检索结果-内蒙古大学图书馆

IEEE OPEN JOURNAL OF THE INDUSTRIAL ELECTRONICS SOCIETY 2021年 2卷 128-141页

作者： Profanter, Stefan Perzylo, Alexander Rickert, Markus Knoll, Alois Tech Univ Munich Chair Robot Artificial Intelligence & Real Time S Dept Informat D-80333 Munich Bayern Germany

Typical industrial workcells are composed of a plenitude of devices from various manufacturers, which rely on their own specific control interfaces. To reduce setup and reconfiguration times, a hardware-agnostic Plug & Produce system is required. In this paper, we present a system architecture that uses generic and semantically augmented OPC UA skills for robots, tools, and other system components. Standardized skill interfaces and parameters facilitate flexible component interchange and automatic parametrization with a focus on reusability of skills across different platforms and domains. The hierarchical composition of such skills allows for additional abstraction through the grouping of functionalities. Through the extension of OPC UA discovery services, available skills are dynamically detected whenever a manufacturing system's component is updated. The introduced Plug & Produce system is evaluated in multiple industrial workcells composed of robots, tool changer, electric parallel gripper, and vacuum gripper-all controlled via the proposed OPC UA skill interface. The evaluation of our system architecture demonstrates the applicability of the Plug & Produce concept in the domain of robot-based industrial assembly. Although it is necessary to adapt existing hardware to comply with the semantic skill concept, the initial one-time effort yields reoccurring efficiency gains during system reconfiguration. In particular, small lot production benefits from reduced changeover times.

关键词： Plugs Robots Semantics Middleware Hardware Service robots Systems architecture Flexible manufacturing systems manufacturing automation middleware plug & produce robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Analysis of Motor Imagery-Based fNIRS-BCI for Knee Flexion and Extension

Analysis of Motor Imagery-Based fNIRS-BCI for Knee Flexion a...

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Hamza Shabbir Minhas Hammad Nazeer Noman Naseer Iraj Kainat Haroon Khan Peyman Mirtaheri Department of Mechatronics and Biomedical Engineering Air University Islamabad Pakistan Department of Mechanical Electronic and Chemical Engineering OsloMet - Oslo Metropolitan University Oslo Norway

ISBN: (数字)9798350355703

ISBN: (纸本)9798350355710

This study aimed to explore the potential of functional near-infrared spectroscopy (fNIRS) as a non-invasive technique for detecting hemodynamic responses in cortical brain activities during motor imagery (MI) tasks. Specifically, the study focused on classifying multiclass MI tasks with fNIRS data. A total of 10 healthy individuals participated in the experiment, where they were instructed to perform motor imagery tasks. A multi-channel continuous wave fNIRS system records the signals from the motor cortex for knee flexion and extension imagery tasks. Discriminant Analysis (LDA) and Support Vector Machine (SVM), comparatively computationally efficient, algorithms were used to classify the data for fNIRS-based BCI applications. The SVM classifier performed comparatively better than the LDA classifier in accuracy, with 88.8% and 89.4% for two-feature and three-feature combinations. Brain activation maps show the increased activation for flexion movement of the knee. Future research should focus on refining the classification process through feature selection, preprocessing improvements, and ensemble methods to enhance accuracy.

关键词： Support vector machines Industries Limbs Accuracy Neuromuscular Refining Motors Hemodynamics Functional near-infrared spectroscopy robotics and automation

来源：评论

学校读者我要写书评

暂无评论

Enhancing Path Planning Algorithms with CubicSearch: A Novel Structured Approach for Propagation and Obstacle Avoidance

Enhancing Path Planning Algorithms with CubicSearch: A Novel...

引用

International Workshop on Research and Education in Mechatronics (REM)

作者： Ali F Yousef Essa Alghannam Hasan E Alwara Amin F Haydar Ali Ghanem Mechatronic Engineering Dept. Robotics Club Tishreen University Latakia Syria System Engineering Dept. University of Applied Sciences Ruhr West Mulheim Germany

ISBN: (数字)9798331505974

ISBN: (纸本)9798331505981

Many path planning algorithms rely on generating random points that share specific attributes with the target, such as proximity. This approach can render algorithms ineffective in complex environments and increase execution time. Therefore, enhancing algorithms with classical logic and improving their speed is a promising avenue of research. CubicSearch is a new method that employs an organized and efficient way for propagation and obstacle avoidance, with minimized memory and time complexity to O(n/C), where $C$ is the accuracy. It integrates other algorithms, such as BFS (Breadth-First Search) for tree propagation, and Boolean array for obstacle checking and verifying visited points with a high level of memory management. Additionally, it allows for adjustable accuracy in propagation, which can control execution time. These features contribute to the method's effectiveness, producing near-optimal paths that can be refined to become fully optimal. Unlike random algorithms, CubicSearch reliably finds a path even when only one path exists between numerous obstacles. The results show that the CubicSearch algorithm effectively manages highly complex 3D environments space) with multiple obstacles (greater than 100,000), generating the shortest paths for large data inputs in under one second. For 2D environments, it provides real-time path finding, resolving any path in milliseconds.

关键词： Three-dimensional displays Accuracy Memory management Sampling methods Path planning Real-time systems Collision avoidance Time complexity robotics and automation Optimization

来源：评论

学校读者我要写书评

暂无评论

Control Allocation of X-form Rudder Based on Neural Networks

Control Allocation of X-form Rudder Based on Neural Networks

引用

IEEE International Conference on Mechatronics, robotics and automation (ICMRA)

作者： Yueming Qin Wubo Pei Xing Shao Yang Xu Yichang Testing Technique Research Institute Yichang China

ISBN: (数字)9798350352474

ISBN: (纸本)9798350352481

At present, there are mainly two common frameworks for implementing the control allocation of X-form rudder: namely the pseudo-inverse framework and the optimization based framework. In order to obtain better allocation performance than the former and lower computational complexity than the latter at the same time, this paper proposes a new framework, namely the neural networks framework, for control allocation of X-form rudder. In this paper, neural networks are applied to fit the mapping from desired moments (roll moment, pitch moment and yaw moment) to the proper rudder angles. The experimental results show that the proposed method is effective and can fulfill the task of control allocation.

关键词： Mechatronics Neural networks Resource management robotics and automation Computational complexity Optimization

来源：评论

学校读者我要写书评

暂无评论

QuadricsNet: Learning Concise Representation for Geometric Primitives in Point Clouds

QuadricsNet: Learning Concise Representation for Geometric P...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Ji Wu Huai Yu Wen Yang Gui-Song Xia School of Computer Science Wuhan University Wuhan China School of Electronic Information Wuhan University Wuhan China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

This paper presents a novel framework to learn a concise geometric primitive representation for 3D point clouds. Different from representing each type of primitive individually, we focus on the challenging problem of how to achieve a concise and uniform representation robustly. We employ quadrics to represent diverse primitives with only 10 parameters and propose the first end-to-end learning-based framework, namely QuadricsNet, to parse quadrics in point clouds. The relationships between quadrics mathematical formulation and geometric attributes, including the type, scale and pose, are insightfully integrated for effective supervision of QuaidricsNet. Besides, a novel pattern-comprehensive dataset with quadrics segments and objects is collected for training and evaluation. Experiments demonstrate the effectiveness of our concise representation and the robustness of QuadricsNet. Our code is available at https://***/MichaelWu99-lab/QuadricsNet.

关键词： Point cloud compression Training Three-dimensional displays Codes Robustness robotics and automation

来源：评论

学校读者我要写书评

暂无评论

MORPH: Design Co-optimization with Reinforcement Learning via a Differentiable Hardware Model Proxy

MORPH: Design Co-optimization with Reinforcement Learning vi...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： Zhanpeng He Matei Ciocarlie Department of Computer Science Columbia University New York USA Department of Mechanical Engineering Columbia University New York USA

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

We introduce MORPH, a method for co-optimization of hardware design parameters and control policies in simulation using reinforcement learning. Like most co-optimization methods, MORPH relies on a model of the hardware being optimized, usually simulated based on the laws of physics. However, such a model is often difficult to integrate into an effective optimization routine. To address this, we introduce a proxy hardware model, which is always differentiable and enables efficient co-optimization alongside a long-horizon control policy using RL. MORPH is designed to ensure that the optimized hardware proxy remains as close as possible to its realistic counterpart, while still enabling task completion. We demonstrate our approach on simulated 2D reaching and 3D multi-fingered manipulation tasks.

关键词： Three-dimensional displays Reinforcement learning Hardware Task analysis robotics and automation Physics Optimization

来源：评论

学校读者我要写书评

暂无评论

FIPFuse: Visible and Infrared Image Fusion Based on Frequency Information Perception

FIPFuse: Visible and Infrared Image Fusion Based on Frequenc...

引用

IEEE International Conference on Mechatronics, robotics and automation (ICMRA)

作者： Shaokang Jiao Yanan Li Huabing Zhou School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China The Key Laboratory for Crop Production and Smart Agriculture of Yunan Province Kunming China Hubei Key Laboratory of Intelligent Robot Wuhan China

ISBN: (数字)9798350352474

ISBN: (纸本)9798350352481

The fusion of visible and infrared images aims to generate fused images that has the advantages of both modalities. Traditional methods typically rely on manually designed strategies for feature extraction and fusion, resulting in increased computational complexity. The existing deep learning methods ignore the utilization of the frequency information of the source images. These methods are typically unsupervised and constrained by loss functions during the training. However, the limitations of previous loss functions have led to training that focuses excessively on the local information region of the source images, ignoring important global information. In order to solve the above problems, this paper proposes a visible and infrared image fusion method based on frequency information perception designed as FIPFuse. The frequency information perception module in FIPFuse is utilized in both the image reconstruction and image fusion stages, effectively extracting high-frequency and low-frequency information from the source images. A random structure similarity loss was proposed to train the model, with the objective of guiding the network to sufficiently focus on the source image information, thereby effectively fusing the source images. Extensive experiments on public datasets have demonstrated that FIPFuse outperforms other representative methods in both qualitative and quantitative assessments.

关键词： Training Deep learning Mechatronics Feature extraction Data mining robotics and automation Computational complexity Image fusion Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

LSTM-based modeling of the Tangnaihai and Fen River basins Rainfall Runoff Simulation

LSTM-based modeling of the Tangnaihai and Fen River basins R...

引用

Advanced Information, Mechanical Engineering, robotics and automation (AIMERA), IEEE International Conference on

作者： Zhengfang Jiang Baohong Lu Zunguang Zhou Yirui Zhao College of Hydrology and Water Resources Hohai University Nanjing China

ISBN: (数字)9798350343335

ISBN: (纸本)9798350343342

In this study, the Tangnaihai basin, characterized by weak human activities at the source of the Yellow River, and the Fenhe River basin, marked by significant human activities in the middle reaches of the Yellow River, were chosen as research subjects. Rainfall and runoff simulations with forecasting foresight periods of 1-3 days were conducted using LSTM and BPNN models. Despite declining simulation accuracy with longer forecast periods, LSTM consistently outperforms BPNN. Notably, the LSTM model effectively captures the hydrological nuances of different watershed types, although the precise internal hidden layer structure and historical information inputs remain ambiguous. The study reveals that watersheds experiencing strong human disturbances necessitate a complex hidden layer structure for accurate rainfall and runoff simulation. Furthermore, it is observed that the model’s dependence on historical information diminishes with the extension of the forecast period, highlighting the evolving relationship between historical data and forecasting accuracy.

关键词： Analytical models Accuracy Rain Watersheds Predictive models Rivers Solar radiation Forecasting robotics and automation Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Design and Test of Power Chassis for Small Tracked Sand Barrier Placing Vehicle

Design and Test of Power Chassis for Small Tracked Sand Barr...

引用

Advanced Information, Mechanical Engineering, robotics and automation (AIMERA), IEEE International Conference on

作者： Weiqiang Zheng Zehui Wang Liping Zhang Jianqiao Long Chang Liu Feiyang Xing School of Mechanical Engineering Xinjiang University Urumqi China School of Computing Newcastle University UK

ISBN: (数字)9798350343335

ISBN: (纸本)9798350343342

Aiming at the problems of low efficiency of the existing sand barriers burying machinery, large quality of the whole machine, inconvenient operation of large-scale machinery, and difficult to adapt to the complex terrain environment in the desert area, a self-propelled small and flexible power chassis has been developed, which mainly consists of the frame, the power system, the traveling system, and the control system. According to the environment of sand barriers buried, put forward the design target performance requirements and the overall structure of the program; first of all, the walking system components for the calculation and selection, followed by the matching calculation of the drive motor and power battery and the control system hardware circuit design and software programming; finally, the power chassis for the field test. The test results show that the power chassis has good range and climbing ability, with a range of up to 12km, a maximum speed of 6.1km/h, the ability to cross 25° sandy slopes, and a wireless remote control distance of 100m, which is in line with the desert environment driving and sand barriers burying operational needs.

关键词： Wireless communication Legged locomotion Programming Control systems Motors Software Power systems robotics and automation Mechanical engineering Remote control

来源：评论

学校读者我要写书评

暂无评论

Analysis of Three-Body Pitching Motion of New Unmanned Boat Based on Genetic Algorithm

Analysis of Three-Body Pitching Motion of New Unmanned Boat ...

引用

Advanced Information, Mechanical Engineering, robotics and automation (AIMERA), IEEE International Conference on

作者： Di Zhang Guoming Li Ke Zhang Meng Li School of Mechanical and Electrical Engineering Weifang Engineering Vocational College Weifang China

ISBN: (数字)9798350343335

ISBN: (纸本)9798350343342

When the current rescue unmanned boat is sailing on the sea, the vertical shake on the boat is too large, which will lead to a great reduction in the sailing performance of rescue unmanned boats. This article uses the three-body boat modal water vertical shake attenuation experiments as the research object. The programming ideas based on systematic identification methods and genetic algorithms, and establish four vertical system identification mathematical models. Through experiments, the peak of the boat model increased, the peak of the vertical corner speed increased, and the time of the boat model reached a stable state increase. Secondly, the best fitting model pitch motion identification equation is obtained, which not only verifies the feasibility of the unmanned vehicle model, but also verifies the reliability of the adapted software. Finally, through the comparison of dual - boating models, the three-body boat models have a good reduction effect.

关键词： Adaptation models Systematics Boats Mathematical models Software System identification Software reliability robotics and automation Autonomous vehicles Genetic algorithms

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：