检索结果-内蒙古大学图书馆

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Kousheek Chakraborty Thijs Hof Ayham Alharbat Abeje Mersha Smart Mechatronics and Robotics research group Saxion University of Applied Science Enschede The Netherlands Robotics and Mechatronics research group Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede The Netherlands

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

This paper proposes a Reinforcement Learning (RL)-based control framework for position and attitude control of an Unmanned Aerial System (UAS) subjected to significant disturbance that can be associated with an uncertain trigger signal. The proposed method learns the relationship between the trigger signal and disturbance force, enabling the system to anticipate and counteract the impending disturbances before they occur. We train and evaluate three policies: a baseline policy trained without exposure to the disturbance, a reactive policy trained with the disturbance but without the trigger signal, and a predictive policy that incorporates the trigger signal as an observation and is exposed to the disturbance during training. Our simulation results show that the predictive policy outperforms the other policies by minimizing position deviations through a proactive correction maneuver. This work highlights the potential of integrating predictive cues into RL frameworks to improve UAS performance.

关键词： Training Attitude control Simulation Force Reinforcement learning Autonomous aerial vehicles Stability analysis Maintenance Dynamical systems Logistics

来源：评论

学校读者我要写书评

暂无评论

RL-based Control of UAS Subject to Significant Disturbance

arXiv

引用

arXiv 2025年

作者： Chakraborty, Kousheek Hof, Thijs Alharbat, Ayham Mersha, Abeje Smart Mechatronics and Robotics Research Group Saxion University of Applied Science Enschede Netherlands Robotics and Mechatronics Research Group Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede Netherlands

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Sarax: An Open-Source Software/Hardware Framework for Aerial Manipulators

Sarax: An Open-Source Software/Hardware Framework for Aerial...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Ayham Alharbat Dion Zwakenberg Hanieh Esmaeeli Abeje Mersha Smart Mechatronics and Robotics research group Saxion University of Applied Science Enschede The Netherlands Robotics and Mechatronics research group Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede The Netherlands

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

The use of Multi-Rotor Aerial Vehicles (MRAVs) in tasks that require physical interaction has been an active research field in the last decade which resulted in an increasing interest in Aerial Manipulators (AMs). This raises many challenges in the modeling, control, perception, and planning of these robots. However, designing and realizing an AM testbed is a complicated multi-disciplinary task, and there is a lack of standardization in the relatively new field of AMs. For this purpose, we introduce Sarax, an open-source hardware and software framework tailored for AMs research and innovation. The software of Sarax is built on top of open-source projects such as the Robot Operating System (ROS) and PX4 Autopilot, while the hardware is designed to be customizable, modular, and easily scalable through parameterized models. We verified and validated the proposed framework through indoor and outdoor experiments. We aim to open the door to accelerate AMs research and innovation, allow researchers and developers to focus on their core contributions, and take AMs technology to a higher readiness level.

关键词： Technological innovation Operating systems Standardization Manipulators Software Planning Open source hardware

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Ensemble-Based Long Short-Term Memory Approach for Traffic Volume Prediction

引用

Computers, Materials & Continua 2024年第3期78卷 3585-3602页

作者： Duy Quang Tran Huy Q.Tran Minh Van Nguyen Faculty of Civil Engineering Nha Trang UniversityNha Trang650000Vietnam Robotics and Mechatronics Research Group Faculty of Engineering and TechnologyNguyen Tat Thanh UniversityHo Chi Minh City700000Vietnam Department of Civil Engineering Ho Chi Minh City University of Technology and EducationHo Chi Minh City700000Vietnam

With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service *** volume is an influential parameter for planning and operating traffic *** study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning *** fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal ***,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition *** second aspect involves predicting traffic volume using the long short-term memory ***,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent ***,the fusion of the obtained results leads to a final traffic volume *** experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and *** achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the *** findings highlight the accuracy of traffic pattern ***,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.

关键词： Ensemble empirical mode decomposition traffic volume prediction long short-term memory optimal hyperparameters deep learning

来源：评论

学校读者我要写书评

暂无评论

Motion Control of a Mini-Quadcopter Using a Fuzzy-PD Controller 12

Motion Control of a Mini-Quadcopter Using a Fuzzy-PD Control...

引用

12th RSI International Conference on robotics and mechatronics, ICRoM 2024

作者： Talaeizadeh, Amin Alaeizadeh, Hadi Najafi, Esmaeil School of Mechanical Engineering Sharif University of Technology Tehran Iran School of Mechanical Engineering K.N. Toosi University of Technology Tehran Iran Smart Mechatronics and Robotics Research Group Saxion University of Applied Science Netherlands

ISBN: (纸本)9798331529734

Drones have been used extensively in the last decade, and there are estimates that this trend will continue in the coming decades. Having a sophisticated motion control algorithm is one of the important keys when we invite drones into our daily life. This paper develops a Fuzzy-PD controller for a Parrot mini-quad copter to follow various specific paths while keeping its stability. A nonlinear six Degrees of Freedom (DOF) model of the mini-quadcopter is considered to simulate different maneuvers in the Matlab/Simulink software. The proposed Fuzzy-PD controller has been investigated with respect to a conventional PD controller through two different trajectories. The virtual reality results validate the proper performance of the designed motion controller compared with the outcome of the conventional PD controller. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study on the Failure Detection Methods Using Time-Series Data Image Generation and CNN for Driving Module of Cobots 9

A Comparative Study on the Failure Detection Methods Using T...

引用

9th International Conference on Control, Decision and Information Technologies, CoDIT 2023

作者： Choi, Seung-Hwan Park, Jun-Kyu An, Dawn Kim, Chang-Hyun Park, Gunseok Park, Jongbum Kim, Tae-Keun Jung, Byungjin Lee, Suwoong Korea Institute of Industrial Technology Advanced Mechatronics R&d Group Korea Republic of Korea Electric Power Research Institute Renewable Energy Solution Group Korea Republic of Korea Electronics Technology Institute Intelligent Robotics Research Center Korea Republic of

ISBN: (纸本)9798350311402

The objective of this study was to propose the method to detect failure in the driving module of collaborative robots (cobots). We used three image generation algorithms and four convolutional neural network (CNN) models to detect failures and compared the performance of the models using the time-series vibration data acquired from the durability test of the driving module for cobots. We used recurrence plot, Gramian angular field, and spectrogram as image generation models and applied AlexNet, GoogleNet, ResNet, and DenseNet as CNN models. We generated images from time-series data, and using the images as input, we applied CNN models to detect failures. Subsequently, the detection accuracy for each image generation and CNN model was calculated and compared. The results of this study indicate that the spectrogram and ResNet models are relatively superior image generation and detection methods, respectively, compared to other methods. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Stereo Vision Based Robot for Remote Monitoring with VR Support

arXiv

引用

arXiv 2024年

作者： Fazil, M.S. Mohamed Selvakumar, A. Arockia Schilberg, Daniel Design and Automation Research Group SMBS Vellore Institute of Technology Chennai India Mechatronics and Research Head of Institute of Robotics Mechatronics University of Applied Sciences Bochum Germany Mechatronics and Robotics Tandon School of Engineering New York University United States

The machine vision systems have been playing a significant role in visual monitoring systems. With the help of stereovision and machine learning, it will be able to mimic human-like visual system and behaviour towards the environment. In this paper, we present a stereo vision based 3-DOF robot which will be used to monitor places from remote using cloud server and internet devices. The 3-DOF robot will transmit human-like head movements, i.e., yaw, pitch, roll and produce 3D stereoscopic video and stream it in Real-time. This video stream is sent to the user through any generic internet devices with VR box support, i.e., smartphones giving the user a First-person real-time 3D experience and transfers the head motion of the user to the robot also in Real-time. The robot will also be able to track moving objects and faces as a target using deep neural networks which enables it to be a standalone monitoring robot. The user will be able to choose specific subjects to monitor in a space. The stereovision enables us to track the depth information of different objects detected and will be used to track human interest objects with its distances and sent to the cloud. A full working prototype is developed which showcases the capabilities of a monitoring system based on stereo vision, robotics, and machine learning. © 2024, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

External-Wrench Estimation for Aerial Robots Exploiting a Learned Model

External-Wrench Estimation for Aerial Robots Exploiting a Le...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Ayham Alharbat Gabriele Ruscelli Roberto Diversi Abeje Mersha Smart Mechatronics and Robotics research group Saxion University of Applied Science Enschede The Netherlands Robotics and Mechatronics research group Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede The Netherlands Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

ISBN: (数字)9798331513283

ISBN: (纸本)9798331513290

This paper presents an external wrench estimator that uses a hybrid dynamics model consisting of a firstprinciples model and a neural network. This framework addresses one of the limitations of the state-of-the-art modelbased wrench observers: the wrench estimation of these observers comprises the external wrench (e.g. collision, physical interaction, wind); in addition to residual wrench (e.g. model parameters uncertainty or unmodeled dynamics). This is a problem if these wrench estimations are to be used as wrench feedback to a force controller, for example. In the proposed framework, a neural network is combined with a first-principles model to estimate the residual dynamics arising from unmodeled dynamics and parameters uncertainties, then, the hybrid trained model is used to estimate the external wrench, leading to a wrench estimation that has smaller contributions from the residual dynamics, and affected more by the external wrench. This method is validated with numerical simulations of an aerial robot in different flying scenarios and different types of residual dynamics, and the statistical analysis of the results shows that the wrench estimation error has improved significantly compared to a model-based wrench observer using only a firstprinciples model.

关键词： Uncertain systems Analytical models Statistical analysis Atmospheric modeling Dynamics Neural networks Observers Autonomous aerial vehicles Numerical simulation Numerical models

来源：评论

学校读者我要写书评

暂无评论

External-Wrench Estimation for Aerial Robots Exploiting a Learned Model

arXiv

引用

arXiv 2025年

作者： Alharbat, Ayham Ruscelli, Gabriele Diversi, Roberto Mersha, Abeje Smart Mechatronics and Robotics research group Saxion University of Applied Science Enschede Netherlands Robotics and Mechatronics research group Faculty of Electrical Engineering Mathematics & Computer Science University of Twente Enschede Netherlands Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

This paper presents an external wrench estimator that uses a hybrid dynamics model consisting of a first-principles model and a neural network. This framework addresses one of the limitations of the state-of-the-art model-based wrench observers: the wrench estimation of these observers comprises the external wrench (e.g. collision, physical interaction, wind);in addition to residual wrench (e.g. model parameters uncertainty or unmodeled dynamics). This is a problem if these wrench estimations are to be used as wrench feedback to a force controller, for example. In the proposed framework, a neural network is combined with a first-principles model to estimate the residual dynamics arising from unmodeled dynamics and parameters uncertainties, then, the hybrid trained model is used to estimate the external wrench, leading to a wrench estimation that has smaller contributions from the residual dynamics, and affected more by the external wrench. This method is validated with numerical simulations of an aerial robot in different flying scenarios and different types of residual dynamics, and the statistical analysis of the results shows that the wrench estimation error has improved significantly compared to a model-based wrench observer using only a first-principles model. © 2025, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conceptual Mechatronic Design of Robotic System for Lower Limb Rehabilitation in Post-Stroke Patients using the VDI 2206 and VDI 2225 Standard

Conceptual Mechatronic Design of Robotic System for Lower Li...

引用

IEEE Students' Conference on Electrical, Electronics and Computer Science (SCEECS)

作者： Carol Sandoval Cesar Martel Jose Cornejo Adrian Nacarino Margarita Murillo Manrique Ricardo Palomares Research Group of Advanced Robotics and Mechatronics (GI-ROMA) Ricardo Palma University Lima Peru Institute of Research in Biomedical Sciences (INICIB) Lima Peru

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529840

This study aims to design a robotic system for continuous passive motion therapy to support lower limb rehabilitation in post-stroke patients. The design process adheres to VDI 2206 and VDI 2225 standards. Key stages include defining requirements based on anthropometric and biomechanical data, function structuring, and using a morphological matrix to explore solutions. Weighted matrices evaluated ergonomics, control precision, and safety, leading to an optimal design for knee and ankle rehabilitation. The system provides controlled, passive movement, supports up to 80 kg, and allows adjustable speed and load resistance, ensuring smooth actuation and biomechanical alignment for effective motor recovery. A Von Mises analysis of the rail-structure connector, using 304 stainless steel under a 784 N vertical load (simulating patient weight), revealed a maximum stress of 29.58 MPa and deformation of 1.12×10 -4 , remaining within the material's elastic limit.

关键词： Biomechanics mechatronics Wheelchairs Medical treatment Stroke (medical condition) Motors Standards Robots Stress Testing

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：