检索结果-内蒙古大学图书馆

作者： Kim, HyungTae Lee, duk-Yeon Choi, dongwoon Kang, Jaehyeon Lee, dong-Wook Digital Transformation R&D Department Korea Institute of Industrial Technology Ansan Gyeonggi15588 Korea Republic of Applied Robot R&D Department Korea Institute of Industrial Technology Ansan Gyeonggi15588 Korea Republic of

A digital focus index (dFI) is a value used to determine image focus in scientific apparatus and smart devices. Automatic focus (AF) is an iterative and time-consuming procedure;however, its processing time can be reduced using a general processing unit (GPU) and a multi-core processor (MCP). In this study, parallel architectures of a minimax search algorithm (MSA) are applied to two dFIs: range algorithm (rA) and image contrast (CT). The dFIs are based on a histogram;however, the parallel computation of the histogram is conventionally inefficient because of the bank conflict in shared memory. The parallel architectures of rA and CT are constructed using parallel reduction for MSA, which is performed through parallel relative rating of the image pixel pairs and halved the rating in every step. The array size is then decreased to one, and the minimax is determined at the final reduction. Kernels for the architectures are constructed using open source software to make it relatively platform independent. The kernels are tested in a hexa-core PC and an embedded device using Lenna images of various sizes based on the resolutions of industrial cameras. The performance of the kernels for the dFIs was investigated in terms of processing speed and computational acceleration;the maximum acceleration was 32.6× in the best case and the MCP exhibited a higher performance. Copyright © 2023 KSII.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

reinforcement Learning Based Position Control of 1-dOF rotational Hydraulic Actuator

Reinforcement Learning Based Position Control of 1-DOF Rotat...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Hokwon Kang Jin Tak Kim Sangsin Park Jungsan Cho Department of Robotics Engineering University of Science and Technology(UST) Daejeon Korea The Hydraulic Robot Laboratory Robot R&D Group Korea Institute of Industrial Technology(KITECH) Ansan South Korea

ISBN: (数字)9788993215380

ISBN: (纸本)9798331517939

In this study, we propose a reinforcement learning (rL) based position control method for a one-degree-of-freedom (1-dOF) rotational hydraulic actuator. Controlling hydraulic actuators is challenging due to their nonlinear characteristics and complex structure. reinforcement learning offers the advantage of enabling control through learning without requiring a detailed understanding of the model, using virtual environments. However, simulators do not perfectly replicate real-world conditions. To address this, we aim to enhance the fidelity of the simulation and improve the performance of reinforcement learning-based controllers by integrating real-world data into the simulation using deep neural networks (dNN). The reinforcement learning is trained using the Proximal Policy Optimization (PPO) algorithm, and it is validated through experiments with step and sine inputs.

关键词： Legged locomotion refining Hydraulic actuators Position control Virtual environments reinforcement learning Artificial neural networks Hydraulic systems Control systems Optimization

来源：评论

学校读者我要写书评

暂无评论

Workspace Analysis of Cable-driven Continuum Manipulator Using Universal Joint

Workspace Analysis of Cable-Driven Continuum Manipulator Usi...

引用

International Conference on Ubiquitous robots (Ur)

作者： Myung-oh Kim dongwoon Choi duck-Yeon Lee dong-Wook Lee Department of Mechanical Engineering Hanynag University Seoul Korea Applied Robot R&D Department Korea Institute of Industrial Technology (KITECH) Ansan Korea

This paper presents a comprehensive study on the workspace of a continuum manipulator using a universal joint. The research focuses on analyzing the effect of different parameters such as joint angles and flexible link lengths on the workspace of the manipulator. A mathematical model is developed to determine the workspace and validate the results through simulations. The study also includes a discussion on the limitations and challenges of using a universal joint in continuum manipulators and ways to overcome them. The findings of this research contribute to the understanding of the workspace of continuum manipulators and can be used to design more effective and efficient manipulator systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Button recognition for Indoor Mobile robots

Self-Supervised Button Recognition for Indoor Mobile Robots

引用

International Symposium on Soft Computing and Intelligent Systems (SCIS)

作者： Jeong-Won Pyo Kwang-Hee Lee Jung-San Cho Tae-Yong Kuc Electrical and Computer Engineering SungKyunKwan University Suwon Korea Robot R&D Group Korea Institute of Industrial Technology Ansan korea

In recent years, with the rapid advances in technology, the precision and accuracy of indoor autonomous driving have also improved remarkably. However, despite the development of these technologies, there are still many difficulties to perform services through real mobile robots. In this paper, we focused on the mobile robot that drives in multiple spaces in a multi-story building using an elevator. In order to operate the elevator, the mobile robot must be able to operate by pressing the elevator button itself. To solve this problem, in this paper, we propose self-supervised button recognition. We created fake buttons for self-supervised learning and placed these on random backgrounds to increase the diversity of the dataset. In addition, the generated realistic buttons are re-generated like real buttons through a GAN. In experiments, we presented that our self-supervised button recognition was performed in an actual environment without separate labeling.

关键词： Training Self-supervised learning Pressing Generative adversarial networks Elevators Mobile robots Labeling

来源：评论

学校读者我要写书评

暂无评论

Numerical Analysis of Soliton Propagation in a Tapered Waveguide

引用

Journal of Optical Communications 2023年第4期44卷 535-538页

作者： raja, M.A. ranathive, S. Sivaram, M. Krishna Kumar, L. Vinoth Kumar, K. Amiri, Iraj S Department of Biomedical Engineering Dr. N.G.P. Institute of Technology Coimbatore India Department of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Networking Lebanese French University Kurdistan Region Erbil Iraq Department of CSE Nehru Institute of Engineering & Technology Coimbatore India Department of EEE Karunya Institute of Technology and Sciences Coimbatore India Computational Optics Research Group Advanced Institute of Materials Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Applied Sciences Ton Duc Thang University Ho Chi Minh City Viet Nam

In this paper, dispersion decreased profiled tapered fiber is designed whose dispersion characteristics and soliton propagation is investigated numerically using darboux transformation. The result reveals that solitons pulse gets compression as it propagates along the length of the tapered region. © 2019 Walter de Gruyter GmbH, Berlin/Boston.

关键词： dispersion (waves)

来源：评论

学校读者我要写书评

暂无评论

Trotting gait control of quadruped robot based on Trajectory Planning

Trotting gait control of quadruped robot based on Trajectory...

引用

World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)

作者： Baoping Ma Ziqian Liu Changwu Peng Xiaoqiang Li R&D Engineer. Laboratory of the Quadruped Robot The 21st Research Institute of China Electronics Technology Group Corporation Shanghai China R & D Engineer The 21st Research Institute of China Electronics Technology Group Corporation Shanghai China

ISBN: (纸本)9781665421737

In order to improve the motion stability and environmental adaptability of quadruped robot in trotting gait, a motion control method based on swing leg gait planning is proposed in this paper. The kinematics model of quadruped robot is established, the forward and inverse solutions are obtained, and the trajectory curve of swinging leg of quadruped robot in trotting gait is planned. The simulation model is established in AdAMS to verify that the trotting gait control method based on the foot trajectory planning of the swing leg is effective and feasible.

关键词： Legged locomotion Adaptation models Torque Trajectory planning Stability analysis Trajectory Quadrupedal robots

来源：评论

学校读者我要写书评

暂无评论

The Optimal Energy Flow of Combined Heat and Power Systems Considering Users' Comfort 5

The Optimal Energy Flow of Combined Heat and Power Systems C...

引用

5th IEEE Conference on Energy Internet and Energy System Integration, EI2 2021

作者： Lin, Junguang Pan, Zhaoguang Zhao, Shenyi Wu, Fan Jiang, Yuehong Shi, runye International Joint Lab on Low-grade Energy Utilization of Zhejiang Province Zhejiang Energy Group R&D Institute Co. Ltd.2 Hangzhou China Department of Electrical Engineering and Applied Electronics Technology Tsinghua University Beijing China Tsinghua-Berkeley Shenzhen Institute Tsinghua University Shenzhen China

ISBN: (纸本)9781665434256

Combined heat and electric power energy networks are common as multi-energy systems and its optimal operation is a hot topic. The goals of this manuscript is to achieve the optimal heat and power flow for the coupling network with tree-topology heat network and dC power network. The study aims to minimize the total deviations between user setting points and building indoor temperatures, decrease total energy consumption and cost. An optimization model is proposed using a steady-state method. The effectiveness of this method is proved by simulation results. Optimal operational schedule is obtained which can considers the complexity of the combined heat and electric networks. © 2021 IEEE

关键词： Electric load flow

来源：评论

学校读者我要写书评

暂无评论

Hand-eye Calibration using Images restored by deep Learning

Hand-eye Calibration using Images Restored by Deep Learning

引用

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)

作者： Hyun-Su Kim Tae-Yong Kuc Kwang-Hee Lee Sungkyunkwan University Robot R&D Group Korea Institute of Industrial Technology

ISBN: (数字)9781728161648

ISBN: (纸本)9781728161655

The problem of determining the transformation between the end-effector and the camera attached to the robot arm is called hand-eye calibration. For this calibration, the pose of the robot and the image data of the calibrated camera must be acquired. Since industrial robots use fixed focus cameras, the depth of field is limited, and variable focus lenses cannot determine the camera position or pose with high accuracy because the parameters of the camera change. If the pose of a robot is out of depth of field (dOF), the camera is out of focus, and the image is blurred. If hand-eye calibration is performed using these images, the resulting data includes errors. In this paper, image restoration is performed using deep learning on a blurred image where a marker cannot be found because it is out of focus. This technique is used to sharply restore images and demonstrate a technique for finding markers. We improved the precision of the hand-eye calibration problem by obtaining a clear image restored even in various pose of the robot and reducing the error that occurs in the blurred image.

关键词： Calibration Cameras robots Image restoration robot vision systems robot kinematics deep learning

来源：评论

学校读者我要写书评

暂无评论

Kinesthetic sensing of hole position by 3-finger gripper

Kinesthetic sensing of hole position by 3-finger gripper

引用

International Conference on Ubiquitous robots and Ambient Intelligence (UrAI)

作者： Myoung-Su Choi dong-Hyuk Lee Jae-Han Park Ji-Hun Bae Robotics R&D Group Korea Institute of Industrial Technology Ansan Repulbic of Korea(South) Applied Robot R&D Departmment Korea Institute of Industrial Technology Ansan Repulbic of Korea(South)

ISBN: (数字)9781728157153

ISBN: (纸本)9781728157160

In this study, we present a novel method for `peg-in-hole' assembly using a multi-joint three-fingered gripper. In previous studies, we have conducted peg-in-hole assembly based on spiral search method, not knowing the exact hole position. However, search time varies greatly depending on the error between the peg and the hole, it was difficult to estimate tact time of the assembly task. In this paper, in order to reduce the search time deviation of the hole, we propose a method that estimating the direction of the hole first before conducting the search motion. direction of the hole is estimated by `kinesthetic sensing' using the fingers grasping the peg. The feasibility of the proposed method has been verified through peg-in-hole assembly experiments using the three-fingered robot gripper.

关键词： robot sensing systems Grippers Navigation Grasping Performance evaluation Estimation

来源：评论

学校读者我要写书评

暂无评论

Meal intention recognition system based on gaze direction estimation using deep learning for the user of meal assistant robot

引用

Journal of Institute of Control, robotics and Systems 2021年第5期27卷 334-341页

作者： Park, Hyunji Jang, Inhoon Ko, Kwangeun Applied Robot R&D Department Korea Institute of Industrial Technology Korea Republic of Department of Computer Science & Engineering Hanyang University Korea Republic of Industry Academic Cooperation Foundation Hankyong National University Korea Republic of

Care robots that provide dietary supplements to the elderly and the disabled should be able to intelligently interact with the users’ intention to eat in real-time and provide the food they want. To this end, based on deep learning, we have developed a user interface that facilitates the selection of food to be eaten according to six user gaze directions. A single-stage object-detection deep learning model has been implemented as a lightweight, single-stage object-detection deep learning model that can be installed on commercial tablets, and the accuracy of this model was 0.9857. © ICrOS 2021.

关键词： Human robot interaction

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：