<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://purl.org/rss/1.0/" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <channel rdf:about="https://scholar.dgist.ac.kr/handle/20.500.11750/9959">
    <title>Repository Community: null</title>
    <link>https://scholar.dgist.ac.kr/handle/20.500.11750/9959</link>
    <description />
    <items>
      <rdf:Seq>
        <rdf:li rdf:resource="https://scholar.dgist.ac.kr/handle/20.500.11750/59085" />
        <rdf:li rdf:resource="https://scholar.dgist.ac.kr/handle/20.500.11750/58291" />
        <rdf:li rdf:resource="https://scholar.dgist.ac.kr/handle/20.500.11750/47887" />
        <rdf:li rdf:resource="https://scholar.dgist.ac.kr/handle/20.500.11750/46735" />
      </rdf:Seq>
    </items>
    <dc:date>2026-04-21T13:40:56Z</dc:date>
  </channel>
  <item rdf:about="https://scholar.dgist.ac.kr/handle/20.500.11750/59085">
    <title>원격조정 무인기의 자율충돌회피 알고리즘</title>
    <link>https://scholar.dgist.ac.kr/handle/20.500.11750/59085</link>
    <description>Title: 원격조정 무인기의 자율충돌회피 알고리즘
Author(s): 이진우; 김경대; 박상용
Abstract: 본 발명의 바람직한 일 실시예로서, 무인기에서 자율충돌회피를 수행하는 방법은 무인기에 기설치된 센서들에서 검출한 적어도 하나의 객체 각각과 상기 무인기 간의 상대거리 및 상대속도를 기초로 상기 적어도 하나의 객체 각각마다 가상의선을 생성하고, 가상의선 각각과 상기 무인기와의 최단거리가 최소정지거리 이하인 경우 해당 객체는 충돌가능성이 있다고 판단하는 단계; 충돌가능성이 있다고 판단된 객체에 대해서만 충돌회피값 벡터를 계산하는 단계; 및 상기 충돌회피값 벡터를 이용하여 충돌가능성이 있다고 판단된 객체들을 회피하는 단계;를 포함하는 것을 특징으로 한다.</description>
  </item>
  <item rdf:about="https://scholar.dgist.ac.kr/handle/20.500.11750/58291">
    <title>An RNN based Adaptive Hybrid Time Series Forecasting Model for Driving Data Prediction</title>
    <link>https://scholar.dgist.ac.kr/handle/20.500.11750/58291</link>
    <description>Title: An RNN based Adaptive Hybrid Time Series Forecasting Model for Driving Data Prediction
Author(s): Seo, Ji Hwan; Kim, Kyoung-Dae
Abstract: In this paper, we propose a hybrid time series forecasting model, named as the Adaptive Multivariate Exponential Smoothing - Recurrent Neural Networks (AMES-RNN), which enables accurate prediction for time series data with non-seasonal and additive trend characteristics. To enhance prediction performance, the optimal smoothing parameters of the Exponential Smoothing (ES) model are estimated and updated online. Here, the parameter estimation is performed through a deep learning-based regression model, and a method for training the regression model is presented. In addition, the prediction model utilizes future-implying information as additional input if available in order to improve prediction accuracy. The effectiveness of the proposed model was validated through multistep forecast tests using vehicle driving data that has non-seasonal and additive trend characteristics. The results show that the prediction accuracy of the proposed model was improved at least 23.0% compared to those of the existing prediction model. Additionally, we demonstrated that AMES-RNN requires low computational resources, making it feasible to perform online predictions.  © IEEE.</description>
    <dc:date>2025-02-28T15:00:00Z</dc:date>
  </item>
  <item rdf:about="https://scholar.dgist.ac.kr/handle/20.500.11750/47887">
    <title>An Accurate Path Tracking Algorithm for Autonomous Vehicles Based on Pure Pursuit with Systematically Designed Look-Ahead Distance and Sideslip Compensation</title>
    <link>https://scholar.dgist.ac.kr/handle/20.500.11750/47887</link>
    <description>Title: An Accurate Path Tracking Algorithm for Autonomous Vehicles Based on Pure Pursuit with Systematically Designed Look-Ahead Distance and Sideslip Compensation
Author(s): Seo, Ji Hwan; Youn, Sung Hoon; Kim, Jungeun; Kim, Kyoung-Dae
Abstract: Pure pursuit is still being utilized as a path tracking algorithm for autonomous vehicles due to its advantages, such as robustness and easy implementation. However, using an inappropriate look-ahead distance and ignoring the effects of dynamics deteriorate the path tracking performance of pure pursuit. To improve the tracking performance, we propose a pure pursuit-based path tracking algorithm that quickly reduces tracking error and considers the sideslip by dynamics. For fast tracking error reduction, a dynamic look-ahead distance is designed as a function of speed and path curvature by analyzing the tracking error change according to the look-ahead distance. In addition, to compensate for the sideslip effect, the desired steering angle is calculated using the sideslip integrated-pure pursuit geometry. Simulation results show that the proposed algorithm significantly reduced the tracking error compared to the classical pure pursuit at a maximum 70 km/h speed. Also, the proposed method outperformed existing improved pure pursuits.  © 2023 ICROS.</description>
    <dc:date>2023-10-18T15:00:00Z</dc:date>
  </item>
  <item rdf:about="https://scholar.dgist.ac.kr/handle/20.500.11750/46735">
    <title>자율 주행 차량 및 이의 조향 제어 방법</title>
    <link>https://scholar.dgist.ac.kr/handle/20.500.11750/46735</link>
    <description>Title: 자율 주행 차량 및 이의 조향 제어 방법
Author(s): 윤성훈; 김경대
Abstract: 자율 주행 차량이 개시된다. 본 자율 주행 차량은, 차량의 제동을 제어하는 제동 장치, 차량의 조향을 제어하는 조향 장치 및 프로세서를 포함하고, 프로세서는, 차량의 타이어에 작용하는 횡력과 선형 관계에 있는 타이어의 최대 사이드 슬립각을 결정하고, 최대 사이드 슬립각 및 차량의 이동 경로의 곡률에 따라 차량의 최대 속력을 결정하여, 차량이 최대 속력 이내의 속력으로 선회하도록 제동 장치를 제어하고, 차량의 선회 속력, 차량의 현재 위치 및 이동 경로의 목표 지점에 따라 타이어의 슬립각을 고려하여 차량의 조향각을 결정하여, 차량이 조향각으로 선회하도록 조향 장치를 제어한다.</description>
  </item>
</rdf:RDF>

