• 제목/요약/키워드: Autonomous Driving Vehicle

검색결과 520건 처리시간 0.027초

Personal Driving Style based ADAS Customization using Machine Learning for Public Driving Safety

  • Giyoung Hwang;Dongjun Jung;Yunyeong Goh;Jong-Moon Chung
    • 인터넷정보학회논문지
    • /
    • 제24권1호
    • /
    • pp.39-47
    • /
    • 2023
  • The development of autonomous driving and Advanced Driver Assistance System (ADAS) technology has grown rapidly in recent years. As most traffic accidents occur due to human error, self-driving vehicles can drastically reduce the number of accidents and crashes that occur on the roads today. Obviously, technical advancements in autonomous driving can lead to improved public driving safety. However, due to the current limitations in technology and lack of public trust in self-driving cars (and drones), the actual use of Autonomous Vehicles (AVs) is still significantly low. According to prior studies, people's acceptance of an AV is mainly determined by trust. It is proven that people still feel much more comfortable in personalized ADAS, designed with the way people drive. Based on such needs, a new attempt for a customized ADAS considering each driver's driving style is proposed in this paper. Each driver's behavior is divided into two categories: assertive and defensive. In this paper, a novel customized ADAS algorithm with high classification accuracy is designed, which divides each driver based on their driving style. Each driver's driving data is collected and simulated using CARLA, which is an open-source autonomous driving simulator. In addition, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) machine learning algorithms are used to optimize the ADAS parameters. The proposed scheme results in a high classification accuracy of time series driving data. Furthermore, among the vast amount of CARLA-based feature data extracted from the drivers, distinguishable driving features are collected selectively using Support Vector Machine (SVM) technology by comparing the amount of influence on the classification of the two categories. Therefore, by extracting distinguishable features and eliminating outliers using SVM, the classification accuracy is significantly improved. Based on this classification, the ADAS sensors can be made more sensitive for the case of assertive drivers, enabling more advanced driving safety support. The proposed technology of this paper is especially important because currently, the state-of-the-art level of autonomous driving is at level 3 (based on the SAE International driving automation standards), which requires advanced functions that can assist drivers using ADAS technology.

신경회로망을 이용한 자율주행차량의 속도 및 조향제어 (Speed and Steering Control of Autonomous Vehicle Using Neural Network)

  • 임영철;류영재;김의선;김태곤
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
    • /
    • pp.274-281
    • /
    • 1998
  • This paper describes a visual control of autonomous vehicle using neural network. Visual control for road-following of autonomous vehicle is based on road image from camera. Road points on image are inputs of controller and vehicle speed and steering angle are outputs of controller using neural network. Simulation study confirmed the visual control of road-following using neural network. For experimental test, autonomous electric vehicle is designed and driving test is realized

  • PDF

A Vehicle Recognition Method based on Radar and Camera Fusion in an Autonomous Driving Environment

  • Park, Mun-Yong;Lee, Suk-Ki;Shin, Dong-Jin
    • International journal of advanced smart convergence
    • /
    • 제10권4호
    • /
    • pp.263-272
    • /
    • 2021
  • At a time when securing driving safety is the most important in the development and commercialization of autonomous vehicles, AI and big data-based algorithms are being studied to enhance and optimize the recognition and detection performance of various static and dynamic vehicles. However, there are many research cases to recognize it as the same vehicle by utilizing the unique advantages of radar and cameras, but they do not use deep learning image processing technology or detect only short distances as the same target due to radar performance problems. Radars can recognize vehicles without errors in situations such as night and fog, but it is not accurate even if the type of object is determined through RCS values, so accurate classification of the object through images such as cameras is required. Therefore, we propose a fusion-based vehicle recognition method that configures data sets that can be collected by radar device and camera device, calculates errors in the data sets, and recognizes them as the same target.

정밀 지도에 기반한 자율 주행 시스템 개발 (A Development of the Autonomous Driving System based on a Precise Digital Map)

  • 김병광;이철하;권수림;정창영;천창환;박민우;나용천
    • 자동차안전학회지
    • /
    • 제9권2호
    • /
    • pp.6-12
    • /
    • 2017
  • An autonomous driving system based on a precise digital map is developed. The system is implemented to the Hyundai's Tucsan fuel cell car, which has a camera, smart cruise control (SCC) and Blind spot detection (BSD) radars, 4-Layer LiDARs, and a standard GPS module. The precise digital map has various information such as lanes, speed bumps, crosswalks and land marks, etc. They can be distinguished as lane-level. The system fuses sensed data around the vehicle for localization and estimates the vehicle's location in the precise map. Objects around the vehicle are detected by the sensor fusion system. Collision threat assessment is performed by detecting dangerous vehicles on the precise map. When an obstacle is on the driving path, the system estimates time to collision and slow down the speed. The vehicle has driven autonomously in the Hyundai-Kia Namyang Research Center.

자율주행 차량의 다 차선 환경 내 차량 추종 경로 계획 (Car-following Motion Planning for Autonomous Vehicles in Multi-lane Environments)

  • 서장필;이경수
    • 자동차안전학회지
    • /
    • 제11권3호
    • /
    • pp.30-36
    • /
    • 2019
  • This paper suggests a car-following algorithm for urban environment, with multiple target candidates. Until now, advanced driver assistant systems (ADASs) and self-driving technologies have been researched to cope with diverse possible scenarios. Among them, car-following driving has been formed the groundwork of autonomous vehicle for its integrity and flexibility to other modes such as smart cruise system (SCC) and platooning. Although the field has a rich history, most researches has been focused on the shape of target trajectory, such as the order of interpolated polynomial, in simple single-lane situation. However, to introduce the car-following mode in urban environment, realistic situation should be reflected: multi-lane road, target's unstable driving tendency, obstacles. Therefore, the suggested car-following system includes both in-lane preceding vehicle and other factors such as side-lane targets. The algorithm is comprised of three parts: path candidate generation and optimal trajectory selection. In the first part, initial guesses of desired paths are calculated as polynomial function connecting host vehicle's state and vicinal vehicle's predicted future states. In the second part, final target trajectory is selected using quadratic cost function reflecting safeness, control input efficiency, and initial objective such as velocity. Finally, adjusted path and control input are calculated using model predictive control (MPC). The suggested algorithm's performance is verified using off-line simulation using Matlab; the results shows reasonable car-following motion planning.

Tunnel lane-positioning system for autonomous driving cars using LED chromaticity and fuzzy logic system

  • Jeong, Jae-Hoon;Byun, Gi-Sig;Park, Kiwon
    • ETRI Journal
    • /
    • 제41권4호
    • /
    • pp.506-514
    • /
    • 2019
  • Currently, studies on autonomous driving are being actively conducted. Vehicle positioning techniques are very important in the autonomous driving area. Currently, the global positioning system (GPS) is the most widely used technology for vehicle positioning. Although technologies such as the inertial navigation system and vision are used in combination with GPS to enhance precision, there is a limitation in measuring the lane and position in shaded areas of GPS, like tunnels. To solve such problems, this paper presents the use of LED lighting for position estimation in GPS shadow areas. This paper presents simulations in the environment of three-lane tunnels with LEDs of different color temperatures, and the results show that position estimation is possible by the analyzing chromaticity of LED lights. To improve the precision of positioning, a fuzzy logic system is added to the location function in the literature [1]. The experimental results showed that the average error was 0.0619 cm, and verify that the performance of developed position estimation system is viable compared with previous works.

자율주행을 위한 레이더 기반 인지 알고리즘의 정량적 분석 (Quantitative Analysis of Automotive Radar-based Perception Algorithm for Autonomous Driving)

  • 이호준;채흥석;서호태;이경수
    • 자동차안전학회지
    • /
    • 제10권2호
    • /
    • pp.29-35
    • /
    • 2018
  • This paper presents a quantitative evaluation method and result of moving vehicle perception using automotive radar. It is also important to analyze the accuracy of the perception algorithm quantitatively as well as to accurately percept nearby moving vehicles for safe and efficient autonomous driving. In this study, accuracy of the automotive radar-based perception algorithm which is developed based on interacting multiple model (IMM) has been verified via vehicle tests on real roads. In order to obtain experimental data for quantitative evaluation, Long Range Radar (LRR) has been mounted on the front of the ego vehicle and Short Range Radar (SRR) has been mounted on the rear side of both sides. RT-range has been installed on the ego vehicle and the target vehicle to simultaneously collect reference data on the states of the two vehicles. The experimental data is acquired in various relative positions and velocity, and the accuracy of the algorithm has been analyzed according to relative position and velocity. Quantitative analysis is conducted on relative position, relative heading angle, absolute velocity, and yaw rate of each vehicle.

SLAM을 이용한 카메라 기반의 실내 배송용 자율주행 차량 구현 (Implementation of Camera-Based Autonomous Driving Vehicle for Indoor Delivery using SLAM)

  • 김유중;강준우;윤정빈;이유빈;백수황
    • 한국전자통신학회논문지
    • /
    • 제17권4호
    • /
    • pp.687-694
    • /
    • 2022
  • 본 논문에서는 Visual 동시적 위치추정 및 지도작성(SLAM : Simultaneous Localization and Mapping)기술을 응용하여 실내에서 생성된 SLAM 맵을 기반으로 지정된 목적지에 물건을 배달하는 자율주행 차량 플랫폼을 제안하였다. 실내에서 SLAM 맵을 생성하기 위해 소형 자율주행 차량 플랫폼의 상단에 SLAM 맵 생성을 위한 심도 카메라를 설치하고 SLAM 맵 속에서의 정확한 위치추정을 하기 위해 추적 카메라를 장착하여 구현하였다. 또한, 목적지의 표찰을 인식하기 위해 합성곱 신경망(CNN : Convolutional neural network)을 사용하여 목적지에 정확하게 도착할 수 있도록 주행 알고리즘을 적용하여 설계하였다. 실내 배송 자율주행 차량을 실제로 제작하였고 SLAM 맵의 정확도 확인과 CNN을 통한 목적지 표찰 인식 실험을 수행하였다. 결과적으로 표찰 인식의 성공률을 향상시켜 구현한 실내 배송용 자율주행 차량의 활용 적합성 여부를 확인하였다.

종방향 자율주행의 미지 고장 재건을 위한 순환 최소 자승 기반 적응형 슬라이딩 모드 관측기 개발 (Development of a RLS based Adaptive Sliding Mode Observer for Unknown Fault Reconstruction of Longitudinal Autonomous Driving)

  • 오세찬;송태준;이종민;오광석;이경수
    • 자동차안전학회지
    • /
    • 제13권1호
    • /
    • pp.14-25
    • /
    • 2021
  • This paper presents a RLS based adaptive sliding mode observer (A-SMO) for unknown fault reconstruction in longitudinal autonomous driving. Securing the functional safety of autonomous vehicles from unexpected faults of sensors is essential for avoidance of fatal accidents. Because the magnitude and type of the faults cannot be known exactly, the RLS based A-SMO for unknown acceleration fault reconstruction has been designed with relationship function in this study. It is assumed that longitudinal acceleration of preceding vehicle can be obtained by using the V2V (Vehicle to Vehicle) communication. The kinematic model that represents relative relation between subject and preceding vehicles has been used for fault reconstruction. In order to reconstruct fault signal in acceleration, the magnitude of the injection term has been adjusted by adaptation rule designed based on MIT rule. The proposed A-SMO in this study was developed in Matlab/Simulink environment. Performance evaluation has been conducted using the commercial software (CarMaker) with car-following scenario and evaluation results show that maximum reconstruction error ratios exist within range of ±10%.

자율주행 개인화를 위한 역 충돌시간 및 차두시간 융합 기반 인간중심 제어 알고리즘 개발 (A Human-Centered Control Algorithm for Personalized Autonomous Driving based on Integration of Inverse Time-To-Collision and Time Headway)

  • 오광석
    • 한국융합학회논문지
    • /
    • 제9권10호
    • /
    • pp.249-255
    • /
    • 2018
  • 본 논문은 자율주행 개인화를 위한 역 충돌시간 및 차두시간 융합 기반 인간중심 제어 알고리즘 개발에 관한 것이다. 운전자 및 탑승자의 자율주행에 대한 이질감 최소화를 위해 인간중심적 주행제어 기술이 필요하다. 운전자가 선행차량과 함께 주행하는 조건에서 운전자의 주행특성을 분석하고, 분석된 결과를 종방향 자율주행 제어에 반영하였다. 주행특성으로 가속도, 역 충돌시간, 차두시간 분포가 분석되었고, 운전자의 주행특성이 반영된 제어기 구성을 위해 역 충돌시간 및 차두시간을 이용한 종방향 제어기를 구성하였다. 본 연구에서 제안된 제어 알고리즘은 Matlab/Simulink 환경에서 구성되었으며 실 주행데이터 기반 성능평가가 수행되었다.