자동 주차 지원 시스템에 대한 사용자 감성 평가에 관한 연구

전재석(Jaeseok Jeon),문희석(Heeseok Moon),곽수진(Sujin Kwag) 한국자동차공학회 2012 한국자동차공학회 부문종합 학술대회 Vol.2012 No.5

In this paper, we described about evaluation of human sensibility using automatic parking assistance system. The perpendicular parking and parallel parking have been carried out as a user test and subjects are classified as beginning drivers, drivers with less than 1 year experience and over 3 years experience. As a result, parking duration of beginning drivers and drivers with less than 1 year experience who use automatic parking assistance system is similar to drivers with over 3 years experience. However error occurred according to sensor position and distance between vehicle and parking space. And also it occurred that the vehicle leaves from parking line or does not recognize the parking space. Therefore, if we improve its completeness by compensating problems that came up from this evaluation and distribute the automatic parking assistance system, it is expected that the automatic parking assistance system is to help driver providing convenience of parking.

실내 자동 주차 서비스를 위한 측위 기술과 표준화 동향 분석

문재영,배일,김시호 한국차세대컴퓨팅학회 2015 한국차세대컴퓨팅학회 논문지 Vol.11 No.1

실내 공간에서 자동 주차 서비스를 위한 측위기술과 표준화 동향을 분석하였다. 실내공간에 최소한의 인프라를 구축 하고 센서와 지능형 알고리듬을 지원하는 장치가 장착된 자동차로 서비스를 실시하는 모델과 일반자동차에 최소한 의 센서와 액추에이터를 장착하고 스마트 인프라 환경을 구축하는 방식에 대해서 비교하였다. 현재 전 세계적으로 자율주행 자동차에 대한 활발한 연구와 더불어 실내공간에서의 주행을 위한 표준화와 실내 공간에 대한 표준화가 진 행되고 있는데, 인프라와 자동차의 지능화 수준을 모두 고려하여 실내 자동 발렛 파킹 서비스를 개발하는 것이 매우 중요하며, 본 논문에서는 실내 자동 주차를 위하여 필요한 스마트 자동차 측위 센서의 요구 사양과 고성능 센서를 장착하지 않은 일반자동차에게 자동 주차 서비스를 제공하기 위한 인프라의 구성 요건을 비교하고 분석하였다. We investigated positioning technology and standardization activity for an indoor autonomous valet parking service. There might be two potential system architecture for indoor autonomous valet parking service, excepts for the current standardized cooperative system between infrastructure and vehicles with on-board sensors and equipment. One is using smart vehicles with minimum required infrastructure, another model is a smart infrastructure with general vehicles with low grade sensors and equipments. There are very active development of autonomous vehicle technologies and standardization for indoor navigation and parking service. We evaluated trade-off between two potential solutions either smart infra structure based service or smart car based service.

3D 라이다 기반 훼손 주차선 인식 방법에 관한 연구

이태호(Taeho Lee),김영춘(Youngchoon Kim),정도현(Dohyun Jung),이영우(Youngwoo Lee),김문식(Moonsik Kim) 한국자동차공학회 2023 한국자동차공학회 학술대회 및 전시회 Vol.2023 No.11

As autonomous driving technology advances, various autonomous driving technologies such as HDA (Highway Driving Assist) and LKA(Lane Keeping Assist) systems are being developed and commercialized. In addition, the parking assist system have recently been actively developed for the convenience of driver who is not familiar with driving. Therefore, parking space or parking line recognition technology is essential for accurate and safe automatic parking. The purpose of this paper is to detect and recover the damaged parking lines through parking line recognition using LiDAR, which is more robust to illumination and environmental changes than other sensors such as a camera and ultrasonic sensors.

자율주행차량의 자동주차를 위한 경로계획 시스템 개발

김종민(Jongmin Kim),임경일(Kyungil Lim),김정하(Jungha Kim) 한국자동차공학회 2015 한국자동차공학회 학술대회 및 전시회 Vol.2015 No.11

In this paper, static obstacles avoidance path planning and auto-parking path planning algorithm of autonomous vehicle in parking area are proposed. The path planning technologies for auto-parking in limited parking space have been achieved but these don’t be considered about the driving environment of parking area. As a mission in parking area, the situation that obstacles appeared can be caused and then the vehicle will have to avoid the obstacles for continuously detecting a empty parking lot. In this research, for obstacles avoidance using point data from laser scanner voronoi field is used . As a map, generated voronoi field is used to search the path via the A* algorithm and finally the autonomous vehicle will do collision free driving along the generated path. The driving goal point is a parking lot. Reeds-Shepp curve consist of arcs that have minimum turning radius. this curve algorithm is used to generate auto-parking path from vehicle’s pose to a parking lot.

자동 발렛 파킹을 위한 테스트 플랫폼 설계 및 주행 검증

우훈제(HoonJe Woo),손성효(SungHyo Son),문희창(HeeChang Moon),성경복(KyungBok Sung),김정하(JungHa Kim) 한국자동차공학회 2011 한국자동차공학회 부문종합 학술대회 Vol.2011 No.5

This paper introduces an automated valet parking system (AVP) which applies an autonomous driving concept into the current parking assistant system (PAS). The present commercial PAS technology is limited into vehicle. It means vehicle only senses and controls by and for itself to assist the parking. Therefore, the present PAS is restricted to simple parking events. But AVP includes wider parking events and planning because it uses infra-sensor network as well as vehicle sensor. For the realization of AVP, the commercial steering system of a compact vehicle was modified into steer-by-wire structure and various sensors like LRF (Long Range Finder) and camera were installed in a parking area. And local & global server decides where and when the vehicle can go and park in the testing area after recognized the status of environment and vehicle from those sensors. GPS solution was used to validate the AVP performance. More various parking situations, vehicles and obstacles will be considered in the next research stages based on these results. And we expect this AVP solution with more intelligent vehicles can be applied in a big parking lot like a market, an amusement park, etc.

상용차 기반에 대한 주차보조시스템 사용자 감성 평가

전재석(Jaeseok Jeon),박현배(Hyunbae Park),문희석(Heeseok Moon),곽수진(Sujin Kwag) 한국자동차공학회 2013 한국자동차공학회 부문종합 학술대회 Vol.2013 No.5

In this paper, we described about evaluation of human sensibility using park assist system of the commercial vehicle. The perpendicular parking and parallel parking have been carried out as a user test and subjects are classified as beginning drivers, drivers with less than 1 year experience and over 3 years experience. As a result, parking duration of beginning drivers and drivers with less than 1 year experience who use automatic parking assistance system is similar to drivers with over 3 years experience. However error occurred according to sensor position and distance between vehicle and parking space. And also it occurred that the vehicle leaves from parking line or does not recognize the parking space. Therefore, if we improve its completeness by compensating problems that came up from this evaluation and distribute the automatic parking assistance system, it is expected that the park assistance system is to help driver providing convenience of parking.

무인 자율주차 시스템 구현을 위한 기반기술 연구

전재한(Jaehan Jeon),최아라(Ara Choi),박성훈(Sunghoon Park),정태영(Taeyoung Chung) 한국자동차공학회 2014 한국자동차공학회 학술대회 및 전시회 Vol.2014 No.11

As an autonomous driving technology is the future of on-road driving, an unmanned valet parking system is one of a key technology to realize door to door autonomous vehicle. When an autonomous vehicle arrive its destination, the driver steps out of the car and pushes button on the smart phone, and then the vehicle autonomously parking in without any anxiety of user. Similarly, the vehicle gets out from the parking lot at right time and right position for user. We mainly focused on a vehicle actuator control, path following control for parking slot detection, parking maneuver control with shift-by-wire system, and smart phone interface between the user and vehicle. As the localization technology of a vehicle at the indoor or outdoor parking areas is most important and difficult problem, we applied precise position information from the DGPS for preliminary implementation of the system.

자율 주차 시스템의 직각 주차를 위한 조향 제어 알고리즘

이한승(Hanseung Lee),김동욱(Dongwook Kim),이경수(Kyongsu Yi) 한국자동차공학회 2011 한국자동차공학회 부문종합 학술대회 Vol.2011 No.5

This paper describes a steering control algorithm of autonomous parking vehicle for perpendicular parking. The proposed control algorithm consists of a desired path generation, a path tracking controller and steering angle decision. The desired path is generated by consisting of arcs and lines when starting point and target point are given. A path tracking controller is designed based on linear quadratic optimal control method using 2 DOF bicycle model. The path tracking controller determines a front steering angle in order to track the desired path determined by the path generation algorithm while vehicle moves forward to approach to parking space. Parking space and updated target point is defined by using sonar sensors when vehicle approaches to parking space. Steering control algorithm calculates a front steering angle in order to enter parking space backward and determines feedback steering angle when collision is predicted by sonar sensor data. The performance of proposed control algorithm has been verified using computer simulations.

Convolutional Neural Network를 이용한 주차 차량 자세 추정

서주원(Ju Won Seo),김대정(Dae Jung Kim),정정주(Chung Choo Chung) 한국자동차공학회 2020 한국자동차공학회 부문종합 학술대회 Vol.2020 No.7

This paper proposes a technique based on Convolutional Neural Network(CNN) using rear view camera images to estimate the vehicle pose for the target point when parking. Identifying the vehicle’s pose for the target point in autonomous vehicles is a key technology in the automatic parking system. Generally, existing algorithm is used to recognize parking spaces with rear view camera images or rear view camera images and ultrasonic sensors to identify the vehicle’s poses for the target point. In this paper, we present feasibility of the network learned by CNN as AVM images to find out the pose of the vehicle simply. We show the performance that was observed when confirming the root mean squared error of the actual values and the predicted values.

V2X 통신 기반 효율적 무인 주차 유도 시스템 고안

김민구(Mingu Kim),이동훈(Donghun Lee),김정하(Jungha Kim) 한국자동차공학회 2018 한국자동차공학회 부문종합 학술대회 Vol.2018 No.6

This system is to search the shortest-distance path from autonomous car by receiving vacant space information for autonomous car to park over V2X communication. This eliminates the need of lots of time and fuel consumption wandering around parking spaces. The composition of this paper is as follows. In Chapter 2, we explain camera system to extract parking spaces. In Chapter 3, the empty spaces are sent to an autonomous car over a V2X communication. In Chapter 4, we set the closest parking spot from the location of the car. Based on the target point, A <SUP>*</SUP>, a shortest-distance search algorithm, is applied to create a route that can be driven to a parking space. Chapter 5 presents the results of the experiment and we draw conclusion at chapter 6.