• 한국IT서비스학회지
• /
• 제15권4호
• /
• pp.1-24
• /
• 2016

With the innovation of information technology, non-face-to-face robo advisor with high accessibility and convenience is spreading. The current robot advisor recommends appropriate investment products after understanding the investment propensity based on the structured data entered directly or indirectly by individuals. However, it is an inconvenient and obtrusive way for financial consumers to inquire or input their own subjective propensity to invest. Hence, this study proposes a way to deduce the propensity to invest in unstructured data that customers voluntarily exposed during consultation or online. Since prediction performance based on unstructured document differs according to the characteristics of text, in this study, classification algorithm optimized for the characteristic of text left by financial consumers is selected by performing prediction performance evaluation of various learning discrimination algorithms and proposed an intelligent method that automatically recommends investment products. User tests were given to MBA students. After showing the recommended investment and list of investment products, satisfaction was asked. Financial consumers' satisfaction was measured by dividing them into investment propensity and recommendation goods. The results suggest that the users high satisfaction with investment products recommended by the method proposed in this paper. The results showed that it can be applies to non-face-to-face robo advisor.

• 로봇학회논문지
• /
• 제1권1호
• /
• pp.25-35
• /
• 2006

Improving practicality of SLAM requires various sensors to be fused effectively in order to cope with uncertainty induced from both environment and sensors. In this case, combining sonar and vision sensors possesses numerous advantages of economical efficiency and complementary cooperation. Especially, it can remedy false data association and divergence problem of sonar sensors, and overcome low frequency SLAM update caused by computational burden and weakness in illumination changes of vision sensors. In this paper, we propose a SLAM method to join sonar sensors and stereo camera together. It consists of two schemes, extracting robust point and line features from sonar data and recognizing planar visual objects using multi-scale Harris corner detector and its SIFT descriptor from pre-constructed object database. And fusing sonar features and visual objects through EKF-SLAM can give correct data association via object recognition and high frequency update via sonar features. As a result, it can increase robustness and accuracy of SLAM in indoor environment. The performance of the proposed algorithm was verified by experiments in home -like environment.

• 한국위성정보통신학회논문지
• /
• 제9권4호
• /
• pp.32-37
• /
• 2014

파노라마 영상은 카메라 시야각의 제한을 극복할 수 있으므로 로봇 비전, 스테레오 카메라, 보안 감시 등의 분야에서 효율적으로 연구되고 있다. 파노라마 영상은 사람의 시야각 이상의 넓은 화각을 가진 영상을 구현할 수 있으며 시야각의 현장감을 중심으로 실제로 현장에 있는 듯한 실감 공간을 제공하는 기술이다. 영상에서 기하학적 변화에 강인한 특징점 및 대응점을 검출하고 호모그래피 행렬을 추정하는데 있어서 모든 대응점을 사용하면 연산량이 많아지고 정확한 호모그래피 행렬을 추정하기 어렵다. 따라서 본 논문에서는 전처리 과정에서 입력 영상들의 히스토그램을 비교 분석하여 유사도가 높은 중첩되는 영역을 추정하며 특징점을 검출하기 위해 SURF 알고리즘을 사용하였다. 또한 영상을 입력하는 순서를 해결하여 순서에 제약 없이 영상을 입력하여 파노라마를 생성할 수 있도록 하였다.

• Journal of Astronomy and Space Sciences
• /
• 제30권4호
• /
• pp.279-290
• /
• 2013

Due to the continuous space development by mankind, the number of space objects including space debris in orbits around the Earth has increased, and accordingly, difficulties of space development and activities are expected in the near future. In this study, among the stages for space debris removal, the implementation of a vision-based approach technique for approaching space debris from a far-range rendezvous state to a proximity state, and the ground test performance results were described. For the vision-based object tracking, the CAM-shift algorithm with high speed and strong performance, and the Kalman filter were combined and utilized. For measuring the distance to a tracking object, a stereo camera was used. For the construction of a low-cost space environment simulation test bed, a sun simulator was used, and in the case of the platform for approaching, a two-dimensional mobile robot was used. The tracking status was examined while changing the position of the sun simulator, and the results indicated that the CAM-shift showed a tracking rate of about 87% and the relative distance could be measured down to 0.9 m. In addition, considerations for future space environment simulation tests were proposed.

• 한국항해항만학회지
• /
• 제35권2호
• /
• pp.121-130
• /
• 2011

The localization of vehicle is an important part of an unmanned vehicle control problem. Pseudolite ultrasonic system(PUS) is the method to find an absolute position with a high accuracy by using ultrasonic sensor. And Gyro is the inertial sensor to measure yaw angle of vehicle. PUS can be able to estimate the position of mobile robot precisely, in which errors are not accumulated. And Gyro is a more faster measure method than PUS. In this paper, we suggest a more accuracy method of calculating PUS which is numerical analysis approach named Newtonian method. And also propose the fusion method to increase the accuracy of estimated angle on moving vehicle by using PUS and Gyro integrated system by Kalman filtering. To control the 4WS unmanned vehicle, the trajectory following algorithm is suggested. And the new concept arbitration of goal controller is suggested. This method considers the desirability function of vehicle state. Finally, the performances of Newtonian method and designed controller were verified from the experimental results with the 4WS vehicle scaled 1/10.

• 한국산학기술학회논문지
• /
• 제16권6호
• /
• pp.3714-3721
• /
• 2015

서셉터 히터에서 쉬스 열선을 사용하는 방법이 일반화되어 있지만, 대면적 초고온 조건에서는 서셉터의 온도 균일도 성능 저하의 문제가 있다. 본 연구에서는 온도균일도 성능을 향상시킬 수 있도록 판형 형태의 열선을 기본으로 새로운 서셉터를 설계하여 프로토타입을 개발하였다. 표면 온도 $450^{\circ}C$의 고온에서 1.4% 이내로 온도 균일도가 시제작된 서셉터에서 검증될 수 있었다. 또한 온도 학습 데이터를 이용하여 측정 온도 데이터를 예측할 수 있는 커널 회귀 알고리즘을 개발하고, 이러한 예측 데이터와 측정 데이터의 비교 분석으로 균일도 측정 온도의 신뢰성을 확인할 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제19권9호
• /
• pp.1647-1658
• /
• 2016

RGB+D database has been widely used in object recognition, object tracking, robot control, to name a few. While rapid advance of active depth sensing technologies allows for the widespread of indoor RGB+D databases, there are only few outdoor RGB+D databases largely due to an inherent limitation of active depth cameras. In this paper, we propose a novel method used to build outdoor RGB+D databases. Instead of using active depth cameras such as Kinect or LIDAR, we acquire a pair of stereo image using high-resolution stereo camera and then obtain a depth map by applying stereo matching algorithm. To deal with estimation errors that inevitably exist in the depth map obtained from stereo matching methods, we develop an approach that estimates confidence of depth maps based on unsupervised learning. Unlike existing confidence estimation approaches, we explicitly consider a spatial correlation that may exist in the confidence map. Specifically, we focus on refining confidence feature with the assumption that the confidence feature and resultant confidence map are smoothly-varying in spatial domain and are highly correlated to each other. Experimental result shows that the proposed method outperforms existing confidence measure based approaches in various benchmark dataset.

• 한국지능시스템학회논문지
• /
• 제17권5호
• /
• pp.701-706
• /
• 2007

최근 고층건물의 방진시스템 및 자동차의 현가장치 분야에 MR 유체를 이용한 반능동 진동제어에 관한 연구가 활발히 진행되면서 MR 유체의 밸브모드 특성을 이용한 선형 MR 댐퍼가 널리 사용되고 있다. 그러나 전단모드를 이용한 회전형 MR 댐퍼에 관한 연구는 초기단계에 머물고 있다. 본 연구에서는, 주행로봇의 무한회전형 액츄에이터용 회전형 댐퍼의 진동제어에 관한 연구를 수행하였으며, 퍼지 로직을 기반으로 한 회전형 MR 댐퍼용 진동제어 알고리즘을 제안하였다. 퍼지제어기의 입출력 이득과 멤버쉽 함수의 모양은 유전자 알고리즘을 이용하여 조정하였다. 시뮬레이션 결과는 MR 댐퍼에 충격력이 가해질 때 퍼지 스카이-훅 제어의 제어성능을 보여준다.

• 한국정보통신학회논문지
• /
• 제11권10호
• /
• pp.1977-1985
• /
• 2007

문자 인식은 인공지능의 한 분야로써 자동화 시스템, 로봇, HCI 분야에서 그 응용성 이 증대되고 있는 첨단 기술이다. 본 논문에서는 숫자, 기호, 영어, 한글이 여러 가지 형태로 조합되어 사용될 수 있는 영역에서의 문자 인식을 위해 인식 문자 집합과 대표 문자를 도입하였다. 여러 가지 조합의 언어 집합에 따른 소규모 인식기를 계층적으로 조합하여 인식 결과의 정확성을 높이고 시간 비용을 줄일 수 있는 효율적인 인식기 구조를 제안하였다. 그리고 학습 성능이 우수한 Delta-bar-delta 알고리즘을 이용하여 개별 소규모 인식기를 학습한 다음 다양한 개별 문자를 대상으로 그 인식 성능을 살펴본 결과 99%의 인식률을 획득함으로써 혼용 언어 문자 인식의 효율성과 신뢰성을 증명하였다.

• 한국반도체및디스플레이장비학회:학술대회논문집
• /
• 한국반도체및디스플레이장비학회 2005년도 추계 학술대회
• /
• pp.110-123
• /
• 2005

This paper proposes an intelligent method for the optimal load distribution of two cooperating robots(TCRs) using fuzzy logic. The proposed scheme requires the knowledge of the robots' dynamics, which in turn depend upon the characteristics of large flat panel displays(LFPDs) carried by the TCRs. However, the dynamic properties of the LFPD are not known exactly, so that the dynamics of the robots, and hence the required joint torque, must be calculated for nominal set of the LFPD characteristics. The force of the TCRs is an important factor in carrying the LFPD. It is divided into external force and internal force. In general , the effects of the internal force of the TCRs are not considered in performing the load distribution in terms of optimal time, but they are essential in optimal trajectory planning: if they are not taken into consideration, the optimal scheme is no longer fitting. To alleviate this deficiency, we present an algorithm for finding the internal-force factors for the TCRs in terms of optimal time. The effectiveness of the proposed system is demonstrated by computer simulations using two three-joint planner robot manipulators.