检索结果-内蒙古大学图书馆

robotics, Control and automation (ICRCA), international conference on

作者： Bin CHEN Yugo NAKAMURA Shogo FUKUSHIMA Yutaka ARAKAWA ISEE. Kyushu University Kyushu University Fukuoka Japan

ISBN: (数字)9798350344721

ISBN: (纸本)9798350344738

Dense video captioning tasks are used to detect interesting events and provide descriptive text for these events from untrimmed videos. this technology has the potential to be used in security surveillance and human care applications. However, current methods often overlook the relationships between objects in the video, which limits their applicability and makes it challenging to adapt them to specific domains, such as video summarization for indoor human activities. In these scenarios, human activities are closely intertwined with the objects in the scene. In this paper, we propose a plug-and-play module designed to enhance existing dense video captioning methods with spatial information. Specifically, we extract spatial information about the interesting objects using Red-Green-Blue-Depth (RGB-D) images and the results of image segmentation. We then integrate this information into the captions generated by the Dense Video Captioning (DVC) method using a fine-tuned Large Language Model (LLM). We evaluate the performance of our model on a custom dataset and demonstrate that our system provides a convenient and effective approach for obtaining space-enhanced captions.

关键词： Image segmentation Surveillance Large language models Pipelines Information retrieval Security Human activity recognition

来源：评论

学校读者我要写书评

暂无评论

A Dual-Graph Learning Framework with Sparse Adaptive Embedding for EEG Emotion Recognition

A Dual-Graph Learning Framework with Sparse Adaptive Embeddi...

引用

Industrial automation, robotics and Control Engineering (IARCE), international conference on

作者： Wenkang Liu Fangkun Li Yang Li Department of Automation Science and Electrical Engineering Beihang University Beijing China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

EEG brain networks capture the complex relationships between multiple brain regions, providing rich information for emotion recognition. However, most existing methods rely on dynamically random initialized adjacent matrix, which limits their ability to effectively model emotional features across different brain regions. Additionally, these methods typically ignore the importance of synchronously modeling both adjacent and long-distance channels, resulting to suboptimal emotion recognition performance. In this paper, we propose a novel dual-graph learning framework with sparse adaptive embedding (DGLF-SAE) for EEG-brain-network emotion recognition, which includes a global hypergraph sparse adaptive embedding (GHG-SAE) module and a local adjacency graph sparse adaptive embedding (LAG-SAE) module. Specifically, the GHG-SAE module is designed to capture global relationships by associating long-distance channels, while the LAG-SAE module focuses on learning local relationships by modeling adjacent channels. We validate the effectiveness of our proposed DGLF-SAE on the SEED and SEED-IV datasets, with experimental results (98.05% and 92.83% on SEED and SEED-IV datasets, respectively) demonstrating that our approach outperforms state-of-the-art methods.

关键词： Emotion recognition Adaptation models Technological innovation Control engineering Service robots Graph convolutional networks Benchmark testing Brain modeling Electroencephalography Sparse matrices

来源：评论

学校读者我要写书评

暂无评论

Hierarchical control of soft manipulators towards unstructured interactions

引用

international JOURNAL OF robotics RESEARCH 2021年第1期40卷 411-434页

作者： Jiang, Hao Wang, Zhanchi Jin, Yusong Chen, Xiaotong Li, Peijin Gan, Yinghao Lin, Sen Chen, Xiaoping Univ Sci & Technol China Sch Comp Sci Multiagent Syst Lab Hefei 230027 Anhui Peoples R China

Performing daily interaction tasks such as opening doors and pulling drawers in unstructured environments is a challenging problem for robots. the emergence of soft-bodied robots brings a new perspective to solving this problem. In this paper, inspired by humans performing interaction tasks through simple behaviors, we propose a hierarchical control system for soft arms, in which the low-level controller achieves motion control of the arm tip, the high-level controller controls the behaviors of the arm based on the low-level controller, and the top-level planner chooses what behaviors should be taken according to tasks. To realize the motion control of the soft arm in interacting with environments, we propose two control methods. the first is a feedback control method based on a simplified Jacobian model utilizing the motion laws of the soft arm that are not affected by environments during interaction. the second is a control method based on Q -learning, in which we present a novel method to increase training data by setting virtual goals. We implement the hierarchical control system on a platform with the Honeycomb Pneumatic Networks Arm (HPN Arm) and validate the effectiveness of this system on a series of typical daily interaction tasks, which demonstrates this proposed hierarchical control system could render the soft arms to perform interaction tasks as simply as humans, without force sensors or accurate models of the environments. this work provides a new direction for the application of soft-bodied arms and offers a new perspective for the physical interactions between robots and environments.

关键词： Soft robotics motion control flexible arms dexterous manipulation

来源：评论

学校读者我要写书评

暂无评论

A Control Algorithm for an Aerial Co-Manipulation System

A Control Algorithm for an Aerial Co-Manipulation System

引用

Industrial automation, robotics and Control Engineering (IARCE), international conference on

作者： Fan Chen Xinyue Zhang Yuxin Li Yixin Wang Electronic Information Engineering Southwest University of Science and Technology Mianyang China Communication Engineering Southwest University of Science and Technology Mianyang China Robotics Engineering Southwest University of Science and Technology Mianyang China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

During aerial co-manipulation, addressing the disturbances caused by the motion of the lower UAV on the aerial dexterous manipulation platform and the perturbations induced by the manipulation platform's own movement, as well as the issue of the inadequate number of existing simulation platforms, this study introduces an adaptive sliding mode control approach that leverages radial basis function neural networks and establishes a simulation platform for aerial comanipulation within the Gazebo environment. In the control method, the Lagrangian equation is employed for standardized modeling, and the model is simplified through projection. the universal approximation property of neural networks is utilized for adaptive rate optimization. Additionally, a sliding mode algorithm grounded on the exponential reaching law is implemented to bolster robustness. To further mitigate chattering, the hyperbolic tangent function is employed. Finally, the results were verified through trajectory tracking in Matlab/Simulink, ensuring that the system converged in about 1 second and achieved micron-level multi-channel tracking error accuracy, effectively reducing chatter. the Gazebo simulation platform sets up three aerial dexterous manipulation platforms capable of performing basic aerial tasks, and control stability is verified using PID algorithms.

关键词： Adaptation models Accuracy Uncertainty Trajectory tracking Heuristic algorithms Visual systems Mathematical models Stability analysis Sliding mode control Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

A Kalman Filter-Based Submersible Position Prediction Model and a Multi-Target Dynamic Search and Rescue Scheme

A Kalman Filter-Based Submersible Position Prediction Model ...

引用

international conference on Control, automation, robotics and Vision (ICARCV)

作者： Yujie Tian Yuxi Luo Sitong Zhou Kun Zhang Yan Wang School of Astronautics Beihang University Beijing China School of Mechanical Electrical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

Aiming at the deep-sea submarine search and rescue problem, this paper proposes a universally applicable submarine position prediction model and search model. the position prediction of the submersible is realized by Kalman filtering and dynamics modeling. Meanwhile, Monte Carlo method is used to construct the initialized population of the motion trajectory and optimize the search path step by step by iterative genetic algorithm. In this paper, the optimal search path is taken as the objective, the main ship SAR trajectory is simulated, and the probability of the diver is fitted as a function of time and cumulative search results. For the multiple submersible search and rescue problem, this paper proposes two possible search and rescue schemes and compares the search and rescue time. then we propose the optimal multi-objective dynamic search and rescue method. In addition, this paper adopts the G1-entropy weight-coefficient of variation combined assignment method to evaluate different search devices and creatively adopts the CRITIC method to secondary assign the weights obtained from different evaluation methods to select the optimal search device. Finally, sensitivity and robustness analysis are also carried out in this paper.

关键词： Analytical models Sensitivity Predictive models Search problems Robustness Trajectory Kalman filters Vehicle dynamics Underwater vehicles Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

SGCL: A B-Rep-Based Geometry Modeling Language in MATLAB for Designing 3D-Printable Medical Robots 17

SGCL: A B-Rep-Based Geometry Modeling Language in MATLAB for...

引用

17th IEEE international conference on automation Science and Engineering (CASE)

作者： Sun, Yilun Lueth, Tim C. Tech Univ Munich Inst Micro Technol & Med Device Technol Munich Germany

ISBN: (纸本)9781665418737

the additive manufacturing technology greatly shortens the design and fabrication period of a complex robotic system, as the entire system can be once printed in a short time without complicated assembly process. To keep up with the fast development of this new technology, an efficient tool for constructing compact and 3D-printable surface models is highly desirable. In this paper, we present a novel boundary-representation-based geometry modeling language, the Solid Geometry Coding Language (SGCL), for the efficient surface modeling of 3D-printable medical robots. the proposed language is implemented in MATLAB, based on our previously developed modeling toolbox, the Solid Geometry Library. the basic data structures and modeling syntax of the language are illustrated in detail. To demonstrate the performance of the SGCL language, a modeling case as well as the 3D-printed prototype is presented. Furthermore, the proposed language could also be used as an open platform for developing optimization-based automatic synthesis methods for 3D-printed medical instruments and robots.

关键词： Geometry Solid modeling Medical robotics Prototypes Tools Syntactics Solids

来源：评论

学校读者我要写书评

暂无评论

Trinary Relationship Interaction Detection

Trinary Relationship Interaction Detection

引用

IEEE international conference on Mechatronics, robotics and automation (ICMRA)

作者： Fangqun Gao YunTao Wu Yanduo Zhang Tao Lu Pan Tang Liwei Wang Jifeng Han Wanghui Wu Hubei Key Laboratory of Intelligent Robot School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China Hubei University of Arts and Science Xiangyang China State Key Laboratory of Power Grid Environmental Protection China Electric Power Research Institute Wuhan China Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (数字)9798350352474

ISBN: (纸本)9798350352481

In various specialized operational scenarios, particularly those involving tool usage, the capacity to detect relationships between entities is crucial for understanding complex interactions. Traditional methods, which typically focus on unary or binary relationship detections, often fall short in capturing the subtleties present in such environments. this paper introduces the HTOI (Human Tool Object Interaction) model, a novel and pioneering approach to trinary relationship detection that addresses these limitations. the HTOI model has been designed to excel in complex interaction scenarios, including those characterized by the use of tools, as evidenced by its exceptional performance on our TData dataset. this dataset specifically highlights the nuanced actions of electric utility workers during tool-assisted operations, underscoring the model’s ability to detect intricate interactions with higher accuracy and reliability compared to existing HOI (Human Object Interaction) techniques. Our study aims to showcase the HTOI model’s significant advancement in the field of relationship detection, offering a valuable tool for analyzing and interpreting complex operational interactions involving tools.

关键词： Analytical models Mechatronics Accuracy Power industry Reliability robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Multi-Process Machining Errors of Frame Parts Based on State Space

Analysis of Multi-Process Machining Errors of Frame Parts Ba...

引用

Industrial automation, robotics and Control Engineering (IARCE), international conference on

作者： Haicheng Zhang Yali Ma Qi Zhang Zhi Wang School of Mechanical Engineering Dalian University of Technology State Key Laboratory of High-performance Precision Manufacturing Dalian China

ISBN: (数字)9798350380323

ISBN: (纸本)9798350380330

the critical processing characteristics of components are key in ensuring product accuracy and quality consistency. this paper focuses on the key machining characteristics of frame parts and develops a multi-process machining error prediction model based on the state space theory to anticipate machining errors. Firstly, the error sources such as reference error, fixture error, and machine tool geometric error during the multi-process processing of frame parts are described using the homogeneous coordinate transformation theory, multi-body system theory, and error transformation theory. Secondly, a multi-dimensional model is constructed using the above error sources to predict the machining error process. Lastly, the sensitivity analysis of the multi-process machining error prediction model is performed using partial derivatives to study the contribution of each error source to the multi-process machining error prediction model during the processing of frame parts. the model's effectiveness is verified by taking the machining process of the external surface key machining feature of frame parts as an example, and the contribution of each error source to the errors of the key machining feature of frame parts is further explained.

关键词： Analytical models Accuracy Fixtures Machining Predictive models Aerospace electronics Stability analysis Machine tools State-space methods Surface treatment

来源：评论

学校读者我要写书评

暂无评论

Equipment Health Monitoring for Industrial Robotic Arms

Equipment Health Monitoring for Industrial Robotic Arms

引用

IEEE international conference on automation Science and Engineering (CASE)

作者： James Moore Daniela Sawyer Advanced Manufacturing Research Centre’s Integrated Manufacturing Group University of Sheffield Sheffield UK

ISBN: (数字)9798350358513

ISBN: (纸本)9798350358520

the topic of equipment health monitoring (EHM) for robotics, including condition monitoring (CM), process monitoring (PM) and predictive maintenance (PdM) is of great interest within the literature, however, there is a significant lack of historical datasets for techniques to be tested upon. Commercial offerings in this area are often manufacturer specific, meaning that fleets that include robots from multiple suppliers cannot easily have performance/condition compared across the fleet. To address this, the work presented within this paper includes an accelerated wear test (AWT) conducted on an industrial robotic arm whilst being monitored using a suite of retrofitted sensors. the resulting data from the AWT is then analysed through a variety of techniques, including regression models, classification models, and a long short-term memory (LSTM) autoencoder, to demonstrate the potential for such methods to be utilised for robot ***, the associated dataset captured during the AWT is to be made openly available through the University of Sheffield’s online research data repository, ORDA, to allow further research to be conducted.

关键词： Adaptation models Accuracy Service robots Predictive models Robot sensing systems Manipulators Data models Maintenance Robots Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Solution for Agri Disaster Using Climate Changes Adaptation by Ml 6

Solution for Agri Disaster Using Climate Changes Adaptation ...

引用

6th international conference on Contemporary Computing and Informatics, IC3I 2023

作者： Ganesh, L. Venkatesh, R. Prasanna Kumar, Kaushal Kumari, Khushboo Borkakoty, Sangeeta Raju, A. Rajalakshmi Engineering College Robotics and Automation Dept. Tamilnadu Chennai India SACS MAVMM Engineering College Department of Mechanical Engineering Tamilnadu Madurai India School of Life Sciences Department of Botany Mahatma Gandhi Central University Bihar India University of Science & Technology Department of Computer Science & Electronic Meghalaya India KLEF Vaddeswaram Green Field Department of Commerce Vijayawada India

ISBN: (纸本)9798350304480

this paper proposes using good sized getting to know fashions to recognize lesions of cotton leaves in the context of pictures of the reaping within the subject. Cotton is among the maximum economically essential plant harvests, as it's far grown all over the international. Its spread in tropical areas has made it the goal of a wide variety of farming irritations and illnesses, necessitating succesful plans. moreover, the consequences of commonplace disturbances and disorders are difficult to isolate inside the early stages, and the author may additionally battle to locate the suitable visible verification of a scientific difficulty. To help in resolving the difficulty, it contemporary inquiry proposes a solution that takes into consideration substantial training within the filtering of cotton leaves, making it possible to reveal the cotton yield's health and make higher judgments approximately its management. the studying models GoogleNet like Resnet50, which use convolutional cerebrum associations, performed an accuracy of 86.6 percentage and 89.2 percentage, respectively. assist vector machines, Closest k-pals, faux creativeness associations, and neuro-tender are some of the extraordinary as well as everyday tactics again for treatment of photographs. the convolutional cerebellum networks ended up being 25% extra unique, implying that this method can upload to a more strong and short investigation of the flora looking to fill inside the field. © 2023 IEEE.

关键词： Artificial Intelligence Convolutional Neural Networks Image Processing Precision Agriculture

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：