This study aimed to enhance the safety of autonomous bus services by systematically identifying safety-related factors and establishing priorities based on real-world operating environments. An expert survey was conducted using a autonomous bus currently operating in Pangyo Zero City as a case study. Building on the concept of the Operational Design Domain, a two-layer safety framework was developed consisting of four primary categories (Layer 1): physical infrastructure, operating conditions, communication environment, and weather conditions, and their corresponding detailed elements (Layer 2). A fuzzy Analytic Hierarchy Process(AHP) analysis revealed that physical infrastructure had the highest relative importance, with key safety-critical factors identified as intersection type, construction work zone, lane markings, and adverse weather. Subsequently, a strength, weakness, opportunity and threat (SWOT) analysis was employed to propose short-, mid-, and long-term strategic actions, including the enhancement of object recognition functions based on advanced camera sensor fusion, reinforcement of safety driver and onboard safety personnel systems, and establishment of infrastructure pre-notification systems for construction and maintenance activities. This study provides a quantitative prioritization of safety factors for autonomous bus services and links these findings to a practical technology and policy roadmap, contributing to the enhancement of safety and development of commercialization strategies for future autonomous public transportation services.

With the rapid transition to an aging society, the need for assistive technologies that promote independent indoor living for the elderly and mobility-impaired has become increasingly critical. This study proposes the development of a next-generation powered chair designed to support such independence by compensating for mobility limitations caused by natural aging. The proposed system incorporates two core functionalities: (1) an low seat-lifting mechanism capable of lowering the seat height to 7 cm, and (2) a short-range autonomous driving mode operable in both lowered and lifted positions. The low driving mode enables the user to approach low tables or desks and facilitates effortless transfer to and from low beds or sofas. In the lifted position, the system performs real-time obstacle detection and avoidance within a 3-meter range, preventing falls and collisions while expanding the user’s range of motion— for instance, by allowing access to higher objects or enabling eye-level communication with standing individuals. To realize these functions, a rack-and-pinion lifting mechanism is applied, along with a direct target-point designation method utilizing an LED pointer and a wiper-type screening approach for real-time obstacle avoidance. The design concept, implementation strategy, and validation plan are presented. This research contributes to enhancing the quality of life for elderly users by maximizing their remaining physical capabilities, while simultaneously reducing the physical and emotional burden on caregivers.

This paper presents the design and experimental validation of an intelligent tire alignment and lifting control system for an under-vehicle autonomous parking robot. The proposed system enables the robot to autonomously enter beneath a vehicle, recognize tire positions using a LiDAR-based sensing module, and perform precise lifting through a fork-type mechanism. A YOLOv8 instance segmentation algorithm is employed to detect tire regions from LiDAR point cloud data and estimate their geometric centers. The detected tire positions are then matched with a vehicle database to determine the correct alignment for lifting. Experiments were conducted on three different vehicle types under various surface conditions. The results show that the proposed system achieved a tire recognition accuracy exceeding 95%, a lifting success rate of 100%, and an average lifting operation time of 12.3 seconds. These results demonstrate the reliability and practicality of the proposed method for real-world autonomous parking applications.

선박 충돌 위험 평가는 항해 안전 확보를 위한 핵심 절차로, 실시간 의사결정 지원과 회피 기동 판단의 기초를 제공하며, 특히 자율운항선박 시대의 안전성 확보를 위해 그 중요성이 커지고 있다. 기존 연구들은 다양한 시나리오에 맞춘 지표와 모델을 제안해 왔으 나, 충돌 위험 변수와 변수 모델링 방법론 간의 구조적 연계에 대한 통합적 분석은 부족한 실정이다. 본 연구는 PRISMA 2020 지침에 따라 문헌 검토 절차를 체계화하고, 자율운항선박 기술개발이 본격적으로 진행된 2020년부터 2025년까지 발표된 관련 논문 중 75편을 선정하 여 선박 충돌 위험도 평가에 사용된 변수와 방법론을 각각 다섯 개의 범주로 분류하였다. 이를 통해 각 요소의 출현 빈도와 조합 경향을 통계적으로 분석하였으며, 변수-방법론 연계 행렬을 통해 연구 경향을 시각화하였다. 분석 결과, 대부분의 충돌 회피 모델이 여전히 운동 학 기반의 거리 중심 지표에 의존하고 있으며, 인간 요인이나 맥락 조건에 기반한 위험 평가는 상대적으로 적게 다루어졌다. 본 연구는 이러한 통합적 분석을 통해 향후 충돌 위험 평가 연구에서 확장되어야 할 변수와 기법의 방향을 제안하며, 제시한 5축 기반 분류체계는 향후 관련 연구자들이 연구 목적에 따라 적절한 변수와 방법론을 선택하고 설계하는데 유용한 개념적 틀로 활용될 수 있을 것으로 기대 한다.

원격운항자는 자율운항선박의 안전 운항에 대한 책임이 있는 사람으로 위급한 상황에 개입하여 원격조종을 수행하는 역할을 수행한다. 기존의 유인선 항해 환경에서는 단일 선박에 선장, 당직사관, 당직 조타수 등의 선교 인력이 동시에 승선하고 있어, 미숙한 선 박조종을 수행할 때에도 이를 지원이 가능한 조직으로 구성된다. 다수의 선박을 동시에 관리하는 원격운항자는 각 선박에 대한 조종 특 성에 대응이 필요하고, 위급한 상황에서만 상대적으로 짧은 시간 동안 개입해야 함에도 단일 선박에만 집중할 수 없는 방식으로서, 긴급 한 선박 조종에 대한 조직적 지원을 제공받기 어려울 것으로 예상된다. 본 연구에서는 원격운항자의 선박조종을 지원하기 위한 선박 조 종 행동 예측 모델 개발을 위한 기초연구로서, 숫자가 아닌 패턴을 활용한 행동 예측 방법을 제안한다. 제안하는 방법론은 선박 조종 데 이터를 패턴화하는 과정, 행동 패턴을 자기회귀 모델에 학습하여, 실제 선박에서의 개인의 조종 습관에 기반한 선박 조종 행동 예측 방법 을 제안하고, 원격운항자의 선박별 선박 조종을 지원하기 위한 선박 조종 행동 예측 모델 활용의 구체적인 예시를 제공한다. 검증된 패턴 을 활용한 행동 예측 방법은 원격운항자의 조종 특성 적응을 지원하는 모델의 개발에 활용될 수 있을 것으로 기대한다.

우리나라 농촌 인구의 고령화는 빠르게 진행되고 있으며, 2020년 기준 농업경영주의 평균 연령은 66.1세, 65세 이상 경영주 비율은 56%에 이른다. 2022년 기준 밭작물 전체의 기계화율은 63.3%인 반면, 정식 작업의 기계화율은 12.2%에 불과하며, 특히 고추 정식의 기계화율은 거의 0% 수준이다. 이러한 문제를 해결하기 위해 본 연구에서는 1회전 2식부 방식의 식부 메커니즘을 적용한 고추 정식기를 설계하였다. 식부 장치는 식부 프레임, 암(arm), 그리고 호퍼로 구성되며, 호퍼는 상사점에서 모종을 공급받아 하사점에서 식부한 후 모종과의 충돌 없이 복귀하도록 캠 메커니즘과 스윙 구조의 보조를 받는다. 호퍼는 하강 시 시계 방향의 반원 궤적을 따라 이동하고, 상승 시에는 타원 궤적으로 이동하며, 이때 상승 궤적은 사이클로이드 곡선과 높은 유사성을 보였고 주행속도가 증가할수록 그 유사성이 더욱 증가하였다. 재배 환경에 따른 주행속도는 하우스 재배에서 2.0 km/h(55.6 rpm), 노지 일반 재배에서 2.5 km/h(52.1 rpm), 노지 터널 재배에서 3.0 km/h(50.0 rpm)로 설정하였다. 식부 암의 회전속도를 60 rpm으로 고정한 조건에서, 주간거리별 최대 주행속도를 산출하였다. 주행속도와 주간거리가 증가할수록 식부 호퍼의 후퇴 면적은 감소하는 경향을 보였으며, 노지 터널 재배 조건(주간거리 500 mm, 주행속도 3.6 km/h)에서 가장 작은 후퇴 면적(10,560.0 mm²)이 나타났다. 본 연구는 1구 2식부 방식의 식부 메커니즘이 우수한 작동 성능을 가짐을 입증하였으며, 고추 정식기의 구조 및 구동 시스템 최적화를 위한 궤적 및 운전 조건 설정에 기초 자료를 제공한다.

This study analyzes and compares the determinants of accident severity between human-driven vehicle (HDV) and autonomous vehicle (AV) mixed environments using collision data from the California Department of Motor Vehicles . To address the high dimensionality and categorical complexity of the dataset, an XGBoost-based classification model was developed and the Shapley additive explanations method was employed to explain the contribution and directional influence of each explanatory variable. An undersampling and ensemble approach was utilized to mitigate class imbalances and enhance the model stability. The results revealed that in an HDV environment, driver perception and evasive responses were dominant factors influencing crash outcomes, with collision direction and relative speed significantly affecting the severity. By contrast, in the AV–HDV mixed environment, intersection conditions and complex driving contexts were associated with higher accident severity, thus demonstrating the current limitations of AV systems in managing unstructured traffic scenarios. These findings suggest that as AV deployment progresses, the key determinants of crash severity shift from human behavioral factors to system and environmental factors, thus providing empirical insights for future AV safety evaluations and policy frameworks.

This study aims to analyze the driving trajectories and lateral behavior characteristics of autonomous vehicles via simulation and to derive the implications for roadway infrastructure design based on the analysis results. A three-lane, one-way autonomous driving simulation environment was established to replicate the actual driving characteristics of autonomous vehicles. Roadways were designed based on domestic road design standards (MLTM, 2020), where horizontal, vertical, and cross-sectional alignments were incorporated and design speeds ranging from 20 to 120 km/h were considered. Curves with minimum radii of 15, 30, 60, …, 710 m were implemented. Autonomous vehicles were driven along these designed roads to obtain driving data, including position, speed, and steering angle. The lateral deviation from the lane center was calculated for each lane by measuring the distance between the front and rear wheels of the vehicle and the lane centerline. This approach allows for the analysis of lane-specific deviation characteristics under different speeds and curve radii, thus enabling a quantitative assessment of the lateral clearance required for autonomous-vehicle operation. Lateral deviation increased when vehicles entered or exited curves, particularly in outer lanes and at curves with changing turning directions. Passenger cars and heavy vehicles showed decreasing deviations within curves, whereas the deviations varied in straight sections. The lateral clearance increased with the design speed for passenger cars, whereas heavy vehicles generally exhibited limited clearance owing to their larger size and mirror widths, with slight increases above 100 km/h. Autonomous vehicles maintained lane centers outside curve entries and exit sections, thus indicating that variable lane widths can be safely implemented. The existing design standards based on human driving may be adapted for autonomous vehicles, thus enabling more efficient roadway use while maintaining stability.

This study aims to provide a basis for selecting the appropriate traffic-flow evaluation indicators by quantitatively analyzing the relative importance of such indicators in mixed traffic environments in which automated vehicles (AVs) and conventional vehicles coexist. As AV technology progresses and its adoption increases, establishing reliable evaluation criteria that accurately reflect the characteristics and performance of traffic systems under transitional conditions is crucial. Thus, approximately 40 domestic and international studies were reviewed in this study, from which 45 evaluation indicators were identified. These indicators were classified into three major categories: mobility, safety, and environment. Five frequently used and representative indicators were selected from each category based on the appearance frequency and relevance. An analytic hierarchy process survey was conducted with a group of transportation experts to derive the relative importance (weights) of both the major categories and individual indicators. The analysis revealed that safety (0.53676) was the most important category, followed by mobility (0.34795) and environment (0.11528). After combining the weights of the categories and sub-indicators, the top three indicators, i.e., time to collision (TTC), time exposed to TTC, and deceleration rate to avoid crashes, appeared to be safety related and associated directly with the collision risk. These findings suggest that, in the early stages of AV deployment, traffic evaluations should prioritize safety considerations over mobility or environmental factors to ensure the successful integration of AVs into existing traffic systems.

The automotive industry is rapidly shifting from hardware-focused design to Software Defined Vehicles (SDVs), where functions are flexibly updated through software. Embedded systems are central to this transition, ensuring real-time data processing and control across sensors, actuators, and controllers. Yet, most autonomous driving education and competitions have been designed for senior students, creating high entry barriers for early undergraduates. This study proposes an embedded practice-based education model for lower-year students, implemented through an autonomous driving competition. Arduino was adopted as an accessible embedded platform, enabling rapid prototyping and intuitive learning of sensor–controller–actuator integration. The curriculum was structured to advance from interrupt-based programming to Real-Time Operating System (RTOS)-based task scheduling, providing stepwise exposure to core SDV concepts. The model was validated through a mission-oriented competition that included line following, obstacle avoidance, and stop-line detection tasks. Dual assessment—combining technical performance indicators with rubric-based educational outcomes— demonstrated both algorithmic feasibility and pedagogical effectiveness. This work highlights that early undergraduates can gain meaningful SDV-oriented embedded control experience through lightweight competitions. The proposed framework offers an effective pathway for cultivating the next-generation mobility workforce, bridging the gap between theoretical education and practical implementation in the SDV era.

인공지능(AI), 머신러닝 등 첨단 기술의 급속한 발전은 해사 산업 전반에 큰 영향을 미치고 있으며, 이러한 변화는 자율운항선 박(MASS)의 개발과 상용화를 촉진하고 있다. 국내외에서는 다양한 MASS 실증 프로젝트와 관련 기술 개발이 활발히 진행되고 있으며, 국 제해사기구(IMO)도 이에 대응하여 MASS에 관한 내용을 공식 의제로 채택하고 지속적으로 논의를 이어가고 있다. IMO는 이미 규정식별 작업(RSE)을 완료하고 비강제 MASS Code를 개발 중이며, 조만간 공식 채택을 앞두고 있다. 이 과정에서 기존 국제협약 내에서 MASS 상 용화를 위해 검토가 필요한 항목으로 용어 정의, 원격운항센터, 원격운항자의 법적 지위, 사이버보안 등이 식별되었다. 본 연구는 이러한 국제협약상의 공백과 기술·법적 이슈를 국내 법체계와 연계하여 분석하였으며, 특히 원격운항자의 법적 지위, 안전 기준, 책임 배분 등과 관련된 개정 및 보완 필요사항을 도출하였다. 아울러 원격운항자 자격체계 마련, 안전성 평가 절차 강화, 보험 및 보증 구조 개선, 사이버 보안 체계 확립, 원격운항 인프라 운영지침 정비 등 국내 법제도의 개선 방향을 제시하였다. 또한 국내 주요 법령별 적용 쟁점을 중심으 로 단·중·장기 규제 설계 로드맵을 제안함으로써 MASS 단계별 법제 개편의 방향성을 구체화하였다. 연구 결과, MASS 도입은 단순한 기 술혁신이 아니라 해사 법규 체계 전반에 걸친 근본적 재구조화를 요구하며, 선박의 국제성을 고려할 때 국제협약과 국내법 간 일관성 있 는 연계를 구축하는 것이 해상안전 확보, 법적 예측 가능성 및 국제적 조화를 위해 핵심적임을 제시하였다.

현재 해운업계는 환경 규제 강화와 인력 부족이라는 구조적 도전에 직면하고 있으며, 자율운항선박은 이에 대응할 수 있는 기 술적·친환경적 대안으로 주목받고 있다. 본 연구는 LNG 연료를 사용하는 자율운항 LNG운반선, 컨테이너선, 벌크선을 대상으로 초기투자 비용(CAPEX)과 유지관리비용(OPEX)을 분석하고, 시나리오 기반의 경제성 분석을 통해 자율운항 시스템 도입 효과를 정량적으로 검토하 였다. 분석 결과, 자율운항 기술과 LNG 연료의 결합은 경제성과 환경 지속 가능성을 동시에 확보할 수 있으며, 특히 컨테이너선이 가장 높은 경제성을 보이는 것으로 나타났다. 향후 연구에서는 자율운항선박의 실증 데이터 축적과 차세대 친환경 연료를 적용한 경제성 분석 이 필요하다. 본 연구는 해운업계에서 장기 투자전략 수립을 위한 기초자료를 제공하는 데 목적이 있다.

자율운항선박(MASS)의 상용화가 본격화됨에 따라, 기존 유인선 중심으로 설계된 VTS(Vessel Traffic Services) 체계와의 협력 한계 가 점차 주목받고 있다. 특히 Level 3 및 Level 4 MASS는 음성 기반 VHF 통신이나 비정형 텍스트 형식의 해사안전정보(Maritime Safety Information, MSI)를 기계적으로 인식․처리하는 데 한계가 있다. 본 연구는 이러한 한계를 극복하고 MASS-VTS 간 상호운용성을 강화하기 위해 3가지 구조화 통신체계 전환 방안을 제안하였다. 첫째, MSI를 S-100 계열(S-124, S-210 등) 기반의 기계 판독이 가능한 구조화 형식 (XML, JSON 등)으로 전환한다. 둘째, NAVDAT 또는 VDES를 활용한 실시간 구조화 데이터 전송 인프라를 도입하여, 항법 알고리즘과 즉시 연계를 가능하게 한다. 셋째, VTS는 공간통제구역(Control zone) 개념과 같은 ‘정보-판단’ 기반의 간접 조정 방식을 채택하여 MASS의 자율성 을 보장함과 동시에 VTS의 기능을 강화한다. 본 연구의 제안 방안에 대해 정책적, 기술적, 경제적 타당성을 고찰하고, 해외 유사 사례를 조 사하여 적용 가능성을 검증하였다. 이 연구가 향후 MASS-VTS 협력 체계 강화를 위한 기술 표준 및 정책 수립에 활용되기를 기대한다.

In this study, we comparatively analyzed the efficiency of conventional image recognition methods and propose a digital information provisioning method for autonomous vehicle traffic safety facility recognition. We evaluated the practicality of both approaches from the perspective of autonomous vehicles' capabilities of processing regulatory information and the distribution of legal responsibility. Comprehensive field experiments were conducted at 9 major intersections in the Pangyo Techno Valley area of Hwaseong City over a 10- day period from July 12-23, 2021. Three test vehicles equipped with in-vehicle terminals and video cameras collected data through 300 driving scenarios, including 240 during peak hours and 60 during off-peak periods. The proposed digital information provision method exhibited superior performance, achieving a 100.0 % recognition success rate across all test scenarios and road conditions. In contrast, the conventional image recognition method exhibited significant variability in performance, ranging from 56.9 % in underpass conditions to 95.9 % in areas with communication interference, with an overall average of 70.8 %. The digital information provision method demonstrated superior performance compared to conventional image recognition approaches for autonomous vehicle regulatory compliance. The proposed approach delivered consistent and reliable information regardless of physical obstacles or environmental conditions. This method ensures complete comprehension of regulatory information, which is essential for establishing clear legal responsibility frameworks in autonomous driving environments.

In this study, we propose a data-driven analytical framework for systematically analyzing the driving patterns of autonomous buses and quantitatively identifying risky driving behaviors at the road-segment level using operational data from real roads. The analysis was based on Basic Safety Message (BSM) data collected over 125 days from two Panta-G autonomous buses operating in the Pangyo Autonomous Driving Testbed. Key driving indicators included speed, acceleration, yaw rate, and elevation, which were mapped onto high-definition (HD) road maps. A hybrid clustering method combining self-organizing map (SOM) and k-means++ was applied, which resulted in eight distinct driving pattern clusters. Among these, four clusters exhibited characteristics associated with risky driving such as sudden acceleration, deceleration, and abrupt steering, and were spatially visualized using digital maps. These visualizations offer practical insights for real-time monitoring and localized risk assessment in autonomous vehicle operations. The proposed framework provides empirical evidence for evaluating the operational safety and reliability of autonomous buses based on repeated behavioral patterns. Its adaptability to diverse urban environments highlights its utility for intelligent traffic control systems and future mobility policy planning.

In this study, we investigated and analyzed the impact of changes in driving speed and inter-vehicle distance on users’ perceived tension during autonomous vehicle operation. To this end, a survey experiment was conducted for both urban roads and highways. The results show that the greatest changes in perceived tension occurred in the range of 50–70 Km/h and 50–70 m following distance on urban roads, and in the range of 80–100 Km/he and 60–80 m following distance on highways. Furthermore, modeling user behavioral responses to perceived tension based on changes in speed and following distance revealed that linear models best described the relationship for speed on both urban roads and highways. For the following distance, a quadratic model was the most suitable for urban roads, whereas a logarithmic model best fit the highway data. These findings are expected to contribute to practical operational guidelines for autonomous vehicles by alleviating users’ psychological discomfort and enhancing public acceptance. Future research will extend this study using a driving simulator to examine user responses in more realistic driving environments.