检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Berra, Andrea Sankaranarayanan, Viswa Narayanan Seisa, Achilleas Santi Mellet, Julien Gamage, Udayanga G.W.K.N. Satpute, Sumeet Gajanan Ruggiero, Fabio Lippiello, Vincenzo Tolu, Silvia Fumagalli, Matteo Nikolakopoulos, George Soto, Miguel Ángel Trujillo Heredia, Guillermo CATEC Advanced Center for Aerospace Technologies Seville Spain Robotics and AI Team Department of Computer Electrical and Space Engineering LuleåUniversity of Technology Luleå Sweden PRISMA Lab Department of Electrical Engineering and Information Technology University of Naples Federico II Naples Italy Automation and Control Group Department of Electrical Engineering and Photonics Technical University of Denmark Denmark Robotics Vision and Control Group School of Engineering University of Seville Seville Spain

The paper introduces a novel framework for safe and autonomous aerial physical interaction in industrial settings. It comprises two main components: a neural network-based target detection system enhanced with edge computing for reduced onboard computational load, and a control barrier function (CBF)-based controller for safe and precise maneuvering. The target detection system is trained on a dataset under challenging visual conditions and evaluated for accuracy across various unseen data with changing lighting conditions. Depth features are utilized for target pose estimation, with the entire detection framework offloaded into low-latency edge computing. The CBF-based controller enables the UAV to converge safely to the target for precise contact. Simulated evaluations of both the controller and target detection are presented, alongside an analysis of real-world detection performance. © 2024, CC BY.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Design of a Flexible Robot Arm for Safe Aerial Physical Interaction

arXiv

引用

arXiv 2024年

作者： Mellet, Julien Berra, Andrea Seisa, Achilleas Santi Sankaranarayanan, Viswa Gamage, Udayanga G.W.K.N. Soto, Miguel Ángel Trujillo Heredia, Guillermo Nikolakopoulos, George Lippiello, Vincenzo Ruggiero, Fabio PRISMA Lab Department of Electrical Engineering and Information Technology University of Naples Federico II Naples Italy CATEC Advanced Center for Aerospace Technologies Seville Spain Robotics and AI Team Department of Computer Electrical and Space Engineering LuleåUniversity of Technology Luleå Sweden Automation and Control Group Department of Electrical Engineering and Photonics Technical University of Denmark Denmark Robotics Vision and Control Group School of Engineering University of Seville Seville Spain

This paper introduces a novel compliant mechanism combining lightweight and energy dissipation for aerial physical interaction. Weighting 400 g at take-off, the mechanism is actuated in the forward body direction, enabling precise position control for force interaction and various other aerial manipulation tasks. The robotic arm, structured as a closed-loop kinematic chain, employs two deported servomotors. Each joint is actuated with a single tendon for active motion control in compression of the arm at the end-effector. Its elasto-mechanical design reduces weight and provides flexibility, allowing passive-compliant interactions without impacting the motors’ integrity. Notably, the arm’s damping can be adjusted based on the proposed inner frictional bulges. Experimental applications showcase the aerial system performance in both free-flight and physical interaction. The presented work may open safer applications for Micro Aerial Vehicle (MAV) in real environments subject to perturbations during interaction. © 2024, CC BY.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

AnyBipe: An End-to-End Framework for Training and Deploying Bipedal Robots Guided by Large Language Models

arXiv

引用

arXiv 2024年

作者： Yao, Yifei He, Wentao Gu, Chenyu Du, Jiaheng Tan, Fuwei Zhu, Zhen Lu, Junguo All authors are with Machine Vision and Autonomous System Laboratory Department of Automation School of Electrical Information and Electronic Engineering Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai Jiao Tong University Shanghai China

Training and deploying reinforcement learning (RL) policies for robots, especially in accomplishing specific tasks, presents substantial challenges. Recent advancements have explored diverse reward function designs, training techniques, simulation-to-reality (sim-to-real) transfers, and performance analysis methodologies, yet these still require significant human intervention. This paper introduces an end-to-end framework for training and deploying RL policies, guided by Large Language Models (LLMs), and evaluates its effectiveness on bipedal robots. The framework consists of three interconnected modules: an LLM-guided reward function design module, an RL training module leveraging prior work, and a sim-to-real homomorphic evaluation module. This design significantly reduces the need for human input by utilizing only essential simulation and deployment platforms, with the option to incorporate human-engineered strategies and historical data. We detail the construction of these modules, their advantages over traditional approaches, and demonstrate the framework’s capability to autonomously develop and refine controlling strategies for bipedal robot locomotion, showcasing its potential to operate independently of human intervention. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Assisted Physical Interaction: Autonomous Aerial Robots with Neural Network Detection, Navigation, and Safety Layers

Assisted Physical Interaction: Autonomous Aerial Robots with...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Andrea Berra Viswa Narayanan Sankaranarayanan Achilleas Santi Seisa Julien Mellet Udayanga G.W.K.N. Gamage Sumeet Gajanan Satpute Fabio Ruggiero Vincenzo Lippiello Silvia Tolu Matteo Fumagalli George Nikolakopoulos Miguel Ángel Trujillo Soto Guillermo Heredia CATEC Advanced Center for Aerospace Technologies Seville Spain Department of Computer Electrical and Space Engineering Robotics and AI Team Luleå University of Technology Luleå Sweden Department of Electrical Engineering and Information Technology PRISMA Lab University of Naples Federico II Naples Italy Department of Electrical Engineering and Photonics Automation and Control Group Technical University of Denmark Denmark Robotics Vision and Control Group School of Engineering University of Seville Seville Spain

ISBN: (数字)9798350357882

ISBN: (纸本)9798350357899

关键词： Visualization Pose estimation Neural networks Lighting Object detection Autonomous aerial vehicles Aircraft navigation

来源：评论

学校读者我要写书评

暂无评论

Part Mass Estimation Strategy for Injection Molding Machines

引用

IFAC-PapersOnLine 2020年第2期53卷 10366-10371页

作者： J. Maderthaner A. Kugi W. Kemmetmüller Automation and Control Institute TU Wien Vienna 1040 Austria Center for Vision Automation & Control Austrian Institute of Technology Vienna 1210 Austria

In injection molding, it is crucial to ensure high part quality over a long time period because typically these parts are produced in large numbers. Process variations influence the production and the resulting part quality. The part mass is frequently used as a quality measure as it can be easily measured by a scale after the part is finished. On the other hand, it is not possible to directly measure the part mass during the injection phase. This paper proposes a method to estimate the part mass by means of sensors, which are typically available in an injection molding machine. Compared to the state of the art, the proposed strategy also allows to estimate the time evolution of the part mass during the injection process. The accuracy of 0.25% and the robustness, with respect to process parameter variations, of the proposed part mass estimation is demonstrated by measurements.

关键词： injection molding part mass estimation process control part quality partial filling

来源：评论

学校读者我要写书评

暂无评论

Fast motion planning for a laboratory 3D gantry crane in the presence of obstacles

引用

IFAC-PapersOnLine 2020年第2期53卷 9508-9514页

作者： M.N. Vu P. Zips A. Lobe F. Beck W. Kemmetmüller A. Kugi Automation and Control Institute (ACIN) TU Wien Vienna Austria Center for Vision Automation & Control AIT Austrian Institute of Technology Vienna Austria

In this paper, a concept is presented for the fast motion planning of a 3D laboratory crane in a static environment with obstacles taking into account the dynamic constraints on the state variables and control inputs. The focus is set on the possibility of a fast (re)planning if the starting and/or target state is changing. The proposed concept consists of two parts: an offline trajectory planner to set up a database of collision-free, time optimal trajectories from the starting to the target space, with an average computing time of 0.17 s for one trajectory, and an online planner based on a constrained quadratic program, with an average computing time of 7 ms for one trajectory. Simulation results for a validated mathematical model demonstrate the feasibility of the proposed approach.

关键词： fast optimal trajectory planning online re-planning direct collocation method constrained quadratic optimization collision avoidance 3D gantry crane

来源：评论

学校读者我要写书评

暂无评论

On the global feedback stabilization of regenerative optical amplifiers

引用

IFAC-PapersOnLine 2020年第2期53卷 5447-5452页

作者： A. Deutschmann W. Kemmetmüller A. Kugi Automation and Control Institute Complex Dynamical Systems Group TU Wien Vienna Austria Center for Vision Automation & Control Austrian Institute of Technology Vienna Austria

The generation of high-energy laser pulses by so-called regenerative (optical) amplifiers is limited by the occurrence of period-doubling bifurcations induced by an inherently unstable pulse-to-pulse dynamics. Recently, the application of linear feedback methods to stabilize this pulse-to-pulse dynamics by modifying the supplied seed pulses was suggested as an alternative to the quite expensive current state of the art involving dedicated pre-amplifiers. To address some shortcomings inherent to the linear feedback, this paper investigates the design of nonlinear state feedback laws and in particular the possibility to stabilize the pulse-to-pulse dynamics globally subject to the given input constraints.

关键词： Regenerative amplifiers pulsed laser systems global asymptotic stability constrained nonlinear control

来源：评论

学校读者我要写书评

暂无评论

Method of Electronic Component Location, Grasping and Inserting Based on Machine vision 16

Method of Electronic Component Location, Grasping and Insert...

引用

16th IEEE International Wireless Communications and Mobile Computing Conference, IWCMC 2020

作者： Xue, Bin Sun, Chang Chu, Huihui Meng, Qingsen Jiao, Shuanben Engineering and Technology Rd Center of Mechanical and Electrical in Colleges of Shandong Qingdao Binhai University Shandong China Qingdao Zhongzhuang Vision Automation System Control Co. Ltd Shandong China

ISBN: (纸本)9781728131290

Aiming at the problems of low efficiency, high cost, missing or wrong insertion of labor in PCB production, a method of electronic component location, grabbing and inserting based on machine vision is proposed. By building the machine vision system, three industrial cameras cooperate with dome light sources to take images of the whole components, the pin features of components and the jack features of PCB board respectively. After image acquisition, image processing is carried out on visionPro 9.0 software platform, which mainly completes feature extraction of component pins and PCB board jacks, and coordinates positioning. Then, coordinate transformation is carried out by nine-point calibration method to guide the manipulator to complete the work of location, grabbing and inserting. Through the running test, the system has a fast grabbing speed and inserting speed. The error inserting rate, missing inserting rate, bad product rate and inserting precision all reach the standard, and the working efficiency is three times that of the manual. © 2020 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Temperature control for Induction Heating of Thin Strips ⁎ ⁎⁎

引用

IFAC-PapersOnLine 2020年第2期53卷 11968-11973页

作者： F. Roetzer A. Aschauer L. Jadachowski A. Steinboeck A. Kugi Automation and Control Institute TU Wien Vienna Austria Christian Doppler Laboratory for Model-Based Process Control in the Steel Industry Automation and Control Institute TU Wien Vienna Austria Center for Vision Automation & Control Austrian Institute of Technology Vienna Austria

In this work, a model-based temperature controller for an induction heating system for moving thin metal strips is developed. The most significant disturbance of the system is an uncertain air gap geometry caused by flatness defects of the metal strip. A computationally expensive calculation of the electromagnetic field is avoided by using an equivalent circuit model and the energy balance. A thermal model of the moving strip is derived in the form of a convection-reaction equation and simplified to a linear time-invariant model. A 2-degrees-of-freedom controller is designed based on the simplified model and tested using a finite-element simulation model of the induction heating system. The simulations demonstrate that the proposed controller clearly outperforms standard feedback control strategies.

关键词： Induction heating metals industry temperature control 2-degrees-of-freedom control

来源：评论

学校读者我要写书评

暂无评论

Visual Module R&D of the Intelligent Grabbing System of WIFI Module

Visual Module R&D of the Intelligent Grabbing System of WIFI...

引用

International Conference on Application of Intelligent Systems in Multi-modal Information Analytics, MMIA 2020

作者： Ma, Shufang Wu, Jiang Jiao, Shuangben Xue, Bin Engineering and Technology R&D Center of Mechanical and Electrical in Colleges of Shandong Qingdao Binhai University QingdaoShandong266555 China School of Mechanical and Electrical Engineering Qingdao Binhai University QingdaoShandong266555 China Qingdao Zhongzhuang Vision Automation System Control Co. Ltd. QingdaoShandong266555 China

ISBN: (纸本)9783030514303

WiFi module intelligent grabbing system based on visual guidance is established by taking MV-CH120-10GM industrial camera and Siemens S7-200smartPLC as the hardware basis designated to realize identification and positioning grabbing of WiFi module. Hardware selection and imaging processing is studied based on visual module, and visual identity and positioning algorithm is developed by taking visionPro9.0 as the platform. Meanwhile, logical judgment on imaging processing result is carried out by using the software vision Studio C#. Besides, visual windows is used for inspecting image and data display. Through experimental verification, it is ultimately indicated that the visual algorithm features higher identification and positioning accuracy and satisfies the requirements of the grabbing system. © 2021, Springer Nature Switzerland AG.

关键词： Computer vision

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：