In this paper, we design a basic algorithm enabling recognition of surrounding environment and collision avoidance among elemental technologies for autonomous driving, also applies sensor theoretical data and actual road performance to robo-racing system based on experimental data obtained through driving tests to enable sophisticated collision avoidance. For this study, a commercial autonomous driving patform(ERP-42), LiDAR and GPS sensors were used to implement efficient comunication systems and autonomous driving algorithms between each module.

PURPOSES : Recently, increasing number of local governments are introducing on-demand public transportation service in real time to improve the management efficiency of public transportation. In preparation for the autonomous driving era, the “autonomous public transportation mobility on-demand service in real time” is being developed in the public transportation sector to introduce on-demand public transportation. For this service to become the public transportation of the future, it must receive publicity. Therefore, in this study, indicators were selected to evaluate the publicity of the autonomous public transportation mobility on-demand service in real time, and a survey was conducted among the general public to examine the validity of the indicators. METHODS : To secure the publicity of on-demand public transportation in real time, the goal of the service was first set. Second, the keywords of the service were analyzed to define the publicity requirements of this service. Based on the analyzed keywords and definition of publicity, service indicator types were classified, and the indicators were defined by type. A user satisfaction survey was conducted on the final selected indicators to improve the degree of completion of indicator development. The user survey was conducted by presenting selected publicity indicators to respondents responding on a five-point scale to determine whether each indicator could satisfactorily evaluate publicity. RESULTS : When examining various previous research cases and the contents required for autonomous public transportation mobility on-demand service in real time, the required items of publicity indicators were found to be “safety” in terms of “autonomous driving” and “convenience” in terms of “demand response.” Publicity indicators were developed according to these three items. Thirty-one indicators were developed, and a satisfaction survey was conducted on the general public for each indicator. In the survey, most of the indicators scored 3.5 points or higher, indicating that the indicators were generally well defined. Users gave the highest score to “fairness” among the three items, and “reasonable fairness” was found to be a necessary item as a publicity indicator. CONCLUSIONS : In this study, evaluation indicators were selected to secure the publicity of autonomous public transportation mobility on-demand service in real time, and a satisfaction survey was conducted for each indicator. Most of the indicators showed a score of 3.5 or higher, indicating that they were generally well defined. However, this study has a limitation in that it surveys the general population. In future, experts should be included in the survey to increase the degree of completeness of the public indicators.

PURPOSES : An automated driving guidance framework was developed for automated vehicles based on cooperation between infrastructure and automated vehicles. The proposed automated driving guidance framework is assumed to function only when an automated vehicle encounters situations in which it cannot safely pass through without cooperation with the infrastructure. METHODS : A four-step concept of automated driving guidance levels was employed, and the decision criteria, such as moving object, event, and externality, were defined as the criteria for determining the automated driving guidance level. The judgment criteria of each stage and procedure for determining the autonomous driving guidance level were determined based on successive judgments, and the proposed automated driving guidance framework was designed based on an expert survey. The survey was aimed at experts with experience related to automated driving system research or technology development. RESULTS : The resulting framework shows the steps and criteria for determining whether automated driving guidance is required under a specific situation and what the guidance should be. CONCLUSIONS : The proposed automated driving guidance framework is designed to function only when an automated vehicle encounters situations in which it cannot safely pass through without cooperation with the infrastructure.

PURPOSES : The purpose of this study was to quantitatively evaluate the variability of LiDAR performance indicators, such as intensity and Number of Point Cloud(NPC), according to various environmental factors and material characteristics. METHODS : To consider the material characteristics of road safety facilities, various materials (Reference Material(RM), reflective sheet, matte sheet, granite, plastic, and rubber) were used in a darkroom, and the performance indicators of LiDAR were repeatedly measured in terms of changes in the measurement distance, rainfall, and angle of observation. RESULTS : In the case of standard reflective materials, the intensity measurement value decreased as the measurement distance and rainfall increased. The NPC showed a tendency to decrease as the measurement distance increased, regardless of rainfall intensity. For materials with high-intensity values, it was found that rainfall intensity and color had negligible effect on the change in intensity compared with the measurement distance. However, for materials with low-intensity values, it was found that the measurement distance, rainfall intensity, and color all had a significant effect on the change in intensity. CONCLUSIONS : For materials with high-intensity values, it was found that rainfall and color had negligible effect on change in intensity compared with the measurement distance. However, for materials with low-intensity values, the measurement distance, rainfall, and color all had a significant effect on the change in intensity value.

Level 3 driving, which enters full-fledged autonomous driving, is becoming more common. And research on autonomous driving is growing rapidly. Therefore, there is a need for a hardware platform to implement autonomous driving, but the actual vehicle price is too high and the implementation conditions are very limited, so its usability is inevitably reduced. In this study, by providing an easy-to-access hardware platform for anyone to support autonomous driving research, compatibility with software platforms can be increased. As a result of this study, it is possible to conduct hardware platform and software platform education at the same time. Through this, trial and error due to errors in each of the two platforms can be reduced. In addition, various sensors, such as camera sensors and LiDAR sensors, were installed on the hardware platform, and a hardware platform capable of testing autonomous driving for education and R&D was conducted not only outdoors but also indoors with little external environmental impact.

최근 급격한 변화를 겪고 있는 자율주행 자동차 분야의 미래 기술 및 시장 전 망 예측에 대한 요구와 관심이 집중되고 있다. 자동차 산업의 특성상, 복합적 요인의 상관관 계가 미치는 영향력이 크고 요인 간의 복잡도가 높으므로, 체계적인 미래 예측 방법론 적용 을 통한 미래 전망분석 및 전략 수립이 시급하다. 본 연구에서는 자동차 분야에 적합한 미래 예측 방법론 중 필드 변칙 완화기법(Field Anomaly Relaxation)과 다중관점 개념 기법 (Multiple Perspective Concept)을 복합적으로 적용하여, 자율주행 자동차 분야의 핵심기술 및 산업 동향에 관한 미래 시나리오들을 개발하여 실증하였다. 도출된 3개의 시나리오는 전 문가 평가 체크리스트를 통하여 타당성을 검증하였다. 본 연구 결과는 자율주행 자동차 산업 과 같은 다양한 변동성이 존재하는 분야의 미래 예측 방법 중 한 가지로 적용될 수 있다는 점에 의의가 있다.

PURPOSES : This study aimed to develop data conversion of NGII HD maps to OpenDRIVE format for virtual road implementation for autonomous-driving verification. METHODS : A method of defining the reference line of OpenDRIVE on the centerline of an NGII HD map is proposed. According to the construction characteristics of the NGII HD map, the optimal conversion method through parametric cubic polynomials was used in the form of piecewise and clamped cubic polynomials. RESULTS : The study focused on curved roads that may cause problems when converting HD map data into OpenDRIVE formats. As a result of data conversion, a reference line was defined to precisely follow the alignment of NGII HD maps drawn based on MMS data, and a lively virtual road was reproduced through road lane width and lane expression. CONCLUSIONS : A virtual road in the same environment as a real road, which is one of the important factors in verifying autonomous driving technology through virtual driving simulation, was constructed. The piecewise-polynomial normal was 0.008 m on average, and as a result of calculating the distance between the endpoint coordinates of the road object and the endpoint coordinates of the converted road object on the NGII HD map, the difference between the two points was 0.163 m on average. The clamped cubic polynomials normal was observed to be an average of 0.170 m.

자율주행 시물레이터는 자율 주행을 시험하고 검증하는 일에 있어 현실에 비해 높은 비용 절감의 효과를 가 지고 오지만 높은 컴퓨터 연산량에 의해 많은 하드웨어 기기를 요구하게 된다. 게임을 이용하여 자율 주행에 필요한 학습 데이터를 획득하는 경우도 있다. 게임은 저비용 시뮬레이터로 활용되고 있지만 게임 외적인 특정 상황을 모의하기에도, 필요한 데이터 획득에도 제한적이다. 또 다른 방법으로 게임 엔진을 통한 가상 환경 모 의 연구가 수행되고 있다. 하지만 게임 엔진에서는 사용자가 직접 필요한 모델링을 해줘야 하기 때문에 개발 비용이 크게 작용된다. 특히, 3D LIDAR는 360도로 Ray를 쏴서 정밀 거리를 최소 10Hz 이내의 실시간 획득이 필요하다. 실시간으로 3D LIDAR 데이터를 획득하는 것은 GPU(Graphics Processing Unit) 사용량이 많은 작업 이기 때문에, 저비용 시뮬레이터를 위해서는 저비용 3D LIDAR 모의가 필요하다. 본 논문에서는 낮은 컴퓨터 연산을 사용하는 C++ 기반 3D LIDAR 모의 프레임 워크를 제안한다. 제안된 3D LIDAR는 다수의 언덕으로 이 루어진 비포장 Map에서 성능을 검증 하였으며, 성능 검증을 의해 본 논문에서 생성된 3D LIDAR로 간단한 LPP(Local Path Planning) 생성 방법도 소개한다. 제안된 3D LIDAR 프레임 워크는 저비용 실시간 모의가 필요 한 자율 주행 분야에 적극 활용되길 바란다.