检索结果-内蒙古大学图书馆

10th International conference on control, Decision and Information technologies (CoDIT)

作者： Ben Rouighi, Ines Chtioui, Hajer Jegham, Imen Ben Khalifa, Anouar Univ Sousse LATIS Lab Adv Technol & Intelligent Syst Ecole Natl Ingn Sousse Sousse 4023 Tunisia Univ Jendouba Inst Natl Technol & Sci Kef Le Kef 7100 Tunisia

ISBN: (纸本)9798350373981;9798350373974

Deploying drones with deep-learning capabilities for real-time object detection is a trendsetting strategy, particularly in dynamic environments such as Intelligent Transportation systems. Drones, or unmanned Aerial Vehicles, offer advantages including a wide field of view, cost-effectiveness, and operational efficiency, making them ideal for perception and surveillance in dynamic settings. However, drones face several challenges in terms of on-board computational capabilities, constraining the deployment of complex algorithms for aerial imagery analysis. In this paper, we exhaustively study the challenges of real-time object detection for drones, emphasizing the adaptability and effectiveness of deep learning-based detectors. We fine-tune and evaluate the six most used scaled versions of real-time object detectors for drone-imagery, using a benchmark, tailored for drone-captured data, to assess detection accuracy, inference speed, and computational efficiency. Our study proves that YOLOv5n excels in terms of inference speed at 454 FPS, but with lower precision, while YOLOv8n surpasses in precision but requires more resources and longer inference times. Larger versions show moderate accuracy improvement but demand increased computational resources and extended inference duration.

关键词： Drone unmanned Aerial Vehicle Real-Time Object Detection ITS YOLO

来源：评论

学校读者我要写书评

暂无评论

Using Artificial Intelligence to control Drones 7

Using Artificial Intelligence to Control Drones

引用

7th IEEE International conference on Methods and systems of navigation and Motion control, MSNMC 2023

作者： Pavlenko, Volodymyr Ponomarenko, Ihor Morhulets, Oksana Osadchyi, Viacheslav Ponomarenko, Dmytro Hrygorevska, Olena Kyiv National University of Technologies and Design Faculty of Mechatronics and Computer Technologies Kyiv Ukraine State University of Trade and Economics Department of Marketing Kyiv Ukraine Kyiv National University of Technologies and Design Department of Tourism Hotel and Restaurant Business Kyiv Ukraine Borys Grinchenko Kyiv University Faculty of Economics and Management Kyiv Ukraine International University of Business and Law Kyiv Ukraine Kyiv National University of Technologies and Design Department of Finance and Business Consulting Kyiv Ukraine

ISBN: (纸本)9798350395150

The importance of using drones to optimize results by types of economic activity is presented. The expediency of conducting comprehensive scientific research with the aim of finding new ways of using the presented technology and identifying ways to optimize the control of unmanned vehicles has been proven. It has been established that thanks to the improvement of the drone control system, it is possible to achieve qualitatively new results regarding the collection of various information and solving logistical problems in an extreme environment or conditions of uncertainty. The main factors of the active development of algorithms in the Data science, which allow optimizing various processes in the field of human activity, are presented. The importance of using server storage for the accumulation and processing of large arrays of heterogeneous information is revealed. Features of the transformation of the mathematical models use directions for data processing and the activation of the machine learning algorithms development are given. The reasons for the intensification of artificial intelligence introduction as a technology for making effective management decisions are revealed. The main directions of using artificial intelligence to optimize the management and operation of unmanned aerial vehicles are presented. A conceptual scheme of collection, accumulation and processing of heterogeneous information, which is generated by various devices placed on drones, and directions for applying artificial intelligence to achieve effective results are presented. The expediency of improving pattern recognition technology on a permanent basis has been proven, which will allow more accurate assessment of individual elements of the external environment and increase the efficiency of the logistics systems implementation. The possibility of using artificial intelligence for decision-making in conditions of uncertainty without the influence of the human factor and training on a perm

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Analysis and Design of Key technologies for Intelligent navigation Ship 9

Analysis and Design of Key Technologies for Intelligent Navi...

引用

9th International Technical conference on Frontiers of Hydraulic and Civil Engineering Technology, HCET 2024

作者： Zhou, Dan Fan, Minghua Li, Yabin Yao, Zhixuan China Waterborne Transport Research Institute Beijing100088 China Shanghai Maritime Surveying and Mapping Center Shanghai200090 China Qingdao Shipping Development Research Institute Shandong Qingdao266034 China

ISBN: (纸本)9781643685595

Intelligent navigation of ships is the core content of intelligent ships, and the development of key technologies for intelligent navigation of ships plays a decisive role in the implementation of intelligent navigation. This article analyzes and proposes the framework and key technology system of intelligent navigation system for ships. The intelligent navigation system for ships includes three parts: intelligent navigation, intelligent navigation protection, and shore based remote control center. The key technologies for intelligent navigation of ships mainly include intelligent perception and recognition, intelligent route planning, intelligent collision avoidance, communication navigation, and remote driving control. Analyze the implementation process of key technologies such as intelligent perception and cognition, intelligent route planning, and intelligent collision avoidance in response to the needs and characteristics of intelligent navigation of ships. Propose a key technology implementation process plan for intelligent navigation of ships, providing direction for the construction of intelligent navigation systems and technical systems for ships. © 2024 The Authors.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Adaptive Super-Twisting Sliding Mode Attitude control for Moving Mass-Actuated unmanned Aerial Vehicles 30

Adaptive Super-Twisting Sliding Mode Attitude Control for Mo...

引用

30th Saint Petersburg International conference on Integrated navigation systems, ICINS 2023

作者： Zheng, Jingzhong Neusypin, K.A. Selezneva, M.S. Zhou, Ruiyang Bauman Moscow State Technical University Moscow Russia

ISBN: (纸本)9785919950950

Different from the traditional fixed-wing unmanned aerial vehicles mounted with ailerons, the moving mass-Actuated fixed-wing unmanned aerial vehicle (MFUAV) uses the offset of moving mass in the airframe to perform roll motion. Considering the model uncertainties and disturbances, a nonlinear coupled mathematical model of the MFUAV is established. The attitude controller with finite time convergence is designed with the help of adaptive supertwisting sliding mode control (ASTSMC). Through the Lyapunov analysis, the proposed controller guarantees the stability. Simulation results are demonstrated to verify the effect of the designed controller, which makes the system with good command tracking performance and robustness. © 2023 Concern CSRI Elektropribor, JSC.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Underwater Inspection and Monitoring: technologies for Autonomous Operations

引用

IEEE AEROSPACE AND ELECTRONIC systems MAGAZINE 2024年第5期39卷 4-16页

作者： Ioannou, Giorgio Forti, Nicola Millefiori, Leonardo M. Carniel, Sandro Renga, Alfredo Tomasicchio, Giuseppe Binda, Stefano Braca, Paolo NATO Ctr Maritime Res & Expt CMRE I-19126 La Spezia Italy Univ Florence Florence Italy Univ Naples Federico II I-80125 Naples Italy Telespazio SpA I-00156 Rome Italy European Space Agcy ESA ESTEC European Space Res & Technol Ctr NL-2201 Noordwijk Netherlands

The underwater environment poses numerous challenges and risks, making unmanned underwater vehicles (UUVs) an indispensable alternative to human operators. Numerous remotely operated vehicles (ROVs) and autonomous underwater vehicles (AUVs) have been developed as a valuable resource in a broad spectrum of underwater operations. However, the deployment and operation of UUVs face significant challenges due to the unique underwater environment that critically affects positioning, navigation, and timing performance, making it incomparable to above-water applications. This discrepancy significantly impacts the decision-making process of industrial operators, particularly those in the sector of critical undersea infrastructures (CUIs). Despite advancements, they persist in the use of heavy ROVs deployed from an expensive and environmentally impactful mothership for inspection and monitoring (I&M) tasks. To explore the potential revolutionary impact on underwater operations, we analyze the resilience of CUIs, and we review the most promising robotics developments that are currently or soon to be available. The forthcoming solutions not only promise to enhance the efficiency of I&M operations, thereby bolstering the security of CUIs, but they also have the potential to transform the broader field of underwater operations as a whole.

关键词： Underwater cables Optical fiber cables Pipelines Optical fibers Inspection Robots Task analysis Monitoring Autonomous systems Autonomous underwater vehicles Performance evaluation navigation Position control underwater vehicles underwater power cables underwater structures underwater technology

来源：评论

学校读者我要写书评

暂无评论

Natural Language navigation for Robotic systems: Integrating GPT and Dense Captioning Models with Object Detection in Autonomous Inspections

Natural Language Navigation for Robotic Systems: Integrating...

引用

2nd Joint conference of the Construction Research Congress (CRC) / Construction-Institute (CI) Summit

作者： Choudhury, Nilay R. Wen, Yining Chen, Kaiwen Univ Alabama Dept Mech Engn Tuscaloosa AL USA Univ Alabama Dept Civil Construct & Environm Engn Tuscaloosa AL 35487 USA

ISBN: (数字)9780784485262

ISBN: (纸本)9780784485262

Autonomous unmanned Aerial Vehicles (UAVs) are rapidly transforming industries requiring inspection and surveillance. However, conventional UAV systems often require complex control schemes and lack adaptability, limiting their efficacy in variable environments such as indoor inspections. This paper introduces an innovative system integrating the cutting-edge Generative Pretrained Transformer (GPT) models and dense captioning models for autonomous navigation and fault detection in indoor environments. Our approach, displaying human-like flexibility, allows the drone to interpret and respond to natural language commands, vastly enhancing its accessibility and user-friendliness. Simultaneously, the drone utilizes object dictionaries derived from dense captioning of its captured images, facilitating an advanced understanding of its surroundings. These capabilities equip the drone to adapt its behavior and effectively handle unexpected scenarios, significantly enhancing the efficiency and accuracy of indoor inspections. This research contributes to revolutionizing building inspections, making the process more user-friendly, and localizable to a broader user base.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Single Beacon Deep Water navigation Method Based on the T-Distribution

A Single Beacon Deep Water Navigation Method Based on the T-...

引用

2024 IEEE International conference on unmanned systems, ICUS 2024

作者： Zhu, Zhongben Li, Ruze Mu, Xiaokai Bai, Guiqiang Qingdao Innovation and Development Base Harbin Engineering University Qingdao China

ISBN: (纸本)9798350384185

In deep water environments, the autonomous underwater vehicle (AUV) operates at a longer distance from the seafloor, which means it can only measure water tracking velocity rather than bottom tracking velocity. However, this water tracking velocity is significantly affected by unpredictable ocean currents, posing a major challenge for precise navigation. To address these issues, this study proposes an integrated multi-sensor navigation system based on the inertial navigation system (INS), incorporating a single beacon, doppler velocity log (DVL), and depth meter (DM). The single beacon provides distance information to estimate current flow velocity, enabling compensation for the DVL-measured water tracking velocity. To handle time-varying and non-Gaussian measurement noise, we employ a hierarchical state-space model with t-distribution for measurement noise, and inverse Wishart and gamma distributions for unknown parameters. To comprehensively estimate the state vector, measurement noise, and these unknown parameters, a variational bayesian (VB) method is utilized. This method updates posterior distributions iteratively, optimizing all parameters simultaneously. Experimental results based on the field data shows that the proposed algorithm significantly improves the navigation performance compared to conventional method. © 2024 IEEE.

关键词： Inertial navigation systems

来源：评论

学校读者我要写书评

暂无评论

EFFICIENT, REAL-TIME AUTONOMOUS navigation SYSTEM FOR SMALL unmanned AIRCRAFT

EFFICIENT, REAL-TIME AUTONOMOUS NAVIGATION SYSTEM FOR SMALL ...

引用

2024 CSAA/IET International conference on Aircraft Utility systems, AUS 2024

作者： Liu, Yunfei Ding, Yi Xie, Ao Che, Jiaxing Beihang University Beijing China Shenyang Aircraft Design and Research Institute China

With the continuous development of the UAV industry, the demand for small UAVs that can fly autonomously in unknown and complex scenarios is increasing. One of the core technologies is the autonomous obstacle avoidance navigation technology in denial scenarios, which requires small UAVs to have an autonomous localization function during flight and can navigate autonomously according to the observed environmental information to avoid collision with obstacles and complete the corresponding flight tasks according to the instructions. To this end, this paper designs an autonomous navigation system with both real-time and execution efficiency, which can be deployed and operated on an embedded platform with limited computational resources to meet the needs of small UAV autonomous navigation applications. © The Institution of Engineering & Technology 2024.

关键词： Aircraft accidents

来源：评论

学校读者我要写书评

暂无评论

Coordinated control Of Tethered unmanned Aerial Vehicle With Launch And Recovery System 6

Coordinated Control Of Tethered Unmanned Aerial Vehicle With...

引用

2024 International conference on Smart systems and technologies

作者： Prkacin, Vicko Duras, Anton Palunko, Ivana Univ Dubrovnik Lab Intelligent Autonomous Syst Dubrovnik Croatia

ISBN: (纸本)9798350386394;9798350386400

The primary objective of the launch and recovery system (LARS) is to extend the operational time of battery-powered unmanned aerial vehicles (UAVs) by providing continuous power via a tether while ensuring safe flight operations. However, the tether introduces coupling between the LARS and UAV, increasing the system's complexity, and demanding the development of algorithms for coordinated control. Additionally, mounting the LARS on a mobile robot or vehicle provides significant operational flexibility, but introduces spatial constraints in terms of design, thereby limiting the landing platform size. This means there is no margin for error in the landing phase, making precise and reliable estimation of the UAV's position relative to the LARS an imperative. This paper gives a comprehensive overview of the developed system and emphasizes the approach taken to address these challenges from a control and estimation perspective. The effectiveness of the system and proposed control algorithms is validated in a real-world environment through field tests carried out during the SeaClear project demonstrations.

关键词： aerial robotics autonomous landing tethered uav

来源：评论

学校读者我要写书评

暂无评论

Sea-U-Dragon: A Lightweight unmanned Underwater Vehicle for Robot-Environment Interaction 11

Sea-U-Dragon: A Lightweight Unmanned Underwater Vehicle for ...

引用

11th IEEE International conference on Cybernetics and Intelligent systems (CIS) / 11th IEEE International conference on Robotics, Automation and Mechatronics (RAM)

作者： Gao, Songqun Yan, Ruixin Zhao, Zuoquan Ding, Wendi Dou, Minghao Chen, Ben M. Chinese Univ Hong Kong Dept Mechan Auto Engn Hong Kong Peoples R China

ISBN: (纸本)9798350364200;9798350364194

Although unmanned underwater vehicles (UUVs) exhibit significant advantages in coastal water applications (e.g. underwater grasping), dynamic and disturbed environments, along with the uncertainties in underwater positioning and navigation pose challenges to dynamic interaction with underwater environments. To deal with these challenges, this paper explores the underwater robot-environment-interaction (REI) task by introducing a lightweight UUV named Sea-U-Dragon. Sea-U-Dragon employs an active-passive compliant control strategy, featuring a flexible end effector designed to passively adapt to underwater dynamic changes, along with an uncertainty disturbance estimator (UDE)-based dynamic motion/force controller to compensate for underwater uncertainties. Finally, the trajectory following experiments and dynamic force tracking demonstrations justify the maneuverability of Sea-U-Dragon and its ability to perform dynamic interaction tasks.

关键词： unmanned Underwater Vehicle Impedance control Robot-environment interaction

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：