• 제목/요약/키워드: Vehicle Driving

검색결과 2,662건 처리시간 0.031초

자동차 운전면허 시험을 위한 자동 채점 시스템 구현 (Realization of a Automatic Grading System for Driver's License Test)

  • 김철우;이동학;양재수
    • 한국ITS학회 논문지
    • /
    • 제16권5호
    • /
    • pp.109-120
    • /
    • 2017
  • 자동차 운전면허 시험에서 객관적인 평가가 중요하다. 특히 도로 주행시험은 실제 도로에서 운전능력, 규칙준수, 상황판단능력 등을 종합적으로 시험하는 것이다. 이를 위하여 본 논문에서는 GPS와 센서 데이터 및 기기조작 정보를 활용하여 운전면허 시험의 자동채점시스템을 제안한다. 자동채점 시스템은 차량탑재장치, 채점용단말, 데이터 제어장치, 데이터 저장 및 처리를 위한 서버로 구성되어 있다. 차량탑재장치는 차량에 설치된 센서 데이터를 수집한다. 채점 단말은 차량탑재장치로부터 받은 데이터를 활용하여 기준에 따라 자동채점 한다. 또한 이동 중에 GPS 오차로 인하여 차량이 도로를 벗어나 표현되므로 지도매칭 기법과 경로이탈 및 복귀 알고리즘을 적용하였다. 이 시스템은 기존 시험 채점 방식과 달리 자동 채점이 가능하며, 시험 결과에서 정확한 차량위치 표시와 GPS 음영지역을 벗어났을 때 10초 이내로 경로 복귀를 하였다. 이 시스템은 도로 주행 교육에도 활용될 수 있을 것으로 기대된다.

Ride Quality Investigation of Passenger Cars on Different Road Conditions

  • Park, Se Jin;Subramaniyam, Murali
    • 대한인간공학회지
    • /
    • 제32권4호
    • /
    • pp.389-396
    • /
    • 2013
  • Objective: The ride qualities of the six passenger cars were evaluated in 4 subjects on the highway and uneven road. The relation between vibration with driving velocity and driving posture were also investigated separately. Background: Ride comfort plays an important role in the vehicle design. Vibration is the one of the principal components associated with ride comfort. Method: The acceleration of the foot, hip and back were measured using B&K accelerometers in this study. The velocity of the passenger cars was maintained at a constant speed of 80km/h on the highway and 40km/h on the uneven road. For evaluating the effects of driving velocity and driving posture on vehicle's vibration level, separate experiments were performed on the highway with 5 different vehicle speeds and 5 different backrest angles, respectively. Results: The overall ride value of the luxury car showed the best result while the smaller car showed the worst value on the highway. On the uneven road the overall ride value level was increased 75~98%. All the vehicles had the SEAT value less than 1. Faster the velocity lowers the SEAT value. The ride quality in terms of vibration gets worst when the backrest angle increased. Conclusion: The smaller car had a first mode at the higher frequency and showed higher vibration level. SEAT value was mostly affected by the seat property not by vehicle. We ranked the luxury car seat had a best vibration reduction quality than others based on SEAT values. When the driving velocity increased, the overall ride values were increased proportionally and the SEAT values were somewhat decreased. Application: Evaluation of whole-body vibration in the passenger car.

Study on the Take-over Performance of Level 3 Autonomous Vehicles Based on Subjective Driving Tendency Questionnaires and Machine Learning Methods

  • Hyunsuk Kim;Woojin Kim;Jungsook Kim;Seung-Jun Lee;Daesub Yoon;Oh-Cheon Kwon;Cheong Hee Park
    • ETRI Journal
    • /
    • 제45권1호
    • /
    • pp.75-92
    • /
    • 2023
  • Level 3 autonomous vehicles require conditional autonomous driving in which autonomous and manual driving are alternately performed; whether the driver can resume manual driving within a limited time should be examined. This study investigates whether the demographics and subjective driving tendencies of drivers affect the take-over performance. We measured and analyzed the reengagement and stabilization time after a take-over request from the autonomous driving system to manual driving using a vehicle simulator that supports the driver's take-over mechanism. We discovered that the driver's reengagement and stabilization time correlated with the speeding and wild driving tendency as well as driving workload questionnaires. To verify the efficiency of subjective questionnaire information, we tested whether the driver with slow or fast reengagement and stabilization time can be detected based on machine learning techniques and obtained results. We expect to apply these results to training programs for autonomous vehicles' users and personalized human-vehicle interfaces for future autonomous vehicles.

C-ITS 기반 PVD를 활용한 차량 내 경고정보의 운전자 주행행태 영향 분석 (A Study to Evaluate the Impact of In-Vehicle Warning Information on Driving Behavior Using C-ITS Based PVD)

  • 김탁영;김호선;강경표;김승범
    • 한국ITS학회 논문지
    • /
    • 제21권5호
    • /
    • pp.28-41
    • /
    • 2022
  • C-ITS(Cooperative-Intelligent Transportation System)는 차량과 차량 또는 차량과 인프라 간의 양방향 무선통신 기술을 기반으로 전방의 교통상황 정보를 제공하는 기술 및 시스템을 의미한다. C-ITS 환경에서는 Vehicle-to-Everything(V2X) 기반의 경고 정보를 제공함으로써 운전자로 하여금 감속을 유도하고, 급격한 감속과 가속을 지양하도록 하여 주행행태를 안정적으로 개선시킬 수 있을 것으로 추측된다. 본 연구는 서울시 C-ITS 기반의 경고 정보의 개별적인 효과를 검증하기 위해 경고정보에 대한 순응여부를 판단할 수 있는 방법론을 개발하였으며 추가로 주행안전성 변화를 분석하여 경고정보의 효과를 정량적으로 평가해 보고자 한다. 순응여부는 정보 제공 유무로 구별되는 사전 PVD (Probe Vehicle Data)와 사후 PVD의 속도 분포를 추출하여 비교하였으며, 주행안전성 평가는 Jerk와 가속소음을 계산하여 분석을 수행하였다. 정량적 분석을 위해서 서울 C-ITS 사업기간동안 수집되었던 PVD와 부족한 데이터 수집을 보완하고자 DTG (Digital Tacho Graph) 데이터를 추가 수집하여 활용하였다. 순응도 분석결과 충분한 유효샘플이 수집된 경고정보에 대해 운전자는 감속운행행태를 보였으며, Jerk와 가속소음과 같은 주행안전성 지표를 산출하여 분석한 결과 경고정보 제공으로 인해 주행안전성이 개선되었음을 알 수 있었다.

안전 옵션 선정 다준규의사결정 모델 (Application of Multi Criteria Decision Making for Selection of Automobile Safety Option)

  • 김태희
    • 자동차안전학회지
    • /
    • 제10권2호
    • /
    • pp.50-55
    • /
    • 2018
  • Choosing automobile safety options is price-performance matter. The best fit options to buyer who has a certain driving habit are problem of MCDM (Multi Criteria Decision Making) because price of safety option, statistics of relating accident, consequence of accident, and driving habit are the multi criteria to be evaluated. In this paper, PROMETHEE-GAIA methodology is applied for solving this MCDM problem. The result shows that a different driving habit makes different choosing priority of safety options.

신경망을 이용한 차량의 주행방향과 장애물 인식에 관한 연구 (Recognition of Driving Direction & Obstacles Using Neural Network)

  • 김명수;양성훈;이석
    • 한국정밀공학회:학술대회논문집
    • /
    • 한국정밀공학회 1995년도 추계학술대회 논문집
    • /
    • pp.341-343
    • /
    • 1995
  • In this paper, an algorithm is presented to recogniz the driving direction of a vehicle and obstacles in front of it based on highway road image. The algorithm employs a neural network with 27 sub sets obtained from the road image as its input. The outputs include the direction of the vehicle movement and presence or absence of obstacles. The road image, obtained by a video camera, was digitized and processed by a personal computer equipped with an image processing board.

  • PDF

A NEW LEARNING ALGORITHM FOR DRIVING A MOBILE VEHICLE

  • Sugisaka, Masanori;Wang, Xin
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1998년도 제13차 학술회의논문집
    • /
    • pp.173-178
    • /
    • 1998
  • The strategy presented in this paper is based on modifying the past patterens and adjusting the content of the driving patterns by a new algorithm. Learning happens during the driving procedure of a mobile vehicle. The purpose of this paper is to solve the problem how to realize the hardware neurocomputer by back propagation (BP) neural network learning on-line.

  • PDF

Theoretical Study on Eco-Driving Technique for an Electric Vehicle with Dynamic Programming

  • Kuriyama, Motoi;Yamamoto, Sou;Miyatake, Masafumi
    • Journal of international Conference on Electrical Machines and Systems
    • /
    • 제1권1호
    • /
    • pp.114-120
    • /
    • 2012
  • Eco-driving technique for electric vehicles (EVs) is investigated in this paper. Many findings on EVs have been reported; however, they did not deal with eco-driving from the viewpoint of theoretical study. The authors have developed an energy-saving driving technique - the so-called "eco-driving" technique based on dynamic programming (DP). Optimal speed profile of an EV, which minimizes the amount of total energy consumption, was determined under fixed origin and destination, running time, and track conditions. DP algorithm can deal with such complicated conditions and can also derive the optimal solution. Using the proposed method, simulations were run for some cases. In particular, the author ran simulations for the case of a gradient road with a traffic signal. The optimization model was solved with MATLAB.

가상 운전 시뮬레이터를 이용한 족동 조향 시스템의 운전 성능 평가 (Driving Performance Evaluation Using Foot Operated Steering System in the Virtual Driving Simulator)

  • 송정헌;김용철
    • 대한의용생체공학회:의공학회지
    • /
    • 제38권4호
    • /
    • pp.197-204
    • /
    • 2017
  • The aim of this study was to evaluate driving performance of normal subjects for controlling the steering wheel by using foot operated steering devices in the driving simulator. Many people with complete bilateral loss or loss of use of upper limbs but with normal lower limbs are frequently left without use and/ or control of their hands, arms, or the upper extremities of their bodies. As a result, persons disabled in this manner have problems in operation an automobile because they cannot grasp and manipulate a conventional steering wheel. Therefore, if foot operated steering devices are used for controlling the vehicle on in people with disabilities, the disabled people could improve their community mobility by driving a car safely. Ten normal subjects were involved in this research to evaluate steering performance by using three types of steering devices(conventional steering wheel, pedal type foot steering, circular type foot steering) in driving simulator. STISim Drive 3 program was used for testing the driving performance in two road scenarios: straight road and curved road at low and high speed of vehicle (40 km/h and 80 km/h). This study used two-way ANOVA to compare the influences of two factors(type of foot steering device and road scenario) in the three dependent variables of steering performance(standard deviation of lateral position, the lateral position of vehicle and the number of line crossing). The average values of the three dependent variables(standard deviation of lateral position, lateral position and the number of line crossing) of driving performance were significantly smaller for conventional steering wheel or pedal type foot steering than circular type foot steering.

군용차량의 주행모드에 따른 상대 노면 가혹도 분석 (Relative Road Damage Analysis with Driving Modes of a Military Vehicle)

  • 서권희;송부근;윤희석
    • 한국자동차공학회논문집
    • /
    • 제24권2호
    • /
    • pp.225-231
    • /
    • 2016
  • A military vehicle is driven at different usage modes with the army application and servicing conditions. For practical durability validation, DT(Development Test) on a new military vehicle should be run up to the durability target kilometers on test courses in the specified proving ground. Driving velocities with test courses at the endurance mode of DT are established definitely. However, OT(Operational Test) and initial endurance test of production car can't be performed only in the DT courses due to the development period limit. Therefore, this paper focuses on the method to analyze the relative road damages between the endurance test in DT and other endurance test. Road load acquisition tests on KLTV(Korean Light Tactical Vehicle) were implemented at 15 driving modes in off-road and cross-country courses of two tests. Wheel accelerations were processed through band-pass filter, and then the main frequency and maximum power of the signals were computed by PSD analysis. Finally, using the proving ground optimization based on RDS(Relative Damage Spectrum) characterization, the damage factors between off-roads of test courses were determined.