• 대한임베디드공학회논문지
• /
• 제18권5호
• /
• pp.225-231
• /
• 2023

With the recent surge in the autonomous driving market, the significance of lane detection technology has escalated. Lane detection plays a pivotal role in autonomous driving systems by identifying lanes to ensure safe vehicle operation. Traditional lane detection models rely on engineers manually extracting lane features from predefined environments. However, real-world road conditions present diverse challenges, hampering the engineers' ability to extract adaptable lane features, resulting in limited performance. Consequently, recent research has focused on developing deep learning based lane detection models to extract lane features directly from data. In this paper, we classify lane detection models into four categories: cluster-based, curve-based, information propagation-based, and anchor-based methods. We conduct an extensive analysis of the strengths and weaknesses of each approach, evaluate the model's performance on an embedded board, and assess their practicality and effectiveness. Based on our findings, we propose future research directions and potential enhancements.

• 한국컴퓨터그래픽스학회논문지
• /
• 제30권3호
• /
• pp.109-123
• /
• 2024

딥러닝과 강화학습을 활용한 비전 기반 엔드투엔드 자율주행 시스템 관련 연구가 지속적으로 증가하고 있다. 일반적으로 이러한 시스템은 위치, 속도, 방향, 센서 데이터 등 연속적이고 고차원적인 차량의 상태를 잠재 특징 벡터로 인코딩하고, 이를 차량의 주행 정책으로 디코딩하는 두 단계로 구성된다. 도심 주행과 같이 다양하고 복잡한 환경에서는 Variational Autoencoder(VAE)나 Convolutional Neural Network(CNN)과 같은 네트워크를 이용한 효율적인 상태 표현 방법의 필요성이 더욱 부각된다. 본 논문은 차량의 이미지 상태 표현이 강화학습 성능에 미치는 영향을 분석하였다. CARLA 시뮬레이터 환경에서 실험을 수행하였고, 차량의 전방 카메라 센서로부터 취득한 RGB 이미지 및 Semantic Segmented 이미지를 각각 VAE와 Vision Transformer(ViT) 네트워크로 특징 추출하여 상태 표현 학습에 활용하였다. 이러한 방법론이 강화학습에 미치는 영향을 실험하여, 데이터 유형과 상태 표현 기법이 자율주행의 학습 효율성과 결정 능력 향상에 어떤 역할을 하는지를 실험하였다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2012년도 춘계학술대회 논문집
• /
• pp.943-944
• /
• 2012

• 한국ITS학회 논문지
• /
• 제23권1호
• /
• pp.167-181
• /
• 2024

자율주행 기술 개발에 있어서 드라이빙 시뮬레이터의 활용은 사고 환경에 대한 다양한 테스트를 단시간에 효과적으로 수행 가능하게 하여 개발 비용 및 노력을 획기적으로 줄일 수 있다. 그러나 드라이빙 시뮬레이터는 실제 환경과 차이가 존재한다는 심각한 단점이 존재하므로 드라이빙 시뮬레이터를 이용하여 개발된 자율주행 알고리즘이 실제 차량 시스템에 직접 적용시킬 때 큰 차이가 발생하는 문제가 있다. 이러한 문제는 Sim2Real 문제로 정의되며, 시나리오, 센서 모델링, 차량 동역학 등으로 구분할 수 있다. 본 논문에서는 Sim2Real 문제 중에서 IMU센서에 대해서 Sim2Real 문제 해결 방안에 대한 연구를 수행한다. 실제 환경과 에뮬레이터된 가상 IMU 센서의 차이를 줄이기 위해서 IMU 센서의 정밀 오차 모델링을 통한 센서 에뮬레이터 기술에 대해 소개한다. Bias, Scale Factor, Misalignmnet, Random Walk에 따른 오차를 가상 IMU 센서 등급별로 모델링하고 이를 실제 IMU 센서의 등급에 따른 오차 지표와 비교함으로써 IMU 센서의 Sim2Real 문제를 완화한다.

• 자동차안전학회지
• /
• 제9권3호
• /
• pp.24-30
• /
• 2017

This paper presents the development of laser scanner based static obstacle detection algorithm for vehicle localization on lane lost section. On urban autonomous driving, vehicle localization is based on lane information, GPS and digital map is required to ensure. However, in actual urban roads, the lane data may not come in due to traffic jams, intersections, weather conditions, faint lanes and so on. For lane lost section, lane based localization is limited or impossible. The proposed algorithm is designed to determine the lane existence by using reliability of front vision data and can be utilized on lane lost section. For the localization, the laser scanner is used to distinguish the static object through estimation and fusion process based on the speed information on radar data. Then, the laser scanner data are clustered to determine if the object is a static obstacle such as a fence, pole, curb and traffic light. The road boundary is extracted and localization is performed to determine the location of the ego vehicle by comparing with digital map by detection algorithm. It is shown that the localization using the proposed algorithm can contribute effectively to safe autonomous driving.

• International journal of advanced smart convergence
• /
• 제13권2호
• /
• pp.25-34
• /
• 2024

The paper investigates how the semiconductor and electric vehicle industries are addressing safety and security concerns in the era of autonomous driving, emphasizing the prioritization of safety over security for market competitiveness. Collaboration between these sectors is deemed essential for maintaining competitiveness and value. The research suggests solutions such as advanced autonomous driving technologies and enhanced battery safety measures, with the integration of AI chips playing a pivotal role. However, challenges persist, including the limitations of big data and potential errors in semiconductor-related issues. Legacy automotive manufacturers are transitioning towards software-driven cars, leveraging artificial intelligence to mitigate risks associated with safety and security. Conflicting safety expectations and security concerns can lead to accidents, underscoring the continuous need for safety improvements. We analyzed the expansion of electric vehicles as a means to enhance safety within a framework of converging security concerns, with AI chips being instrumental in this process. Ultimately, the paper advocates for informed safety and security decisions to drive technological advancements in electric vehicles, ensuring significant strides in safety innovation.

• 전자통신동향분석
• /
• 제33권6호
• /
• pp.107-117
• /
• 2018

In recent years, with the development of autonomous driving technology, high-performance artificial intelligence computing hardware platforms have been developed that can process multi-sensor data, object recognition, and vehicle control for autonomous vehicles. Most of these hardware platforms have been developed overseas, such as NVIDIA's DRIVE PX, Audi's zFAS, Intel GO, Mobile Eye's EyeQ, and BAIDU's Apollo Pilot. In Korea, however, ETRI's artificial intelligence computing platform has been developed. In this paper, we discuss the specifications, structure, performance, and development status centering on hardware platforms that support autonomous driving rather than the overall contents of autonomous driving technology.

• 한국지리정보학회지
• /
• 제26권1호
• /
• pp.1-10
• /
• 2023

4차 산업혁명 시대의 도래에 따라 자율주행 기술에 관한 관심이 증대되고 있다. 이에 따라 기존 교통시설에 대한 자율주행차의 적용 가능성 및 정밀도로지도의 활용과 함께 자율주행차에 부착된 센서를 이용하여 주변 상황을 인지함으로써 안전한 주행을 모색해야 할 필요가 있다. 본 연구에서는 자율주행시대에 도로· 교통 인프라 개선을 위해 개발한 자율주행차에 장착된 센서를 통해 인지하는 표지 시설의 활용을 위해 기존 도로시설물인 도로표지, 교통안전표지, 시선유도시설과 정밀도로지도의 시설물 관련 레이어와의 비교분석을 통한 자율주행차량이 인식 가능한 표지 시설의 역할을 도출한다. 자율주행차량이 인식 가능한 표지 시설은 자율주행차에 직접 특정한 행동을 수행하도록 하는 등의 역할을 함으로써 안전주행을 도모할 수 있다. 자율주행차가 센서를 이용하여 표지시설을 인지함으로써 주행안전을 도모하기 위해서는 설치와 관리 및 활용 기준의 마련이 필요하며, 기준에 따라 지속해서 관리 및 감독이 이루어져야 할 것으로 사료된다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3523-3543
• /
• 2022

Autonomous vehicles are gradually being regarded as the mainstream trend of future development of the automobile industry. Autonomous driving networks generate many intensive and delay-sensitive computing tasks. The storage space, computing power, and battery capacity of autonomous vehicle terminals cannot meet the resource requirements of the tasks. In this paper, we focus on the task scheduling problem of autonomous driving in software-defined edge networks. By analyzing the intensive and delay-sensitive computing tasks of autonomous vehicles, we propose an emotion model that is related to task urgency and changes with execution time and propose an optimal base station (BS) task scheduling (OBSTS) algorithm. Task sentiment is an important factor that changes with the length of time that computing tasks with different urgency levels remain in the queue. The algorithm uses task sentiment as a performance indicator to measure task scheduling. Experimental results show that the OBSTS algorithm can more effectively meet the intensive and delay-sensitive requirements of vehicle terminals for network resources and improve user service experience.

• 자동차안전학회지
• /
• 제13권4호
• /
• pp.129-143
• /
• 2021

This paper proposes actuator fault detection and adaptive fault-tolerant control algorithms using performance index and human-like learning for longitudinal autonomous vehicles. Conventional longitudinal controller for autonomous driving consists of supervisory, upper level and lower level controllers. In this paper, feedback control law and PID control algorithm have been used for upper level and lower level controllers, respectively. For actuator fault-tolerant control, adaptive rule has been designed using the gradient descent method with estimated coefficients. In order to adjust the control parameter used for determination of adaptation gain, human-like learning algorithm has been designed based on perceptron learning method using control errors and control parameter. It is designed that the learning algorithm determines current control parameter by saving it in memory and updating based on the cost function-based gradient descent method. Based on the updated control parameter, the longitudinal acceleration has been computed adaptively using feedback law for actuator fault-tolerant control. The finite window-based performance index has been designed for detection and evaluation of actuator performance degradation using control error.