检索结果-内蒙古大学图书馆

Underwater Object Detection and Pose Estimation using Deep Learning ⁎

IFAC-PapersOnLine 2019年第21期52卷 78-81页

作者： MyungHwan Jeon Yeongjun Lee Young-Sik Shin Hyesu Jang Ayoung Kim Department of the Robotics Program KAIST Daejeon S. Korea KRISO Daejeon S. Korea Department of Civil and Environmental Engineering KAIST Daejeon S. Korea

This paper presents an approach for making a dataset using a 3D CAD model for deep learning based underwater object detection and pose estimation. We also introduce a simple pose estimation network for underwater objects. In the experiment, we show that object detection and pose estimation networks trained via our synthetic dataset present a preliminary potential for deep learning based approaches in underwater. Lastly, we show that our synthetic image dataset provides meaningful performance for deep learning models in underwater environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Hand Direct Manipulation of Complex Constrained Virtual Objects

Multi-Hand Direct Manipulation of Complex Constrained Virtua...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Jun-Sik Kim MyungHwan Jeon Jung-Min Park Center for Intelligent and Interactive Robotics Korea Institute of Science and Technology Hwarangro 14 gil 5 Seongbuk-Gu Korea Robotics Program KAIST Korea

We present a method to manipulate virtual objects which are constrained complexly and reconfigurable as if they would exist in a real world by using multiple hands simultaneously. A complexly constrained, and reconfigurable object, such as a Rubik's cube, is hard to describe its physical motion constraints, mainly because they are determined by the grasping situation and dynamically changeable. Rather than describing the physical motion constraints in a general form, we more focus on the multiple hand interaction of a complex object. A complex object is divided into multiple subparts which are grasped by each hand, and the constraints between the subparts are optimized for inducing natural and continuous movement. For this, we propose a dynamically adjustable data structure for representing object parts grasped by multiple hands, and an optimization-based pose estimation of the constrained subparts along with their grasped hands. The experiments show that human subjects can manipulate a complexly constrained object such as a Rubik's cube without any difficulty as if it exists in the real-world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of a wall-climbing drone with a rotary arm for climbing various-shaped surfaces 15

Development of a wall-climbing drone with a rotary arm for c...

引用

15th International Conference on Ubiquitous Robots, UR 2018

作者： Myeong, Wancheol Song, Seungwon Myung, Hyun Dept. of Civil and Environmental Engineering Robotics Program KAIST Daejeon34141 Korea Republic of

ISBN: (纸本)9781538663349

In this paper, a novel wall-climbing drone installed with a rotary arm is proposed for climb operation on various shaped walls. Robots that can climb the wall are applicable to many operations such as structural health monitoring of high-rise buildings, bridges, nuclear power plants;maintenance of solar panels and glass walls;and visual inspection of the aircraft and vessels. Traditional wall-climbing robots use magnetic, vacuum, or bioinspired methods mimicking gecko foot for those purposes. However, those methods cannot be applied to various-shaped walls like inclined, and an obstacle existing walls such as window frames. To solve this problem, unmanned aerial vehicle (UAV)-type wall-climbing robots have recently been developed, but those types have disadvantages in terms of energy efficiency and impact in attaching and detaching processes. Therefore, in this paper, a wall-climbing drone with a rotary arm is proposed. The angle of the rotary arm is controlled depending on the slope angle of the wall to achieve energy efficiency. The drone was prototyped and tested in indoor environment to verify the feasibility of the mechanism. © 2018 IEEE.

关键词： Walls (structural partitions)

来源：评论

学校读者我要写书评

暂无评论

Correction to “A Sigmoid-Colon-Straightening Soft Actuator With Peristaltic Motion for Colonoscopy Insertion Assistance: Easycolon”

引用

IEEE robotics and Automation Letters 2021年第3期6卷 5736-5736页

作者： Hansoul Kim Joonhwan Kim Jae Min You Seung Woo Lee Ki-Uk Kyung Dong-Soo Kwon Division of Mechanical Engineering School of Mechanical Aerospace and Systems Engineering KAIST Daejeon South Korea Robotics Program KAIST Daejeon South Korea Division of Gastroenterology Department of Internal Medicine College of Medicine The Catholic University of Korea Seoul South Korea

There are two corresponding authors who have contributed to this letter, yet only one of them has been mentioned as the corresponding author in the original letter. As a result, “Ki-Uk Kyung” was added to footnote a... 详细信息

关键词： Actuators Colonoscopy

来源：评论

学校读者我要写书评

暂无评论

RRNet: Repetition-reduction network for energy efficient decoder of depth estimation

arXiv

引用

arXiv 2019年

作者： Oh, Sangyun Kim, Hye-Jin S. Lee, Jongeun Kim, Junmo School of Electrical and Computer Engineering UNIST Ulsan Korea Republic of Neural Processing Research Center Seoul National University Seoul Korea Republic of Robotics Program School of Electrical Engineering KAIST Daejeon Korea Republic of Artificial Intelligence Laboratory ETRI Daejeon Korea Republic of

We introduce Repetition-Reduction network (RRNet) for resource-constrained depth estimation, offering significantly improved efficiency in terms of computation, memory and energy consumption. The proposed method is based on repetition-reduction (RR) blocks. The RR blocks consist of the set of repeated convolutions and the residual connection layer that take place of the pointwise reduction layer with linear connection to the decoder. The RRNet help reduce memory usage and power consumption in the residual connections to the decoder layers. RRNet consumes approximately 3.84 times less energy and 3.06 times less memory and is approaximately 2.21 times faster, without increasing the demand on hardware resource relative to the baseline network [1], outperforming current state-of-the-art lightweight architectures such as SqueezeNet [2], ShuffleNet [3], MobileNetv2 [4] and PyDNet [5]. Copyright © 2019, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Scalar field reconstruction based on the Gaussian process and adaptive sampling 14

Scalar field reconstruction based on the Gaussian process an...

引用

14th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2017

作者： Jonsson, Porsteinn B. Wang, Jeonghyeon Kim, Jinwhan Laboratory Department of Mechanical Engineering KAIST Daejeon34141 Korea Republic of Robotics Program KAIST Daejeon34141 Korea Republic of

ISBN: (纸本)9781509030552

This paper proposes a method of reconstructing a scalar field by adaptively choosing sampling locations and using the measurements obtained from those locations to reconstruct an estimate of the underlying field using Gaussian process regression. Spreading sampling points evenly over the field may not always be effective if the field is not uniformly distributed and the maximum number of measurements is limited. Taking more measurements in regions of large changes in the field than in regions of small changes can give a better estimate than spreading the same number of measurements evenly over the space. The proposed algorithm was tested on a synthetic scalar field and compared to two popular methods of determining sensor placement based on entropy and mutual information from information theory. © 2017 IEEE.

关键词： Gaussian noise (electronic)

来源：评论

学校读者我要写书评

暂无评论

Development of a Transformable Self-Balancing Mobile Robot

Development of a Transformable Self-Balancing Mobile Robot

引用

International Conference on Control, Automation and Systems

作者： Jinkwang Kim Geonhoo Kim Taewoo Han Seungwon Heo Yongjae Kim Hyun Myung Department of the Robotics Program KAIST Daejeon Korea Department of Electronics Engineering Korea University of Technology and Education(Koreatech) Cheonan Korea Department of Civil and Environmental Engineering KAIST Daejeon Korea

ISBN: (纸本)9781538670804;9788993215168

This paper reports the design, construction, and control of a mobile robot that can be transformed from the four-wheel mobile robot into two-wheel self-balancing robot and vice versa. The hardware of the robot utilizes the mechanism of the three-link manipulator. This robot is composed of three components;the body part, the middle link, and the top part. The system architecture comprises a pair of DC motor controllers to move the wheel, two servo motors to move the middle link and the top part, and an Arduino microcontroller board, etc. When the robot is transformed to the two-wheel self-balancing robot, the COM (Center of Mass) equation, and the IMU (Inertial Measurement Unit) sensor are employed for attitude determination. The method of the control is based on a proportional-integral-differential (PID) control. The results show the possibility of performing both functions of the four-wheel mobile robot and two-wheel self-balancing robot.

关键词： Three-link manipulator Two-wheel self-balancing robot Center of mass

来源：评论

学校读者我要写书评

暂无评论

Online Recurrent Extreme Learning Machine and its Application to Time-series Prediction

Online Recurrent Extreme Learning Machine and its Applicatio...

引用

International Joint Conference on Neural Networks

作者： Jin-Man Park Jong-Hwan Kim Robotics Program KAIST School of Electrical Engineering KAIST

ISBN: (纸本)9781509061839

Online sequential extreme learning machine (OS-ELM) is an online learning algorithm training single-hidden layer feedforward neural networks (SLFNs), which can learn data one-by-one or chunk-by-chunk with fixed or varying data size. Due to its characteristics of online sequential learning, OS-ELM is popularly used to solve time-series prediction problem, such as stock forecast, weather forecast, passenger count forecast, etc. OS-ELM, however, has two fatal drawbacks: Its input weights cannot be adjusted and it cannot be applied to learn recurrent neural network (RNN). Therefore we propose a modified version of OS-ELM, called online recurrent extreme learning machine (OR-ELM), which is able to adjust input weights and can be applied to learn RNN, by applying ELM-auto-encoder and a normalization method called layer normalization (LN). Proposed method is used to solve a time-series prediction problem on New-York City passenger count dataset, and the results show that R-ELM outperforms OS-ELM and other online-sequential learning algorithms such as hierarchical temporal memory (HTM) and online long short-term memory (online LSTM).

关键词： Online sequential extreme learning machine (OS-ELM) Online recurrent extreme learning machine (OR-ELM) Online learning Time-series prediction Auto-encoding e-learning recurrent neural nets Learning machines normalization method Chunking data size learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Development of a Hover-Capable AUV System for Automated Visual Ship-Hull Inspection and Mapping

Development of a Hover-Capable AUV System for Automated Visu...

引用

Oceans (Conference)

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

ISBN: (纸本)9781509064298;9780692946909

Generally, underwater hull inspection have been conducted by human divers. It is an extremely dangerous task, and hence, can be a potential application for unmanned underwater vehicles. The operational safety and performance of in-water inspection can be significantly improved by introducing unmanned vehicle systems. This study addresses the development of an hover-capable autonomous underwater vehicle system and its operational algorithms for automated visual ship hull inspection with no (or minimum) human intervention. The feasibility and practical performance of the developed system and algorithms are demonstrated by conducting field experiments with a full-scale ship in a real sea environment.

关键词： Autonomous underwater vehicles Visual inspection Underwater navigation Image mosaicking

来源：评论

学校读者我要写书评

暂无评论

Scalar field reconstruction based on the Gaussian process and adaptive sampling

Scalar field reconstruction based on the Gaussian process an...

引用

International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

作者： Porsteinn B. Jónsson Jeonghyeon Wang Jinwhan Kim Mobile Robotics and Intelligence (MORIN) Laboratory Departrnent of Mechanical Engineering KAIST Daeieon Korea Robotics Program KAIST Daejeon Korea

关键词： Entropy Mutual information Gaussian processes Training Covariance matrices Training data Simulated annealing

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：