检索结果-内蒙古大学图书馆

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

Automatic Heliostat Directing System Based On Microcontroller ESP32

Automatic Heliostat Directing System Based On Microcontrolle...

引用

2023 International Conference on Electrical engineering and Informatics, ICEEI 2023

作者： Medyanto, Richard Sanjaya, Nicholas Liawatimena, Suryadiputra Binus Aso School of Engineering Bina Nusantara University Automotive & Robotics Program Computer Engineering Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350381290

Solar energy is one of the most abundant sources of renewable energy in Indonesia. Solar energy is now typically harnessed using solar panels, but the low efficiency of photovoltaic cells requires the development of other alternatives. The heliostat is a sunlight directing device with mirrors that can be used in a concentrated solar power system. Current heliostats require high capital investment due to their large frames and expensive components. This research was undertaken to develop a lower cost heliostat using a smaller frame, ESP32 microcontroller, servo motor and low-cost components. The position of the sun can be determined using an algorithm based on the National Oceanic and Atmospheric Administration (NOAA) solar calculator, and the mirror is moved to maintain the sun's reflection on a target. The result of this research is a set of heliostat prototypes consisting of the frame and control system. Tests were carried out to test the performance of the designed heliostat and it was found that the heliostat has an accuracy of about 60 cm and can raise temperatures up to 3.41°C. The conclusion is that the heliostat can be used in a concentrated solar power system to heat boilers in solar power towers. © 2023 IEEE.

关键词： Solar energy

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

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

Development of Detection Kidney Function Stand Alone System and Design based on Oral Ammonia Levels 7

Development of Detection Kidney Function Stand Alone System ...

引用

7th International Conference of Computer and Informatics engineering, IC2IE 2024

作者： William Hansen, Natasha Angeline Mariana, Yosica Sitepu, Elioenai Astuti, Winda Siswanto, Melinda Bina Nusantara University Binus Aso School of Engineering Automotive and Robotics Program Computer Engineering Department Jakarta11480 Indonesia Bina Nusantara University Binus Aso School of Engineering Product Design Program Industrial Engineering Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Industrial Engineering Department Jakarta11480 Indonesia Bina Nusantara University Biotechnology Engineering Department Jakarta11480 Indonesia

ISBN: (纸本)9798331505530

The development of detection kidney function system at the first prototype have problem with the dependence on the internet, which make not practical in the development of the system and the initial design was not ergonomic. In this work the development of the second step is done with the improvement of accuracy compared with other methods. In this work the new design of the embedded system is also applied and in term of algorithm, the system applied for woman patient. Three different types of machine learning techniques, namely K-nearest neighbors (KNN), Decision Tree and Random Forest are applied and compared. The AI-based kidney failure severity identification system with KNN algorithm had an average accuracy of 90% and 91% for training and testing accuracy, respectively. The design of the embedded system also renews with stylist, simple and practical. © 2024 IEEE.

关键词： Support vector machines

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

Online 3D Bin Packing for Novel Objects Based on Deep Reinforcement Learning

Online 3D Bin Packing for Novel Objects Based on Deep Reinfo...

引用

2023 International Conference on Advanced robotics and Intelligent Systems, ARIS 2023

作者： Chien, Shao-Yu Wong, Ching-Chang Tamkang University College of Engineering Doctoral Program in Robotics New Taipei City25137 Taiwan Tamkang University Electrical and Computer Engineering Department New Taipei City25137 Taiwan

ISBN: (纸本)9798350302714

In this paper, a method using deep reinforcement learning is proposed to deal with the 3D online bin packing problem. The packing objects are not limited to several specific or fixed cuboid objects, but are composed of more than a thousand objects and randomly generated cuboids, which make the trained policy network can handle novel unknown objects. In addition, the posture of the object in the box can be any angle, not limited to horizontal and vertical. In the proposed method, four voxel maps are used as inputs, and a Soft Actor-Critic (SAC) algorithm is used to train a policy network. On the other hand, in order to deal with various objects with irregular shapes, a packing task simulator with physics engine enable the policy network to learn the state of falling and stacking objects. In terms of training environment of deep reinforcement learning, the proposed method can be applied to boxes of different sizes because of the scalable image information. Moreover, a reward function and a training strategy with gradually increasing difficulty are proposed to effectively improve the learning of policy network. In terms of experimental results, the results on a random object bin packing task in a simulator illustrate the effectiveness of the proposed method. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Visual Mapping of Underwater Ship Hull Surface using View-based Piecewise-Planar Measurements

引用

IFAC-PapersOnLine 2019年第21期52卷 384-389页

作者： Seonghun Hong Jinwhan Kim Robotics Program KAIST Daejeon Korea Department of Mechanical Engineering KAIST Daejeon Korea

Visual inspection of underwater ship hulls using unmanned underwater vehicles needs to be conducted at very close range to the target surface because of the limited visibility conditions in underwater environments due to light attenuation, scattering, and turbidity. These environmental challenges result in ineffective photometric and geometric information in hull surface images, and thus, the performance of conventional 3D reconstruction techniques is often not satisfactory. This paper presents a visual mapping method for 3D reconstruction of underwater ship hull surface using a monocular camera as a primary mapping sensor. The main idea of the proposed approach is to model the moderately curved hull surface as a combination of piecewise-planar panels, and to generate a global map by aligning the images in a 2D reference frame and correcting them appropriately to reflect the information of perspective projections of the 3D panels. Experimental results are shown to demonstrate the feasibility of the proposed method using a dataset obtained in a field experiment with a full-scale ship in a real sea environment.

关键词： visual mapping 3D reconstruction computer vision autonomous underwater vehicle visual inspection

来源：评论

学校读者我要写书评

暂无评论

Multimode locomotion via SuperBot reconfigurable robots

Multimode locomotion via SuperBot reconfigurable robots

引用

作者： Shen, Wei-Min Krivokon, Maks Chiu, Harris Everist, Jacob Rubenstein, Michael Venkatesh, Jagadesh Information Sciences Institute Computer Science Department University of Southern California University of Southern California Polymorphic Robotics Laboratory Information Science Institute Polymorphic Robotics Laboratory Product Development Engineering Program University of Southern California

One of the most challenging issues for a self-sustaining robotic system is how to use its limited resources to accomplish a large variety of tasks. The scope of such tasks could include transportation, exploration, construction, inspection, maintenance, in-situ resource utilization, and support for astronauts. This paper proposes a modular and reconfigurable solution for this challenge by allowing a robot to support multiple modes of locomotion and select the appropriate mode for the task at hand. This solution relies on robots that are made of reconfigurable modules. Each locomotion mode consists of a set of characteristics for the environment type, speed, turning-ability, energy-efficiency, and recoverability from failures. This paper demonstrates a solution using the SuperBot robot that combines advantages from M-TRAN, CONRO, ATRON, and other chain-based and lattice-based robots. At the present, a single real SuperBot module can move, turn, sidewind, maneuver, and travel on batteries up to 500 m on carpet in an office environment. In physics-based simulation, SuperBot modules can perform multimodal locomotions such as snake, caterpillar, insect, spider, rolling track, H-walker, etc. It can move at speeds of up to 1.0 m/s on flat terrain using less than 6 W per module, and climb slopes of no less 40 degrees.

关键词： Robots

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：