method can effectively improve the accuracy of steel pipe surface defect detection. © 2024 American Institute of Mathematical Sciences. All rights reserved.

关键词： Aspect ratio

来源：评论

学校读者我要写书评

暂无评论

Transfer Learning: An Approach on the Riemannian Manifold for Multiclass Motor Imagery EEG Brain-Computer Interface 30

Transfer Learning: An Approach on the Riemannian Manifold fo...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Sun, Xu Chu, Yaqi Luo, Yang Zhao, Xingang Northeastern University Department of Control Engineering Shenyang110819 China China Institutes for Robotics and Intelligent Manufacturing Shenyang110016 China

ISBN: (纸本)9798350391916

Motor imagery (MI) EEG-based brain-computer interface (BCI) facilitates direct communication between the brain's intentions and a computer. In essence, it allows a person to control external equipment by decoding EEG signals during the mental imagery of limb movements. However, due to the intricate individual variances in EEG signals, creating a general decoding model with parameters applicable to all subjects is exceptionally challenging. Consequently, a prolonged calibration process is necessary to gather labeled subject-specific data for each individual, making it less user-friendly. A potential solution to this problem is transfer learning, a methodology that transfers knowledge from related domains to a target domain. To tackle the problem, this paper proposes a novel transfer learning approach on the Riemannian manifold framework in the context of multiclass MI EEG-based BCI classification. Particularly, a user-specific frequency band selection (FBS) method with MI EEG class distinctiveness is utilized to improve the accuracy and efficiency of Riemannian space calculations, which is measured using the inter-class distance and intra-class variance on the manifold. Then, the Riemannian space Alignment (RA) strategy is used to calibrate the MI EEG variances of different subjects. The comparative experiments between the proposed approach and baseline/conventional methods are conducted on a public dataset with four-class motor imagery EEG, including two-class transfer learning scenario and four-class transfer learning scenario. proposed transfer learning approach is outperformed. Compared with the baseline/conventional methods using a fixed wide frequency band, the preliminary results suggests that the proposed approach can significantly improve the transfer learning performance for the MI EEG signals from different subjects in Riemannian space. © 2024 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Multilingual Transliteration based Urdu Chatbot using Rasa Framework 17

Multilingual Transliteration based Urdu Chatbot using Rasa F...

引用

17th International Conference on Open Source Systems and Technologies, ICOSST 2023

作者： Mohiuddin, Hira Kasi, Bakhtiar Ullah, Anayat National Center of Robotics and Automation Control Automotive and Robotics Lab Rawalpindi Pakistan Balochistan University of IT Engineering and Management Sciences Faculty of Information and Communication Technology Quetta Pakistan

ISBN: (纸本)9798350381320

Chatbots, which emulate human conversation, are meeting the rising demand for efficient customer service by reducing the need for manual intervention and alleviating the challenges of timeconsuming human interactions. This paper introduces Ubot, a domain-specific chatbot fluent in both Urdu and English transliteration, designed to reduce the need for human intervention and lower service costs. We address the challenge of low-resource languages by creating a dataset comprising 750 utterances, 28 intents, and 45 entities, validated by 36 participants. Ubot, powered by the Rasa framework, achieves remarkable accuracy in intent detection 94.1% and entity extraction 95.4%, offering efficient multilingual conversational AI solutions. Our approach holds promise for similar script-sharing languages such as Persian and Arabic, contributing to advanced language applications and intelligent virtual assistants. © 2023 IEEE.

关键词： Chatbot Dialogue Management Entities Intents Rasa Ubot

来源：评论

学校读者我要写书评

暂无评论

Novel objects 3-D dense packing through robotic pushing

引用

Science China(Technological Sciences) 2022年第12期65卷 2942-2951页

作者： WU JianHua ZHANG HaoDong CHANG YaFei XIONG ZhenHua ZHU XiangYang Institute of Robotics School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Beijing Institute of Control Engineering Beijing 100190China

Robotic picking and placing systems can increase the flexibility of packing objects in a box and are attractive in many ***,owing to inevitable uncertainties in both the picking and placing stages,the objects cannot be placed at desired positions accurately and hence cannot be packed *** paper presents an additional pushing action that maximizes the packing density;i.e.,after being released from the robot end,the object is moved by robotic pushing actions to arrange the packing *** robotic pushing strategy is determined through a deep reinforcement learning *** idea is to compress the objects toward a corner to improve the volume utilization rate by minimizing the result of a heuristic *** learning process is implemented in simulation and the trained network is transferred to a robot system *** and experiments are presented for the packing of regular and irregular objects to verify the proposed method.

关键词： robotic pushing three-dimensional packing reinforcement learning

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：