检索结果-内蒙古大学图书馆

2023 International Conference on System Science and engineering, ICSSE 2023

作者： Wong, Shang-Wen Chiu, Yu-Chen Tsai, Chi-Yi Tamkang University Doctoral Program in Robotics College of Engineering New Taipei City Taiwan Tamkang University Department of Electrical and Computer Engineering New Taipei City Taiwan

ISBN: (纸本)9798350322941

This paper proposes a pose estimation system for robot grasping based on a novel Object Affordance Detection and Segmentation (OADS) network. The proposed system consists of four modules: (1) OADS network;(2) point cloud extraction;(3) object pose estimation;(4) grasp pose estimation. Based on the OADS network, the proposed system achieves affordance-based object pose estimation results. The proposed grasp pose estimation system is evaluated on a laboratory-made dual-arm robot. Experimental results show that the proposed system achieves high detection rate and high accuracy in affordance detection and segmentation tasks, leading to a high success rate in object grasping tasks with lab-made dual-arm robot. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

In-hand manipulation of a circular dynamic object by soft fingertips without angle measurement

引用

Science China(Information Sciences) 2021年第5期64卷 193-208页

作者： R.GARCIA-RODRIGUEZ V.PARRA-VEGA Aeronautical Engineering Program and Postgraduate Program in Aerospacial Engineering Universidad Politecnica Metropolitana de Hidalgo Robotics and Advanced Manufacturing Department Research Center for Advanced Studies (CINVESTAV)

A multi-fingered robotic hand with curved fingertips enables contact re-positioning without reattaching at the expense of fingertip rolling. This rolling stands for a characteristic that facilitates dexterous manipulation but results in an algebraically complex dynamic model subject to such constraints. The hemispherical shape of fingertips allows a dexterous manipulation when controlling the tangent forces, which are essential to rotate object. However, the measurement of the object angle in practice requires tactile-optical sensing. In this paper, considering robotic fingers with curved soft tips, we propose a feedback control that ensures optimal dynamical grasping of a circular rigid object. It is shown that the collaboration of the contact forces, to get a minimum pose of internal forces, and the tangential forces, to induce the conditions for assuring the grasp closure, is necessary to get a skillful manipulation. In this case, the orientation control of a circular object to the desired angle while avoiding direct measurement of the object angle is presented. Stability conditions of the system are presented in the sense of stability-in-the-manifold. Finally, representative simulations are shown and discussed.

关键词： optimal grasping manipulation soft-fingertips circular object stability-in-the-manifold

来源：评论

学校读者我要写书评

暂无评论

Separation of microalgae from bacterial contaminants using spiral microchannel in the presence of a chemoattractant

引用

Bioresources and Bioprocessing 2024年第1期11卷 511-525页

作者： Leticia F.Ngum Y.Matsushita Samir F.El-Mashtoly Ahmed M.R.Fath El-Bab Ahmed L Abdel-Mawgood Institute of Basic and Applied Sciences Biotechnology ProgramEgypt-Japan University of Science and TechnologyAlexandria 21934Egypt Institute of Basic and Applied Sciences Nanoscience ProgramEgypt-Japan University of Science and TechnologyAlexandria 21934Egypt Mechatronics and Robotics Engineering Department Egypt-Japan University of Science and TechnologyAlexandria 21934Egypt.

Cell separation using microfluidics has become an effective method to isolate biological contaminants from bodily fluids and cell cultures,such as isolating bacteria contaminants from microalgae cultures and isolating bacteria contaminants from white blood *** this study,bacterial cells were used as a model contaminant in microalgae culture in a passive microfluidics device,which relies on hydrodynamic forces to demonstrate the separation of microalgae from bacteria contaminants in U and W-shaped cross-section spiral microchannel fabricated by defocusing CO_(2) laser *** a flow rate of 0.7 ml/min in the presence of glycine as bacteria chemoattractant,the spiral microfluidics devices with U and W-shaped cross-sections were able to isolate microalgae(Desmodesmus sp.)from bacteria(***)with a high separation efficiency of 92%and 96%*** the same flow rate,in the absence of glycine,the separation efficiency of microalgae for U-and W-shaped cross-sections was 91%and 96%,*** was found that the spiral microchannel device with a W-shaped cross-section with a barrier in the center of the channel showed significantly higher separation *** microchannel chips with U-or W-shaped cross-sections were easy to fabricate and exhibited high *** these advantages,these devices could be widely applicable to other cell separation applications,such as separating circulating tumor cells from blood.

关键词： W-shaped cross-section CO_(2)laser ablation Glycine Separation efficiency Removal ratio

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of a new hybrid rotary steerable system for directional drilling

Design and analysis of a new hybrid rotary steerable system ...

引用

2013 44th IEEE International Symposium on robotics, ISR 2013

作者： Park, Jieun Kim, Jongheon Park, Byeolteo Myung, Hyun Division of Mechanical Engineering KAIST Korea Republic of Dept. Civil and Environmental Engineering KAIST Korea Republic of Dept. Civil and Environmental Engineering Robotics Program KAIST Korea Republic of

ISBN: (纸本)9781479911738

Recently, shale gas has become an important energy source. Directional drilling is an imperative technology when it comes to excavating shale gas because it exists in underground in horizontally spaced areas. A rotary steerable system (RSS) enables the effective directional drilling. In general, there are two types of RSS, the point-the-bit and the push-the-bit. In this paper, a new hybrid type RSS is proposed. The hybrid type RSS has advantages of both the point-the-bit and the push-the-bit. We expect that the proposed RSS can increase the build-rate. The effectiveness of the proposed mechanism is discussed by predicting the side force. © 2013 IEEE.

关键词： Directional drilling

来源：评论

学校读者我要写书评

暂无评论

Exploring Classification, Size, and Quality of Mangifera Indica L. Through Image Processing and AI Techniques 2

Exploring Classification, Size, and Quality of Mangifera Ind...

引用

2nd International Conference on Mechanics, Electronics, Automation and Automatic Control, MEAAC 2024

作者： Wanthong, Irin Sri-On, Theeraphat Seangsri, Soontaree Khaengkarn, Sorada Srisertpol, Jiraphon Mechatronics Engineering Program School of Mechanical Engineering Suranaree University of Technology Nakhon Ratchasima Thailand Department of Mechatronics and Robotics Engineering School of Engineering and Innovation Rajamangala University of Technology Tawan-ok Chonburi Thailand

ISBN: (纸本)9781643685403

This paper introduces methods for efficiently classifying mangoes intended for export, a market valued at approximately 4,500 million baht annually. The classification process is divided into two primary components: size categorization and quality assessment. The first phase involves categorizing mango sizes into four distinct categories (M, 1L, 2L, 3L), while the second phase focuses on assessing mango quality, particularly detecting anthracnoseâ€"a prevalent disease affecting mangoes. This detection is achieved through image processing techniques, where images are converted into binary representations and analyzed using both Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs). Comparative analysis reveals that CNN outperforms ANN in size classification, achieving a remarkable train accuracy of 99.16% and a test accuracy of 88.0%. Furthermore, in quality classification, CNN demonstrates a train accuracy of 91.0% and a test accuracy of 88.0%. These findings underscore the effectiveness of CNN techniques in accurately classifying mangoes for export, thereby facilitating improved quality control and market competitiveness. Â© 2024 The Authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Stability Guaranteed Actor-Critic Learning for Robots in Continuous Time 20

Stability Guaranteed Actor-Critic Learning for Robots in Con...

引用

20th International Conference on Electrical engineering, Computing Science and Automatic Control, CCE 2023

作者： Pantoja-Garcia, Luis Parra-Vega, Vicente Garcia-Rodriguez, Rodolfo Robotics and Adv. Manufacturing CINVESTAV Saltillo Mexico Universidad Politecnica Metropolitana de Hidalgo Postgraduate Program in Aerospacial Engineering Tolcayuca Mexico

ISBN: (纸本)9798350306767

Actor-Critic (AC) architecture has the salient feature, for the plethora of Reinforcement Learning schemes, that two intertwining neural networks (NN) collaborate to deploy a motor learning mechanism that oversees and evaluates the action to control a dynamical system as the robot manipulator. Since such NNs can be studied as dynamical systems to learn how to control the robot dynamics with a given performance, it has finally paved the way to deal with stability analysis, unfortunately, few works have addressed it. In this paper, we propose a Critic-NN whose approximation of the value function substantiates the decision making mechanism that collaborates to tune the Actor-NN action (approximation of inverse dynamics). The novel proposed design of the adaptation of the neural weights yields Lyapunov stability that provides explicit conditions for an attractive invariant set that render a stable regime using a quite simple NN with one hidden layer. Numerical simulations show the performance of the proposed approach. In addition, robustness is analyzed when the robot is subject to Liptchitz disturbances, interestingly showing relaunching of the learning mechanism when needed. Finally, a discussion on dealing with asymptotic stability, robustness issues, and the learning mechanism from a reward provided by the expert user is addressed. © 2023 IEEE.

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

ED-NERF: EFFICIENT TEXT-GUIDED EDITING OF 3D SCENE WITH LATENT SPACE NERF 12

ED-NERF: EFFICIENT TEXT-GUIDED EDITING OF 3D SCENE WITH LATE...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Park, Jangho Kwon, Gihyun Ye, Jong Chul Kim Jaechul Graduate School of AI Korea Republic of Robotics Program Korea Republic of Department of Bio and Brain Engineering KAIST Korea Republic of

Recently, there has been a significant advancement in text-to-image diffusion models, leading to groundbreaking performance in 2D image generation. These advancements have been extended to 3D models, enabling the generation of novel 3D objects from textual descriptions. This has evolved into NeRF editing methods, which allow the manipulation of existing 3D objects through textual conditioning. However, existing NeRF editing techniques have faced limitations in their performance due to slow training speeds and the use of loss functions that do not adequately consider editing. To address this, here we present a novel 3D NeRF editing approach dubbed ED-NeRF by successfully embedding real-world scenes into the latent space of the latent diffusion model (LDM) through a unique refinement layer. This approach enables us to obtain a NeRF backbone that is not only faster but also more amenable to editing compared to traditional image space NeRF editing. Furthermore, we propose an improved loss function tailored for editing by migrating the delta denoising score (DDS) distillation loss, originally used in 2D image editing to the three-dimensional domain. This novel loss function surpasses the well-known score distillation sampling (SDS) loss in terms of suitability for editing purposes. Our experimental results demonstrate that ED-NeRF achieves faster editing speed while producing improved output quality compared to state-of-the-art 3D editing models. Code and rendering results are available at our project page. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

CWave: High-performance single-source any-angle path planning on a grid

CWave: High-performance single-source any-angle path plannin...

引用

2017 IEEE International Conference on robotics and Automation, ICRA 2017

作者： Sinyukov, Dmitry A. Padir, Taskin Robotics Engineering Program Worcester Polytechnic Institute WorcesterMA01609 United States Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States

ISBN: (纸本)9781509046331

Path planning on a 2D-grid is a well-studied problem in robotics. It usually involves searching for a shortest path between two vertices on a grid. Single-source path planning is a modified problem which asks to find distances from a given point to all other points on the map. A high-performance algorithm for single-source any-angle path planning on a grid that we named CWave is proposed in this work. 'Any-angle' attribute of a path planning algorithm implies that such algorithm can find paths which may include any angle segments, as opposed to standard A © 2017 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Damping Injection Learning for Robots with Actor-Critic Driven by Integral Sliding Manifolds 20

Damping Injection Learning for Robots with Actor-Critic Driv...

引用

20th International Conference on Electrical engineering, Computing Science and Automatic Control, CCE 2023

作者： Tevera-Ruiz, Alejandro Garcia-Rodriguez, Rodolfo Parra-Vega, Vicente Robotics and Advanced Manufacture-CINVESTAV Saltillo Mexico Univ. Politécnica Metropolitana de Hidalgo Postgraduate Program in Aerospace Engineering Mexico

ISBN: (纸本)9798350306767

Reinforcement Learning (RL) is characterized by enforcing a reward collection mechanism that qualifies task performance aimed at optimizing a value function that tunes the action (control). In contrast to control theory, RL satisfies two metrics simultaneously: the task metric commonly, defined as the task error, and the temporal difference (TD) error. Thus, the RL has been empowered to learn how to fulfill control tasks based on a learning stage that collects rewards that evaluate a second metric of the robot's performance. In this way, including RL in control systems is an advantageous scheme for some critical tasks nowadays. Consequently, the stability can be guaranteed, largely missing in the RL's literature, to safe system operation.. In this paper, we propose an Actor-Critic (AC) scheme using the Critic Neural Network (C-NN) to approximate a value function using the TD error reduction, whereas the adaptive tuning of damping injection gain is provided by the Actor NN (A-NN) to enforce stability in closed-loop finally;achieving asymptotic stability with an underlying integral sliding mode loop. In this way, our proposal contributes to a novel model-free RL scheme that yields local exponential convergence with a smooth control action. Numeric simulations for a 2-DoF robot manipulator are presented and discussed under different conditions.. © 2023 IEEE.

关键词： Asymptotic stability

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Navigation Architecture and Robotic Arm Controller for a Sample Return Rover

Hierarchical Navigation Architecture and Robotic Arm Control...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Velin Dimitrov Mathew DeDonato Adam Panzica Samir Zutshi Mitchell Wills Taskin Padir Robotics Engineering Program Worcester Polytechnic Institute

This work presents a hierarchical navigation architecture and cascade classifier for sample search and identification on a space exploration rover. A three tier navigation architecture and inverse Jacobian based robot arm controller are presented. The algorithms are implemented on AERO, the Autonomous Exploration Rover, participating in the NASA Sample Return Robot Centennial Challenge in 2013 and initial results are demonstrated.

关键词： Navigation Manipulators Robot sensing systems Planning Robot kinematics

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：