• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.687-694
• /
• 2022

In this paper, we proposed an autonomous vehicle platform that delivers goods to a designated destination based on the SLAM (Simultaneous Localization and Mapping) map generated indoors by applying the Visual SLAM technology. To generate a SLAM map indoors, a depth camera for SLAM map generation was installed on the top of a small autonomous vehicle platform, and a tracking camera was installed for accurate location estimation in the SLAM map. In addition, a convolutional neural network (CNN) was used to recognize the label of the destination, and the driving algorithm was applied to accurately arrive at the destination. A prototype of an indoor delivery autonomous vehicle was manufactured, and the accuracy of the SLAM map was verified and a destination label recognition experiment was performed through CNN. As a result, the suitability of the autonomous driving vehicle implemented by increasing the label recognition success rate for indoor delivery purposes was verified.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.1080-1083
• /
• 2020

본 논문에서는 구면 파노라마를 기반으로 하는 SLAM 시스템을 제안한다. Vision SLAM은 촬영하는 시야각이 넓을수록 적은 프레임으로도 주변을 빠르게 파악할 수 있고, 많은 양의 주변 데이터를 이용해 더욱 안정적인 추정이 가능하다. 구면 파노라마 비디오는 가장 화각이 넓은 영상으로, 모든 방향을 활용할 수 있기 때문에 Fisheye 영상보다 더욱 빠르게 3D 맵을 확장해나갈 수 있다. 기존의 시스템 중 Fisheye 영상을 기반으로 하는 시스템은 전면 광각만을 수용할 수 있기 때문에 구면 파노라마를 입력으로 하는 경우보다 적용 범위가 줄어들게 된다. 본 논문에서는 기존에 Fisheye 비디오를 기반으로 하는 SLAM 시스템을 구면 파노라마의 영역으로 확장하는 방법을 제안한다. 제안 방법은 카메라의 투영 모델이 요구하는 파라미터를 정확히 계산하고, Dual Fisheye Model을 통해 모든 시야각을 손실 없이 활용한다.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.10
• /
• pp.907-914
• /
• 2013

A FastSLAM is an algorithm for SLAM (Simultaneous Localization and Mapping) using a Rao-Blackwellized particle filter and its performance is known to degenerate over time due to the loss of particle diversity, mainly caused by the particle depletion problem in the resampling phase. In this paper, the GeSPIR (Geographically Stratified Particle Information-based Resampling) technique is proposed to solve the particle depletion problem. The proposed algorithm consists of the following four steps : the first step involves the grouping of particles divided into K regions, the second obtaining the normal weight of each region, the third specifying the protected areas, and the fourth resampling using regional equalization weight. Simulations show that the proposed algorithm obtains lower RMS errors in both robot and feature positions than the conventional FastSLAM algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.5
• /
• pp.451-457
• /
• 1991

Four computational algorithms are discussed and compared in terms of complexity, required memory, and the number of channels which calculate the blocking probabilities in the two-dimensional multi-slot connection traffic. The overflow and underflow problems can be circumvented, and thus blocking probabilities can be calculated even up to 10000 channels, by the proposed last algorithm. This algorithm is utilized in calculating the blocking probabilities for I-slot and 6-slots calls. And the results of the simulation by the SLAM-II are compared with those of the analytic calculation.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.6
• /
• pp.1029-1040
• /
• 2011

In this paper we propose an intelligent navigation algorithm for real world problem which can build a map without localization. Proposed algorithm operates online and furthermore does not require many memories for applying real world problem. After applying proposed algorithm to toy and huge data set, it does not require to calculate a whole eigenspace and need less memory compared to existing algorithm. Thus we can obtain that proposed algorithm is suitable for real world mobile navigation algorithm.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.1
• /
• pp.189-198
• /
• 2019

In recent years, visual-inertial odometry(VIO) algorithms have been extensively studied for the indoor/urban environments because it is more robust to dynamic scenes and environment changes. In this paper, we propose loosely coupled(LC) VIO algorithm that utilizes the velocity vectors from both visual odometry(VO) and inertial measurement unit(IMU) as a filter measurement of Extended Kalman filter. Our approach improves the estimation performance of a filter without adding extra sensors while maintaining simple integration framework, which treats VO as a black box. For the VO algorithm, we employed a fundamental part of the ORB-SLAM, which uses ORB features. We performed an outdoor experiment using an RGB-D camera to evaluate the accuracy of the presented algorithm. Also, we evaluated our algorithm with the public dataset to compare with other visual navigation systems.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.129-132
• /
• 2019

본 기술의 발달에 따라 실내 공간이 점차 대형화되면서 실내공간은 복잡해졌으며, 이로 인해 원하는 장소를 찾기가 어려워졌다. 4차 산업혁명에 힘입어 앞서 언급한 문제들을 해결하기 위해 실내 내비게이션을 도입하려는 시도가 활발히 이루어지고 있다. 실내 내비게이션의 기술들로는 Wi-Fi, Bluetooth, Beacon, RFID, UWB 등이 있지만, 실내 건물 구조 특성상 여러 장애물들에 의해 신호 정보의 오차가 심하여 사용하기에 어려움이 있다. 이러한 문제점을 해결하기 위해 스마트폰에 내장된 IMU 센서 및 카메라 센서를 이용하여 동시적 위치 인식 및 지도 작성을 하는 SLAM 알고리즘으로 실내 내비게이션을 구현하고, 사용자가 보다 쉽게 길을 찾을 수 있게 접근성이 높은 스마트폰과 AR을 이용하여 어플리케이션을 설계하였다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.3
• /
• pp.108-118
• /
• 2017

This paper presents experimental results of realtime sonar-based SLAM (simultaneous localization and mapping) using probability-based landmark-recognition. The sonar-based SLAM is used for navigation of underwater robot. Inertial sensor as IMU (Inertial Measurement Unit) and DVL (Doppler Velocity Log) and external information from sonar image processing are fused by Extended Kalman Filter (EKF) technique to get the navigation information. The vehicle location is estimated by inertial sensor data, and it is corrected by sonar data which provides relative position between the vehicle and the landmark on the bottom of the basin. For the verification of the proposed method, the experiments were performed in a basin environment using an underwater robot, yShark.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.10
• /
• pp.833-838
• /
• 2016

This paper presents a performance evaluation of various feature-initialization algorithms for forward-viewing mono-camera based simultaneous localization and mapping (SLAM), specifically in indoor environments. For mono-camera based SLAM, the position of feature points cannot be known from a single view; therefore, it should be estimated from a feature initialization method using multiple viewpoint measurements. The accuracy of the feature initialization method directly affects the accuracy of the SLAM system. In this study, four different feature initialization algorithms are evaluated in simulations, including linear triangulation; depth parameterized, linear triangulation; weighted nearest point triangulation; and particle filter based depth estimation algorithms. In the simulation, the virtual feature positions are estimated when the virtual robot, containing a virtual forward-viewing mono-camera, moves forward. The results show that the linear triangulation method provides the best results in terms of feature-position estimation accuracy and computational speed.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.85-86
• /
• 2008

로봇은 오도메터리 정보를 이용해 위치추정을 할 수 있다. 그러나 주행하는 동안 발생되는 슬립현상에 의해 오도메터러 정보만으로는 로봇의 정확한 위치추정을 할 수 없다. 정확한 위치추정을 위해서 관성센서를 이용하여 오도메터리 정보를 보정한 위치추정 방법이 있다. 실내 이동로봇에 적용하려면 관성센서는 소형이어야 하는데, 그에 따라 노이즈는 심해지고, 정확성도 낮아지는 문제가 있나. 그래서 현재까지는 이런 문제를 갖고 있는 관성센서를 실내 이동로봇의 위치추정의 정확성을 높이기 위해 비관성센서 또는 카메라 영상을 조합하는 연구들을 하고 있다. 그러나 이러한 연구들은 대부분 관성센서 성능 실험과 시뮬레이션에 결론을 내리고 있어 실제 실험에 따른 정확성을 확인할 수 없다. 또한 최근 영상 SIFT 알고리즘을 적용한 SLAM 연구에서도 나타나는 문제는 이동로봇의 위치추정의 부정확성이다. 따라서 본 논문은 SLAM에서 문제가 되는 위치추정의 부정확성을 최소화하기 위해 자이로와 가속도계를 이용하여 정학한 위치추정을 하고자 한다.