检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Salfity, Jonathan Wanna, Selma Choi, Minkyu Pryor, Mitch Nuclear and Applied Robotics Group Department of Mechanical Engineering SWARM Lab Department of Electrical and Computer Engineering The University of Texas at Austin United States

Recent works in Task and Motion Planning (TAMP) show that training control policies on language-supervised robot trajectories with quality labeled data markedly improves agent task success rates. However, the scarcity of such data presents a significant hurdle to extending these methods to general use cases. To address this concern, we present an automated framework to decompose trajectory data into temporally bounded and natural language-based descriptive subtasks by leveraging recent prompting strategies for Foundation Models (FMs) including both Large Language Models (LLMs) and Vision Language Models (VLMs). Our framework provides both time-based and language-based descriptions for lower-level sub-tasks that comprise full trajectories. To rigorously evaluate the quality of our automatic labeling framework, we contribute an algorithm SIMILARITY to produce two novel metrics, temporal similarity and semantic similarity. The metrics measure the temporal alignment and semantic fidelity of language descriptions between two sub-task decompositions, namely an FM sub-task decomposition prediction and a ground-truth sub-task decomposition. We present scores for temporal similarity and semantic similarity above 90%, compared to 30% of a randomized baseline, for multiple robotic environments, demonstrating the effectiveness of our proposed framework. Our results enable building diverse, large-scale, language-supervised datasets for improved robotic TAMP. Copyright © 2024, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning for Resource Allocation in Large-Scale Robotic Warehouse Sortation Centers

Multi-Agent Reinforcement Learning for Resource Allocation i...

引用

IEEE Conference on Decision and Control

作者： Yi Shen Benjamin McClosky Joseph W. Durham Michael M. Zavlanos Department of Mechanical Engineering and Materials Science Duke University Amazon Robotics

Robotic sortation centers use mobile robots to sort packages by their destinations. The destination-to-sort-location (chute) mapping can significantly impact the volume of packages that can be sorted by the sortation floor. In this work, we propose a multi-agent reinforcement learning method to solve large-scale chute mapping problems with hundreds of agents (the destinations). To address the exponential growth of the state-action space, we decompose the joint action-value function as the sum of local action-value functions associated with the individual agents. To incorporate robot congestion effects on the rates at which packages are sorted, we couple the local action-value functions through the states of destinations mapped to nearby chutes on the sortation floor. We show that our proposed framework can solve large chute mapping problems and outperforms static or reactive policies that are commonly used in practice in robotic sortation facilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing VTOL Performance: Shrouded Rotor BLDC Motor Model and Validation 7

Enhancing VTOL Performance: Shrouded Rotor BLDC Motor Model ...

引用

7th International Conference on Aeronautical, Aerospace and mechanical engineering, AAME 2024

作者： Dayhoum, Abdallah Etewa, Mohamed Ramirez-Serrano, Alejandro Martinuzzi, Robert Mechanical and Manufacturing Engineering University of Calgary AB Canada Guidance Department Military Technical College Cairo Egypt Director UVS Robotarium Robotics Lab. University of Calgary AB Canada University of Calgary AB Canada

One prominent area of current research interest, driven by a multitude of factors and considerations, centers around drone technology. A primary challenge currently faced in the realm of small-scale Unmanned Aerial Vehicles (UAVs) is the increasing demand for increased power coupled with the constraint of limited flight duration provided by available battery technology. These vehicles fall into two overarching categories based on the presence or absence of shrouding around their rotor(s). Shrouded rotors play a pivotal role in augmenting aerodynamic performance by enhancing thrust while mitigating blade-tip vortex losses and numerous other aspects that are not presented in open rotors. Although such characteristics contribute to an expanded effective rotor diameter and optimized airflow within the shroud. There are numerous aspects related to power, shroud and rotor characterization, etc. that need to be understood before shrouded rotors are commonly used. This paper presents the implementation of an effective mathematical model for Brushless Direct Current (BLDC) motors, specifically tailored for application in conjunction with shrouded rotors aimed at enhancing thrust and reducing power consumption. The proposed model serves to predict the performance characteristics of the utilized motor within the context of the specified shrouded rotor combination. In order to identify the effects of the induced load torque on the rotor's dynamic response, a methodical analysis is conducted on the numerical simulation of the proposed model. The results are experimentally verified for hover flying in a case study of a scalable and highly maneuverable vertical takeoff and landing aircraft developed for operations in highly confined spaces. The adoption of this modeling technique is anticipated to significantly streamline the shrouded rotor combination design and selection process, particularly in the selection of an appropriate motor. © Published under licence by IOP Publishing L

关键词： Brushless DC motors

来源：评论

学校读者我要写书评

暂无评论

Development of an Arm with Safety Harness Function to Hold and Release Lifeline for Multi-Rotor Drones

Development of an Arm with Safety Harness Function to Hold a...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Masui, Kaichi Higashi, Yoshiyuki Sawada, Yuichi Kyoto Institute of Technology Division of Mechanodesign Kyoto606-8585 Japan Osaka Institute of Technology Department of Robotics Osaka530-8568 Japan Kyoto Institute of Technology Faculty of Mechanical Engineering Kyoto606-8585 Japan

ISBN: (纸本)9798350350821

The purpose of this study is to develop an arm to physically prevent multi-rotor crashes. The developed arm serves as a safety harness, and the multi-rotor equipped with the arm is intended to be used for inspection tasks of structures such as bridges. The drone flies while holding the lifelines installed on the structure using the arm and conducts inspection work during that time. In previous study, the arm installed on the quad-rotor with a safety harness had a ring-shaped tip that could not be opened and closed. Therefore, in this study, we developed an openable arm that can hold and release the lifeline at any desired timing. The created arm can hold objects simply by pressing the arm against the target to be restrained. Furthermore, by opening the arm's tip, it is possible to release the restrained object. Experimental results confirmed that when mounted on the multi-rotor, the arm can hold and release objects during flight. © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Estimating the Inclination Angle of Steel Structures Using ToF Camera for Attractive Infrastructure Inspection Drones

Estimating the Inclination Angle of Steel Structures Using T...

引用

2024 IEEE Region 10 Conference, TENCON 2024

作者： Okubo, Taisei Higashi, Yoshiyuki Sawada, Yuichi Kyoto Institute of Technology Division of Mechanodesign Kyoto606-8585 Japan Osaka Institute of Technology Department of Robotics Osaka530-8568 Japan Kyoto Institute of Technology Faculty of Mechanical Engineering Kyoto606-8585 Japan

ISBN: (纸本)9798350350821

In this paper, a method for estimating the inclination angle of steel structures using a Time of Flight (ToF) camera is proposed, enabling the attractive infrastructure inspection drone to be attracted to inclined steel surfaces. Through evalu-ation experiments, it was confirmed that the developed method can estimate the inclination angle of steel structures with a mean error of within 1 degree, © 2024 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

GARField: Addressing the Visual Sim-to-Real Gap in Garment Manipulation with Mesh-Attached Radiance Fields

GARField: Addressing the Visual Sim-to-Real Gap in Garment M...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Delehelle, Donatien Caldwell, Darwin Chen, Fei University of Genova Genova Italy Istituto italiano di Tecnologia Hong Kong Hong Kong T-Stone Robotics Institute Chinese University of Hong Kong Department of Mechanical and Automation Engineering Hong Kong Hong Kong

ISBN: (纸本)9781665481090

While humans intuitively manipulate garments and other textile items swiftly and accurately, it is a significant challenge for robots. A factor crucial to human performance is the ability to imagine, a priori, the intended result of the manipulation intents and hence develop predictions on the garment pose. That ability allows us to plan from highly obstructed states, adapt our plans as we collect more information and react swiftly to unforeseen circumstances. Conversely, robots struggle to establish such intuitions and form tight links between plans and observations. We can partly attribute this to the high cost of obtaining densely labelled data for textile manipulation, both in quality and quantity. The problem of data collection is a long-standing issue in data-based approaches to garment manipulation. As of today, generating high-quality and labelled garment manipulation data is mainly attempted through advanced data capture procedures that create simplified state estimations from real-world observations. However, this work proposes a novel approach to the problem by generating real-world observations from object states. To achieve this, we present GARField (Garment Attached Radiance Field), the first differentiable rendering architecture, to our knowledge, for data generation from simulated states stored as triangle meshes. Code is available on the project website. © 2024 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Human Following Robot Based on Object Detection for Aerospace Application 1

Human Following Robot Based on Object Detection for Aerospac...

引用

1st International Conference of Adisutjipto on Aerospace Electrical engineering and Informatics, ICAAEEI 2024

作者： Sumari, Arwin Datumava Wahvudi Aryandika, Ahnaf Bagus Purnami, Ndaru Atmi Dermawan, Denny Syamsiana, Ika Noer State Polytechnic of Malang Cognitive Artificial Intelligence Research Group Department of Electrical Engineering Malang Indonesia Adisutjipto Institute of Aerospace Technology Electrical Engineering Study Program Yogyakarta Indonesia Adisutjipto Institute of Aerospace Technology Aerospace Navigation Instrumentation Control Automation and Robotics System Research Group Electrical Engineering Study Program Yogyakarta Indonesia Adisutjipto Institute of Aerospace Technology Electrical Engineering Study Program Aerosp. Digit. Syst. Microprocessor Microcontroller and Programmable Logic Devices Research Group Yogyakarta Indonesia

ISBN: (纸本)9798331507930

In this research, the Human Following Robot (HFR) prototype has been designed and implemented using YOLO v3-Tiny and Tensor Flow Lite on Raspberry Pi hardware named Rewang. The HFR Rewang is designed to assist aircraft technicians by bringing maintenance tool kits to aircraft shelters. Rewang's movement is based on a camera as a vision sensor following the movement of human entities. Image input is processed by YOLO v3-Tiny through the determination of the bounding box, the calculation of Euclidean Distance, and the determination of the pixel value of the camera as the basis of Rewang's movement which is regulated by an L298N driver motor that controls two Direct Current (DC) motors for the left and right wheels. The test results show that Rewang can move at an average speed of 0.18 m/s at 2 m with a travel time of 11 seconds with a light intensity of more than 250 lux. The minimum and maximum distance of object detection is as far as 120 cm and 400 cm, with an object detection accuracy of 95.8%. Rewang allows the HFR to have a larger carrying capacity to bring more complete aircraft maintenance tools and is prospective for other aerospace and general applications. © 2024 IEEE.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

PRODUCING MULTIFUNCTIONAL PA6/ORGANOSHEET COMPOSITES WITH SUSTAINABLE PLANT BASED GRAPHENE COATINGS

PRODUCING MULTIFUNCTIONAL PA6/ORGANOSHEET COMPOSITES WITH SU...

引用

SAMPE 2024 Conference and Exhibition

作者： Mulqueen, Daniel W. Wright, Joseph Xiao, Shu Kravchenko, Oleksandr G. Climate Robotics INC HoustonTX77064 United States Department of Mechanical and Aerospace Engineering Old Dominion University Kaufman Hall NorfolkVA23508 United States Department of Electrical and Computer Engineering Old Dominion University Frank Reidy Research Center Suite 300 NorfolkVA23508 United States

ISBN: (纸本)9781934551455

The use of composite components in battery enclosures for electric vehicles requires the addition of electrically conductive elements to provide shielding from Electromagnetic Interference (EMI). Graphene, a highly conductive nanomaterial, can be useful for creating conductive paths on the surface and in interlaminar layers of the composite to provide shielding. In this study we examined impacts of plant-based graphene nanoplatelets (pGNP) surface coating on PA6/glass fiber organosheet with regards to EMI shielding, surface resistance, and flame retardancy. Suspensions of pGNP—derived from agricultural waste materials—were examined for their effectiveness in coating the PA6 surface. Ε-Caprolactam and polyurethane (PU) were examined for their impacts on the sprayed surface and interactions with the substrate. pGNP surface application at 10 g/m2 gave a 790 Ω/sq surface resistance, an improvement over untreated PA6 of seven orders of magnitude. Ε-Caprolactam and PU addition improve adhesion on the PA6 surface, scratch resistance of the coating, and show evidence of in-situ polymerization with pGNP. This material is cost effective for automotive applications and allows for rapid manufacturing using thermoforming processes. We propose a conductive pGNP coating that can be applied after the forming operation, thus avoiding limitations of thermoforming of the conductive veils. © 2024 Soc. for the Advancement of Material and Process engineering. All rights reserved.

关键词： Thermoforming

来源：评论

学校读者我要写书评

暂无评论

Customizing Textile and Tactile Skins for Interactive Industrial Robots

Customizing Textile and Tactile Skins for Interactive Indust...

引用

作者： Su, Bo Ying Wei, Zhongqi McCann, James Yuan, Wenzhen Liu, Changliu Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA15213 United States Department of Mechanical Engineering Carnegie Mellon University PittsburghPA15213 United States Robotics Institute Carnegie Mellon University PittsburghPA15213 United States

Tactile skins made from textiles enhance the robot–human interaction by localizing contact points and measuring contact forces. This paper presents a solution for rapidly fabricating, calibrating, and deploying these skins on industrial robot arms. The novel automated skin calibration procedure maps skin locations to robot geometry and calibrates contact force. Through experiments on a FANUC LR Mate 200id/7L industrial robot, we demonstrate that tactile skins made from textiles can be effectively used for human–robot interaction in industrial environments, and can provide unique opportunities in robot control and learning, making them a promising technology for enhancing robot perception and interaction. © 2023 by ASME.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Nanometer-scale wafer surface defect measurement based on state-space digital holographic microscopy 4

Nanometer-scale wafer surface defect measurement based on st...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Geng, Shengcheng Ai, Lingyu Gao, Yujia Gan, Zhi Xiao, Yingjie Gong, Weixu Cho, Myungiin Won, Kanghee School of Integrated Circuits Jiangnan University Wuxi214122 China School of Internet of Things Engineering Jiangnan University Wuxi214122 China Hankyong National University School of ICT Robotics and Mechanical Engineering Anseong17579 Korea Republic of Kyung Hee University Department of Information Display Seoul02447 Korea Republic of

ISBN: (纸本)9781510688834

Non-destructive measurement of nanoscale surface defects plays a significant role in wafer production and processing. This paper proposes a method based on state-space digital holographic microscopy for measuring wafer surface defects with nanometer-scale accuracy. The angular spectrum method is used to numerically reconstruct the complex wavefront of the object, while reference holograms are applied for conjugate compensation, effectively reducing the effects of surface distortions and noise. To optimize phase estimation, the extended Kalman filter (EKF) method is employed, which can suppress noise, resolve phase unwrapping issues, and achieve accurate phase recovery from a single hologram, thereby extracting detailed defect information from wafer surfaces. Compared to traditional phase recovery methods, this approach demonstrates superior performance in high-noise environments, significantly improving defect measurement accuracy and achieving nanometer-level surface defect measurement. The proposed method has extensive application potential, especially in surface defect detection research for semiconductor manufacturing. © 2025 SPIE.

关键词： Extended Kalman filters

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：