• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제9권4호
• /
• pp.275-280
• /
• 2009

A Genetic Algorithm (GA) is a kind of search techniques used to find exact or approximate solutions to optimization and searching problems. This paper discusses the design of a genetic algorithm-based intelligent parking system. This is a search strategy based on the model of evolution to solve the problem of parking systems. A genetic algorithm for an optimal solution is used to find a series of optimal angles of the moving vehicle at a parking space autonomously. This algorithm makes the planning simpler and the movement more effective. At last we present some simulation results.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제22권12호
• /
• pp.654-662
• /
• 2016

본 논문에서는 가까운 미래에 접하게 될 무인 자율 주행 차량의 주차장에서의 주차 방법과 알고리즘에 대해 살펴보았다. 가장 가까운 주차 장소는 어디이며 어떤 경로를 통해 그 위치로 이동할 것인가 등이 자율주행 차량의 주차를 위한 정보일 것이다. 자율주행 차량의 주차에 적합한 주차장의 구조와 형태를 알아내는 것도 중요한 문제점이 될 것이다. 본 논문에서는 주차장을 그래프로 모델링한 후 중앙제어 시스템을 통해 각 자율주행 차량이 근접한 주차장소로 이동할 수 있도록 안내하는 초기 해결 방법을 제시한다. 몇 가지 구조의 주차장을 모델링한 실험을 통해 본 논문에서 제안한 초기 해결방법이 자율주행차량 주차에 효과적인 안내 시스템이 될 수 있음을 확인하였다.

• ETRI Journal
• /
• 제36권6호
• /
• pp.968-978
• /
• 2014

Autonomous vehicle technology based on information technology and software will lead the automotive industry in the near future. Vehicle localization technology is a core expertise geared toward developing autonomous vehicles and will provide location information for control and decision. This paper proposes an effective vision-based localization technology to be applied to autonomous vehicles. In particular, the proposed technology makes use of numerical maps that are widely used in the field of geographic information systems and that have already been built in advance. Optimum vehicle ego-motion estimation and road marking feature extraction techniques are adopted and then combined by an extended Kalman filter and particle filter to make up the localization technology. The implementation results of this paper show remarkable results; namely, an 18 ms mean processing time and 10 cm location error. In addition, autonomous driving and parking are successfully completed with an unmanned vehicle within a $300m{\times}500m$ space.

• 전자공학회논문지
• /
• 제51권10호
• /
• pp.180-189
• /
• 2014

본 논문은 무인 자동차의 자율주차 알고리즘 개발을 위하여 이 문제를 차량형 이동로봇의 위치-자세 안정화 (posture regulation) 문제로 치환하고 이렇게 치환된 문제를 해결할 수 있는 차량형 이동로봇을 위한 도킹 포메이션과 궤환선형화 제어기법을 제안한다. 경로생성 기법과 최적화 기법을 기반으로 하는 기존의 연구결과들에 비해, 본 논문에서 제안하는 자율주차 알고리즘은 자율주차 문제를 도킹 포메이션 기반의 위치-자세 안정화 문제로 치환하고 입력제한을 고려할 수 있는 궤환선형화 제어기법을 적용함으로써 적은 연산량과 낮은 성능의 프로세서만으로도 무인 자동차의 자율 주차가 가능하도록 한다. 본 논문에서 제안된 차량형 이동로봇의 도킹 포메이션과 궤환선형화 제어기법의 유효성은 안정성 해석을 통하여 보이고, 본 논문에서 제안하는 자율주차 알고리즘의 성능은 모의실험 및 실제 로봇을 통한 실험결과를 통하여 검증한다.

• 로봇학회논문지
• /
• 제14권3호
• /
• pp.170-178
• /
• 2019

This paper proposes a parking space detection method for autonomous parking by using the Around View Monitor (AVM) image and Light Detection and Ranging (LIDAR) sensor fusion. This method consists of removing obstacles except for the parking line, detecting the parking line, and template matching method to detect the parking space location information in the parking lot. In order to remove the obstacles, we correct and converge LIDAR information considering the distortion phenomenon in AVM image. Based on the assumption that the obstacles are removed, the line filter that reflects the thickness of the parking line and the improved radon transformation are applied to detect the parking line clearly. The parking space location information is detected by applying template matching with the modified parking space template and the detected parking lines are used to return location information of parking space. Finally, we propose a novel parking space detection system that returns relative distance and relative angle from the current vehicle to the parking space.

• 한국인터넷방송통신학회논문지
• /
• 제22권6호
• /
• pp.75-81
• /
• 2022

주차 공간의 부족함을 획기적으로 해결할 수 있는 자율주행 자동차는 심층 강화 학습을 통해 큰 발전을 이루고 있다. 심층 강화 학습에는 활성화 함수가 사용되는데, 그동안 다양한 활성화 함수가 제안되어 왔으나 적용 환경에 따라 그 성능 편차가 심했다. 따라서 환경에 따라 최적의 활성화 함수를 찾는 것이 효과적인 학습을 위해 중요하다. 본 논문은 자율주행 자동차가 주차를 학습하기 위해 심층 강화 학습을 사용할 때 어떤 활성화 함수를 사용하는 것이 가장 효과적인지 비교 평가하기 위해 강화 학습에 주로 사용되는 12개의 함수를 분석하였다. 이를 위해 성능 평가 환경을 구축하고 각 활성화 함수의 평균 보상을 성공률, 에피소드 길이, 자동차 속도와 비교하였다. 그 결과 가장 높은 보상은 GELU를 사용한 경우였고, ELU는 가장 낮았다. 두 활성화 함수의 보상 차이는 35.2%였다.

• 반도체디스플레이기술학회지
• /
• 제10권2호
• /
• pp.31-38
• /
• 2011

This paper introduces a video based traffic monitoring system for detecting vehicles and obstacles on the road. To segment moving objects from image sequence, we adopt the background subtraction algorithm based on the local binary patterns (LBP). Recently, LBP based texture analysis techniques are becoming popular tools for various machine vision applications such as face recognition, object classification and so on. In this paper, we adopt an extension of LBP, called the Diagonal LBP (DLBP), to handle the background subtraction problem arise in vision-based autonomous parking systems. It reduces the code length of LBP by half and improves the computation complexity drastically. An edge based shadow removal and blob merging procedure are also applied to the foreground blobs, and a pose estimation technique is utilized for calculating the position and heading angle of the moving object precisely. Experimental results revealed that our system works well for real-time vehicle localization and tracking applications.

• 로봇학회논문지
• /
• 제10권1호
• /
• pp.33-41
• /
• 2015

Recent developments in robotics and intelligent vehicle area, bring interests of people in an autonomous driving ability and advanced driving assistance system. Especially fully automatic parking ability is one of the key issues of intelligent vehicles, and accurate parked vehicles detection is essential for this issue. In previous researches, many types of sensors are used for detecting vehicles, 2D LiDAR is popular since it offers accurate range information without preprocessing. The L shape feature is most popular 2D feature for vehicle detection, however it has an ambiguity on different objects such as building, bushes and this occurs misdetection problem. Therefore we propose the accurate vehicle detection method by using a 3D complete vehicle model in 3D point clouds acquired from front inclined 2D LiDAR. The proposed method is decomposed into two steps: vehicle candidate extraction, vehicle detection. By combination of L shape feature and point clouds segmentation, we extract the objects which are highly related to vehicles and apply 3D model to detect vehicles accurately. The method guarantees high detection performance and gives plentiful information for autonomous parking. To evaluate the method, we use various parking situation in complex urban scene data. Experimental results shows the qualitative and quantitative performance efficiently.

• 로봇학회논문지
• /
• 제12권2호
• /
• pp.152-160
• /
• 2017

Recent studies on automatic parking have actively adopted the technology developed for mobile robots. Among them, the path planning scheme plans a route for a vehicle to reach a target parking position while satisfying the kinematic constraints of the vehicle. However, previous methods require a large amount of computation and/or cannot be easily applied to different environmental conditions. Therefore, there is a need for a path planning scheme that is fast, efficient, and versatile. In this study, we use a multi-dimensional path grid map to solve the above problem. This multi-dimensional path grid map contains a route which has taken a vehicle's kinematic constraints into account; it can be used with the $A^*$ algorithm to plan an efficient path. The proposed method was verified using Prescan which is a simulation program based on MATLAB. It is shown that the proposed scheme can successfully be applied to both parallel and vertical parking in an efficient manner.

• 로봇학회논문지
• /
• 제16권3호
• /
• pp.250-259
• /
• 2021

Path planning is one of the important technologies for automated parking. It requires to plan a collision-free path considering the vehicle's kinematic constraints such as minimum turning radius or steering velocity. In a complex parking lot, Rapidly-exploring Random Tree^* (RRT^*) can be used for planning a parking path, and Reeds-Shepp or Hybrid Curvature can be applied as a tree-extension method to consider the vehicle's constraints. In this case, each of these methods may affect the computation time of planning the parking path, path-tracking error, and parking success rate. Therefore, in this study, we conduct comparative analysis of two tree-extension functions: Reeds-Shepp (RS) and Hybrid Curvature (HC), and show that HC is a more appropriate tree-extension function for parking path planning. The differences between the two functions are introduced, and their performances are compared by applying them with RRT^*. They are tested at various parking scenarios in simulation, and their advantages and disadvantages are discussed by computation time, cross-track error while tracking the path, parking success rate, and alignment error at the target parking spot. These results show that HC generates the parking path that an autonomous vehicle can track without collisions and HC allows the vehicle to park with lower alignment error than those of RS.