检索结果-内蒙古大学图书馆

2024 International Conference on Artificial Intelligence and Emerging technology, Global AI Summit 2024

作者： Malik, Ishan Singh, Sanjay Kumar Saxena, Pranshu University School of Automation and Robotics Guru Gobind Singh Indraprastha University East Delhi Campus Surajmal Vihar Delhi110092 India Abes Engineering College Department of Information Technology Ghaziabad India

ISBN: (纸本)9798350379716

The inspiration that drives this study is the increase in the prevalence of misinformation, and the need to solve the big challenge of detecting fake news. With the possibility of uncontrolled misinformation disastrously impacting our society, the objective of our study is to make contributions towards the body of knowledge which aims to improve the efficiency and accuracy of current methodologies to detect false information. Although there has been an improvement in the fake news detection systems, their adaptation to real-time applications remains sub-optimal due to the subtle and complex processing involved with handling misinformation. The purpose of this study is to bridge this gap and come up with a better detection model using the Recurrent neural network (RNN) models like Long Short-Term Memory (LSTM) and Bi-directional LSTM (BiLSTM) that will enhance the performance of the existing models, especially in terms of detection accuracy, as the existing systems are weak in the 'disagree' category and mostly misclassify it. We use a mix of machine learning algorithms and natural language processing techniques. Integrating LSTM with BiLSTM will analyze textual content at a granular level to find patterns representing fake news. The preliminary results have indicated that our model is performing significantly better than existing ones, with an overall improvement of up to 86.25% in accuracy [15]. However, in the 'disagree' category, there are a few challenges faced by the system, reflecting the scope for many improvements in the future. Our research has made a valuable contribution to the knowledge and tools in the area of digital information credibility by providing a strong model that improves detection rates of more subtle cues of misinformation thereby, combating the spread of fake news. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Design of Mixed Reality Assembly System Based on Improved ORB Algorithm 3

Design of Mixed Reality Assembly System Based on Improved OR...

引用

3rd International Conference on Computer Vision, Image and Deep Learning and International Conference on Computer Engineering and Applications, CVIDL and ICCEA 2022

作者： Lu, Na Xiao, YongFei Zhao, Jie Shandong Provincial Key Laboratory of Robot and Manufacturing Automation Technology ShanDong China Harbin Institute of Technology Institute of Automation Shandong State Key Laboratory of Robotics and System Harbin China

ISBN: (纸本)9781665459112

This paper studies the natural feature point detection algorithm in a virtual assembly system. To address the problems of unsatisfactory detection effect and poor matching accuracy of the ORB algorithm, a feature uniform distribution algorithm based on pyramidal grid division is proposed, and a strategy of retaining feature points according to Harris response values is formulated to solve the problem of feature point aggregation while ensuring extraction speed. Hamming distance and the RANSAC algorithm are used to constrain the matching results. The robot assembly system based on this algorithm overlays the 3D model of the spraying robot and virtual information in the mobile device to improve the assembly efficiency of the staff. The experimental results show that the mixed reality(MR) assembly system based on the algorithm of this paper performs well, and the real-time performance and alignment accuracy are improved. © 2022 IEEE.

关键词： Assembly

来源：评论

学校读者我要写书评

暂无评论

Boosting Behavior Tree Generation for Robots with Large Language Models and Genetic Programming

Boosting Behavior Tree Generation for Robots with Large Lang...

引用

2025 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots, SIMPAR 2025

作者： Verdaguer-Gonzalez, Aaron Dalmau-Moreno, Magi Merino, Luis Garcia, Nestor Eurecat Technology Centre of Catalonia Robotics and Automation Unit Barcelona Spain Universidad Pablo Olavide Service Robotics Laboratory Sevilla Spain

ISBN: (纸本)9798331516857

Mobile robots are becoming increasingly ubiquitous in modern society, requiring more human-like interaction capabilities, such as following operator instructions and collaborating with humans. Conventional robot programming methods often fall short in achieving these complex behaviors. Behavior Trees (BTs) offer a promising alternative due to their modularity, scalability and reactivity. We propose utilizing general purpose, system-prompted Large Language Model (LLM) assistants to decompose task descriptions into executable BTs, which are subsequently refined using Genetic Programming (GP) and a state machine like low-resource BT execution simulator, where they will be tested for task completion. This approach eliminates the need for fine-tuning LLMs, thereby reducing computational costs and saving time and energy. Our method successfully solves all proposed scenarios, enhances applicability across diverse environments, and democratizes behavior generation for non-experts, outperforming baseline methods in efficiency. © 2025 IEEE.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Monocular Visual-Inertial and Robotic-Arm Calibration in a Unifying Framework

引用

IEEE/CAA Journal of Automatica Sinica 2022年第1期9卷 146-159页

作者： Yinlong Zhang Wei Liang Mingze Yuan Hongsheng He Jindong Tan Zhibo Pang Key Laboratory of Networked Control Systems Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016 State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang 110016 Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China School of Computing Wichita State UniversityWichita 67260 USA Department of Mechanical Aerospace and Biomedical EngineeringUniversity of TennesseeTN 37996 USA Department of Automation Technology ABB Corporate Research SwedenVasteras 72178Sweden Department of Intelligent Systems Royal Institute of Technology(KTH)Stockholm 11428Sweden

Reliable and accurate calibration for camera,inertial measurement unit(IMU)and robot is a critical prerequisite for visual-inertial based robot pose estimation and surrounding environment ***,traditional calibrations suffer inaccuracy and *** address these problems,this paper proposes a monocular visual-inertial and robotic-arm calibration in a unifying *** our method,the spatial relationship is geometrically correlated between the sensing units and robotic *** decoupled estimations on rotation and translation could reduce the coupled errors during the ***,the robotic calibration moving trajectory has been designed in a spiral pattern that enables full excitations on 6 DOF motions repeatably and *** calibration has been evaluated on our developed *** the experiments,the calibration achieves the accuracy with rotation and translation RMSEs less than 0.7°and 0.01 m,*** comparisons with state-of-the-art results prove our calibration consistency,accuracy and effectiveness.

关键词： Calibration inertial measurement unit(IMU) monocular camera robotic arm spiral moving trajectory

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Visual - SLAM based Automated Guided Vehicle

Design and Development of a Visual - SLAM based Automated Gu...

引用

International Conference on Advances in Electronics, Computers and Communications (ICAECC)

作者： Ankur Bhargava Ajay S. Singholi Mohd. Suhaib Faculty of Engineering and Technology Jamia Millia Islamia Delhi India Robotics & Automation University School of Robotics & Automation India Delhi

ISBN: (数字)9798350305449

ISBN: (纸本)9798350305456

The automobile industry is currently undergoing fast change as big manufacturers devote their attention to the development of future self- driving vehicles or automated guided vehicles. As a result, mobile robots and current automotive technologies are integrating to create the area of autonomous navigation. The camera sensor is the one garnering the most attention in terms of autonomy sensor research due to the large amount of information it provides for object detection and classification algorithms in addition to depth, coloring, size, and texture recognition. In the last ten years, there have been significant advancements in computing capabilities and image analysis algorithms. The requirement for developing low-level motion controllers grew as a consequence of the increase in machine vision performance and capabilities. This article discusses mecanum wheel mobile robotic applications of vision and SLAM-based motion controller. When using sensors like cameras or Lidar, autonomous mobile robots usually use the vision- based & simultaneous localization and mapping (SLAM) technology. The four-wheeled autonomous robot model that was utilized in the studywas created using a Jetson board with high performance processor, a depth camera, and LIDAR sensors along with ROS's RVIZ software.

关键词： Visualization Simultaneous localization and mapping Laser radar Accuracy Navigation Robot kinematics Robot vision systems

来源：评论

学校读者我要写书评

暂无评论

A study on design and control of Omni-directional mecanum wheels based AGV system

A study on design and control of Omni-directional mecanum wh...

引用

International Conference on Computing and Networking technology (ICCNT)

Automated guided vehicles (AGVs) have emerged as crucial equipment in sectors that demand reliable and effective transportation and material handling systems. The design and control features of AGV systems are discussed in general terms in this study, with an emphasis on important factors and recent developments. The vehicle platform, sensing and perception systems, navigational algorithms, and control architecture are all essential parts of the design of an AGV system. To fit the application's unique requirements, the vehicle platform must be properly developed, taking into account elements like load capacity, maneuverability, and power supply. The AGV can sense its surroundings and maneuver on its own thanks to the choice and integration of sensors including LiDAR, cameras, and encoders. Simultaneous Localization and Mapping (SLAM), one of the most sophisticated perception algorithms, is essential for precisely mapping the environment and locating the AGV within it. Because of navigation algorithms, AGVs can efficiently plan their routes, avoid dangers, and reach their targets. Methods for establishing a path enable smooth, collision-free travel by accounting for factors including distance, time, and dynamic restrictions. Real-time control systems regulate the AGV's speed, acceleration, and steering, enabling accurate and secure operation in a variety of situations. The controls design should enable monitoring of the system and detection of problems in along with enabling integration of perception, navigating, and control modules. This paper examines the mechanical and electrical design of a test prototype autonomous guided vehicle (AGV). The SLAM technique apply in the present work successfully resolves the localization problem in conjunction with the navigation algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Lightweight YOLOv5 Model Integrating GhostNet and Attention Mechanism 4

A Lightweight YOLOv5 Model Integrating GhostNet and Attentio...

引用

4th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2023

作者： Dou, Xinke Wang, Ting Shao, Shiliang School of Information Engineering Shenyang University of Chemical Technology Shenyang China Shenyang Institute of Automation State Key Laboratory of Robotics Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798350326444

Aiming at the problems of complex structure of neural network, large number of parameters and difficult deployment to terminal devices, this paper proposes an improved lightweight object detection model for the purpose of building a model with high classification accuracy and low complexity. First, the one-stage detector yolov5 is used as the base network. Considering the excessive redundant features of feature extraction, Ghost module is used to replace the traditional convolution, effectively allocate computing resources, to reduce the size of the model and improve the speed of model detection. When designing model bottleneck structure, Normalization-based Attention Module (NAM) is added to improve training efficiency and reduce model complexity. Experimental results show that compared with YOLOv5, the calculation speed of the proposed model is increased by 17% and the accuracy is reduced by less than 2%, which is of great significance in the environment of low-performance computing equipment. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Feature Space Augmentation and Old Class Space Preservation for Class Incremental Learning 42

Feature Space Augmentation and Old Class Space Preservation ...

引用

42nd Chinese Control Conference, CCC 2023

作者： Zeng, Ming Li, Siying Liu, Jiazhe Li, Yuanhao Institute of Robotics and Automation Systems School of Electrical and Information Engineering Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System Tianjin University Tianjin300072 China

ISBN: (纸本)9789887581543

The ability of continuously learning new knowledge without forgetting old ones is crucial to adapt to an ever-changing world. This scenario becomes more challenging when the previous data are not available. Current class incremental learning (CIL) approaches tend to incorporate new classes with backward compatibility, i.e., maintaining discriminability of old ones. By contrast, we focus on the extensibility and compatibility for future new classes in the early stage. Our proposed method achieves this by augmenting feature space. In detail, a large number of pseudo-new classes are generated via real example mixture and then train the initial spatially augmented model using pseudo-new classes and the base classes. Besides, considering the fact that it is impossible to maintain backward compatibility with only one prototype for each old class, the updated model also needs to preserve old class space in incremental stages. We employ a certain perturbation to the old class prototypes to effectively avoid old class space from being over-squeezed by the samples of new classes. The experiments on CIFAR-100 and ImageNet-Subset (100 classes) demonstrate that our method substantially reduces the overlap of old and new classes, outperforming state-of-the-art various baselines. © 2023 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Catastrophic forgetting Class incremental learning Feature space augmentation Old class space preservation Pseudo-new classes

来源：评论

学校读者我要写书评

暂无评论

Method for Formation Control of AUV Group in Environment with Obstacles Based on Visual Information

Method for Formation Control of AUV Group in Environment wit...

引用

2023 International Russian automation Conference, RusAutoCon 2023

作者： Oseledets, V.A. Yukhimets, D.A. Far East Federal University Department of Automation and Robotics Vladivostok Russia Far East Federal University Institute of Marine Technology and Problem Feb Ras Vladivostok Russia

ISBN: (纸本)9798350345551

The paper proposes a modification of the method for formation control of the group of autonomous uninhabited underwater vehicles (AUVs) in the unknown environment containing obstacles. AUVs move in the "leader-follower"mode in the given formation. The AUV-leader has information about the mission, swims to the target and defines the motion trajectory to safely avoid the detected obstacles. AUV-followers follow the leader, in accordance with the place given to them in the formation. For this movement, information about the current position of the leader AUV is used. In the basic proposed method, the followers receive this information via hydroacoustic communication channels. Obstacles and the distance to them are determined via onboard rangefinders. The low bandwidth of hydroacoustic channels and large delays in data transmission do not provide safe and accurate movement of group members when they are close to an obstacle or to another AUV. To solve this problem, using onboard video cameras of AUV-followers and technical vision to determine the position of the leader, on which a special beacon is installed, is proposed. This approach makes possible eliminating delays in the receiving of information by the followers and ensure the safe movement of the AUV group when using high-precision control systems. The effectiveness of the proposed modification of the method is confirmed by the results of mathematical modeling. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Object detection methods for Image-based Visual Servoing of 6-DOF Industrial robot

Object detection methods for Image-based Visual Servoing of ...

引用

2022 IEEE Region 10 Symposium, TENSYMP 2022

作者： Krishnan, Megha G Ashok, S. Adi Shankara Institute of Engineering and Technology Department of Robotics and Automation India National Institute of Technology Department of Electrical Engineering Calicut India

ISBN: (数字)9781665466585

ISBN: (纸本)9781665466585

The employment of robots in manufacturing industries is on the rise due to the need for automated industrial operations. Visual servoing is a well-advanced method of controlling the robot movement based on visual sensor feedback. In image-based visual servoing (IBVS), the image features at the final pose implicitly define the desired camera pose relative to the target. The major issue associated with image-based visual servoing of industrial manipulators is the identification and tracking of object to be manipulated from the image sequence. In this paper, two methods are employed to detect the object for providing image feature vector in the visual servoing feedback loop. One method employs a robust and fast algorithm called SpeededUp Robust Features (SURF) for image comparison. Another method utilizes the method of comparing measuring the properties of the image region and comparing with the given image to detect the object. These algorithms are applied in the image-based visual servoing system for obtaining the image feature error to drive the system. Real-time experiments are conducted in IBVS system where IRB 1200 industrial robot manipulator is active with eye-in-hand camera. The results illustrate the improved performance of the object identification algorithms. © 2022 IEEE.

关键词： Object detection

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：