检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man, and Cybernetics

作者： Min-Joo Kim Seung-Hwan Baek Se-Hyoung Cho Jong-Hwan Kim Robotics Program School of Electrical Engineering KAIST 291 Daehak-ro Yuseong-gu Daejeon 305-701 Republic of Korea

ISBN: (纸本)9781509018987

This paper proposes a novel scheme of integrating episodic memory into semantic memory based task planner. Task planners have taken an important role in AI research along with semantic memory to better perform tasks for robots. Episodic memory memorizes and retrieves temporal sequence of situated behaviors by which temporal relationship between behaviors can be defined. None of any research, however, has implemented it into their work for task planning. By introducing episodic memory into task planner, the temporal causal relationship between situated behaviors, which are stored in semantic memory, is taken into consideration. The integrated architecture proves its effectiveness by notably reducing the number of nodes traversed in finding solutions. Robots can reduce time complexity in solving given problems by retrieving previous memories. Deep Adaptive Resonance Theory (Deep-ART) neural model and cogency-based hierarchical behavior planner are used for the episodic memory and the task planner, respectively. Cogency-based hierarchical behavior planner proves its capability of solving given problems in experiment with humanoid robot Mybot, and Deep-ART is augmented to the planner and tested in simulations. Therefore, the contribution of this approach lies on developing a framework which takes advantage of implementing episodic memory and planner in one place.

关键词： Semantics Planning Robots Compounds Subspace constraints Silicon Conferences

来源：评论

学校读者我要写书评

暂无评论

Drone-type wall-climbing robot platform for structural health monitoring 6

Drone-type wall-climbing robot platform for structural healt...

引用

Joint 6th International Conference on Advances in Experimental Structural Engineering, AESE 2015 and 11th International Workshop on Advanced Smart Materials and Smart Structures Technology, ANCRiSST 2015

作者： Myeong, W.C. Jung, K.Y. Jung, S.W. Jung, Y.H. Myung, H. Dept. of Civil and Environmental Engineering KAIST Daejeon Korea Republic of Dept. of Civil and Environmental Engineering KAIST Daejeon Korea Republic of Robotics Program KAIST Daejeon Korea Republic of Dept. of Civil and Environmental Engineering KAIST Daejeon Korea Republic of Dept. Civil and Environmental Engineering KAIST Daejeon Korea Republic of

Though civil structures need constant maintenance and inspection of the structural health condition and safety of the users, the accessibility is getting harder and harder because of their gigantic height and size. To overcome this problem, several approaches for wall-climbing mechanism have been introduced for many decades;however, there is no assured solution yet. One of the reasons why existing wall-climbing robots haven't been put to practical use is the risk of accidental fall due to operational failure from the harsh environment like gust and surface's uncertainty. Therefore, we propose a drone-type wall-climbing aerial robot platform that can approach to any place of the structure by flying and sticking to the target place with pose change and perching mechanism. Not only that the robot is equipped with a moving mechanism like other wall-climbing robots to move on the vertical surface of the structure, but also this paper suggests the wall-climbing mechanism for an aerial robot, its pose change and wall sticking mechanism, and the way to move on the surface of a structure. © International Conference on Advances in Experimental Structural Engineering. All rights reserved.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Fuzzy gaze control-based navigational assistance system for visually impaired people in a dynamic indoor environment

Fuzzy gaze control-based navigational assistance system for ...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Seung-Beom Han Deok-Hwa Kim Jong-Hwan Kim Robotics Program KAIST Daejeon Korea Department of Electrical Engineering KAIST Daejeon Korea

285 million people are estimated to be visually impaired worldwide. Visually impaired people typically use a white cane or a guide dog or both of them to walk down the street. However, such as a cane and/or a dog are not enough to secure them from being collided with obstacles in a dynamic environment. This paper proposes a navigational assistance system based on fuzzy integral-based gaze control for visually impaired people in a dynamic indoor environment. It largely consists of an RGB-D camera and a vibrotactile vest interface. The RGB-D camera detects static and dynamic obstacles and obtains obstacle information on their center positions, sizes, and velocities. The fuzzy integral-based gaze control for obstacle detection is proposed to reduce a blind spot of the camera and obtain more information of the environment. The vibrotactile vest interface notifies a direction to avoid the obstacle using a fuzzy integral-based imminent-obstacle selection algorithm. To confirm the performance of the proposed assistance system for visually impaired people, experiments are carried out in an indoor dynamic environment.

关键词： Cameras 5G mobile communication Navigation Heuristic algorithms Indoor environments Visualization Size measurement

来源：评论

学校读者我要写书评

暂无评论

Underwater Visual SLAM with Loop-Closure using Image-to-Image Link Recovery

Underwater Visual SLAM with Loop-Closure using Image-to-Imag...

引用

OCEANS

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

ISBN: (纸本)9781479987375

This study develops an underwater visual simultaneous localization and mapping (SLAM) algorithm using a monocular vision as a major measurement sensor, focusing in particular on the loop-closure problem. Although most vision-based loop-closure approaches have been implemented by feature-based pairwise image matching, matching underwater images is generally a challenging task due to the limited number of feature correspondences or relatively small overlapping regions between the compared images. The lack of loop-closing events caused by these challenges can degrade the navigation and mapping performance of visual SLAM. For robust visual SLAM, a loop-closure algorithm that can recover image-to-image matching links is presented. The proposed loop-closure algorithm is more resilient to failures of pairwise matching and thus can maximize the use of image-to-image links, thereby improving the estimation performance in the context of visual SLAM. To validate the effectiveness of the proposed algorithm, a hover-capable unmanned underwater vehicle was used for in-water experiments, and the proposed algorithm was also evaluated through a series of comparative results drawn from an experimental dataset.

关键词： Underwater visual SLAM Loop-closure Link recovery

来源：评论

学校读者我要写书评

暂无评论

Optimization of fish-like locomotion using hierarchical reinforcement learning

Optimization of fish-like locomotion using hierarchical rein...

引用

International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

作者： Jeonghyeon Wang Jinwhan Kim Robotics Program Ocean Robotics & Intelligence (ORIN) Laboratory Department of Mechanical Engineering KAIST Daejeon Korea

With an interest in advanced marine propulsion systems, much research has been done on mimicking fish-like locomotion using flapping fins. This study aims to optimize the swimming pattern of fish-like locomotion based on hierarchical reinforcement learning. A simplified carangiform fish model is employed and a segmented tail motion is learned by Q-learning to maximize the average forward velocity by flapping the tail fin. The performance of the self-learned swimming pattern is verified and analyzed in terms of the flapping efficiency. The results show that the flapping angle limit of approximately 35 degrees is best in maximizing the forward moving velocity and the hierarchical reinforcement learning approach is effective in providing a reasonable solution for a large-scale problem.

关键词： Learning (artificial intelligence) Learning systems Mathematical model Markov processes Robots Propulsion

来源：评论

学校读者我要写书评

暂无评论

Development of a drone-type wall-sticking and climbing robot

Development of a drone-type wall-sticking and climbing robot

引用

International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

作者： W.C. Myeong K.Y. Jung S.W. Jung Y.H. Jung H. Myung Dept. of Civil and Environmental Engineering KAIST Daejeon South Korea Robotics Program KAIST Daejeon South Korea

Urban structures need constant maintenance and inspection of the structural health condition and safety of the users, however, to access the structure is getting harder and harder due to their enormous height and size. In order to deal with this problem, though many researchers have developed several robots for wall-climbing there is no guaranteed solution yet. One of the critical reasons why existing wall-climbing robots haven't been available in the field is the risk of accidental fall due to operational failure from the harsh environment like strong wind and surface's unpredictable condition. Therefore, we tried to develop a drone-type wall-climbing aerial robot platform that can approach to any place of the structure by flying and sticking to the target place with pose change and perching mechanism. The robot is equipped with a locomotion mechanism like other wall-climbing robots to move on the vertical surface of the structure. This paper deals with installing the wall-climbing mechanism on the aerial robot, its pose change and wall sticking mechanism, and locomotion on the vertical surface of an urban structure.

关键词： Mobile robots Wheels Force Rotors Payloads Propellers

来源：评论

学校读者我要写书评

暂无评论

User-adaptive fall detection for patients using wristband

User-adaptive fall detection for patients using wristband

引用

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Young-Hoon Nho Jong Gwan Lim Dae-Eon Kim Dong-Soo Kwon Robotics Program and Human-Robot Interaction research center Korea Advanced Institute of Science and Technology Daejeon Republic of Korea Department of Information Engineering Computer Science and University of Trento Italy KAIST Human-Robot Interaction Research Center Daejeon Republic of Korea Department of Mechanical Engineering Human-Robot Interaction research center Daejeon Republic of Korea

Fall detection systems have been proposed to prevent additional injuries following fall accidents. This paper introduces an easily learnable fall detection system based on the data of an individual patient in a hospital room. The improvement of low performance using a single accelerometer at wrists and the inconvenience of sensor attached to a waist in the conventional approach was concentrated on by integrating heart rate signals to the conventional acceleration approach and changing the sensor location from a waist to wrists. As for the optimal heart rate feature selection, we proposed a four-feature vector combination (root mean square of successive differences, standard deviation of successive differences, normal to normal 50, normal to normal 20) with correlation and mutual information analysis in addition to mean absolute deviation selected as an accelerometer feature. To easily acquire and train the patients' fall data, our system was based on unsupervised learning approaches using Gaussian mixture models for optimal classifiers with the optimal cluster number decided by cluster validation index of square error sum. A 10-fold cross validation was applied for a final performance evaluation where each threshold for separating fall state from non-fall state was automatically decided in several comparison groups, which were created on the basis of fusion timing and used sensors. As a result, despite sensors attached to the wrist, the wearable inconvenience of the conventional is overcome using the feature-level fused approach between heart rates and accelerations with the accuracy up to 98.39 %, which is closest to 99.34 % of the case using a single accelerometer located at the waist.

关键词： Accelerometers Heart rate Wrist Training data Hospitals Robot sensing systems Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Development of a UAV-type jellyfish monitoring system using deep learning

Development of a UAV-type jellyfish monitoring system using ...

引用

International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

作者： Hangeun Kim Donghoon Kim Sungwook Jung Jungmo Koo Jae-Uk Shin Hyun Myung Civil & Environmental Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon Korea Urban Robotics Laboratory (URL) Robotics Program Korea Advanced Institute of Science and Technology (KAIST) Daejeon Korea Rastech Inc. Daejeon Korea

At present, unmanned aerial vehicles (UAVs) are the primary platforms widely used for environmental monitoring. The advantage of the UAV-type surveillance system is its low-cost with high observation performance. Using this system, we can extend the workable area of the jellyfish removal system. The proposed system observes jellyfish on the surface of the sea while flying, and can recognize a herd of jellyfish using deep learning. The preliminary results of the proposed system show that the proposed system improves the jellyfish removal system for efficient operation.

关键词： Robots Sea surface Surveillance Machine learning Global Positioning System Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Mechanism and system design of MAV (Micro Aerial Vehicle)-type wall-climbing robot for inspection of wind blades and non-flat surfaces

Mechanism and system design of MAV (Micro Aerial Vehicle)-ty...

引用

International Conference on Control, Automation and Systems

作者： Sungwook Jung Jae-Uk Shin Wancheol Myeong Hyun Myung Robotics Program KAIST Rastech Inc. Dept. of Civil and Environmental Engineering KAIST Dept. of Civil and Environmental Engineering Robotics Program KAIST

ISBN: (纸本)9781479999767

Wind turbines need annual inspections to investigate their states which may have damages, such as cracks, erosion, bonding defects, cavities and delamination. Wind blades inspection, however, is a difficult process which needs specialized equipment and well-trained technicians to perform it manually. In addition, most approaches to inspect require pre-installed infrastructures like ropes or other platforms, so they are not appropriate for a close investigation and has a low preference. To overcome these problems, the need for a wall-climbing robot has emerged. In this paper, we suggest a MAV (Micro Aerial Vehicle) type wall-climbing robot that has four rotors to make thrust force for flying and four wheels for wall-climbing so that it can fly, stick, and move on a vertical and non-flat surface. The overall inspection process has two parts;macro and micro inspections. The main concept was verified throughout simulations.

关键词： Micro Aerial Vehicle (MAV) Wind turbine inspection Non-destructive testing Non-flat surface

来源：评论

学校读者我要写书评

暂无评论

The Role of Relative Spinal Motion during Feline Galloping for Speed Performance

引用

Journal of Bionic Engineering 2014年第4期11卷 517-528页

作者： Young Kook Kim Jongwon Park Byungho Yoon Kyung-Soo Kim Soohyun Kim Robotics Program Korea Advanced Institute of Science and Technology (KAIST) Daejeon 305-701 Republic of Korea Department of Mechanical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon 305-701 Republic of Korea

Felines use their spinal column to increase their running speed at rapid locomotion performance. However, its motion profile behavior during fast gait locomotion has little attention. The goal of this study is to examine the relative spinal motion profile during two different galloping gait speeds. To understand this dynamic behavior trend, a dynamic motion of the feline animal （Felis catus domestica） was measured and analyzed by motion capture devices. Based on the experiments at two different galloping gaits, we observed a significant increase in speed （from 3.2 m.s-1 to 4.33 m.s-1） during the relative motion profile synchronization between the spinal （range： 118.86~ to 168.00~） and pelvic segments （range： 46.35~ to 91.13~） during the hindlimb stance phase （time interval： 0.495 s to 0.600 s）. Based on this discovery, the relative angular speed profile was applied to understand the possibility that the role of the relative motion match during high speed locomotion generates bigger ground reaction force.

关键词： feline galloping galloping gait pattern relative spinal motion speed performance phase match

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：