• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.276-290
• /
• 2023

Several efforts in Korea are currently underway with the goal of commercializing autonomous vehicles. Hence, various studies are emerging on autonomous vehicles that drive safely and quickly according to operating guidelines. The current study examines the path search of an autonomous vehicle from a microscopic viewpoint and tries to prove the efficiency required by learning the lane change of an autonomous vehicle through Deep Q-Learning. A SUMO was used to achieve this purpose. The scenario was set to start with a random lane at the starting point and make a right turn through a lane change to the third lane at the destination. As a result of the study, the analysis was divided into simulation-based lane change and simulation-based lane change applied with Deep Q-Learning. The average traffic speed was improved by about 40% in the case of simulation with Deep Q-Learning applied, compared to the case without application, and the average waiting time was reduced by about 2 seconds and the average queue length by about 2.3 vehicles.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.2
• /
• pp.231-238
• /
• 2023

Since there is a limit to the physically visible horizon that sensors for autonomous driving can perceive, complementary utilization of digital map data such as a Local Dynamic Map (LDM) along the probable route of an Autonomous Vehicle (AV) is proposed for safe and efficient driving. Although the amount of digital map data may be insignificant compared to the amount of information collected from the sensors of an AV, efficient management of map data is inevitable for the efficient information processing of AVs. The objective of this study is to analyze the efficiency of information use and information processing time of AV according to the expansion of the active section of LDM-based static road and traffic information. To carry out this objective, a microscopic simulator model, VISSIM and VISSIM COM, was employed, and an area of about 9 km × 13 km was selected in the Busan Metropolitan Area, which includes heterogeneous traffic flows (i.e., uninterrupted and interrupted flows) as well as various road geometries. In addition, the LDM information used in AVs refers to the real high-definition map (HDM) built on the basis of ISO 22726-1. As a result of the analysis, as the electronic horizon area increases, while short links are intensively recognized on interrupted urban roads and the sum of link lengths increases as well, the number of recognized links is relatively small on uninterrupted traffic road but the sum of link lengths is large due to a small number of long links. Therefore, this study showed that an efficient range of electronic horizon for HDM data collection, processing, and management are set as 600 m on interrupted urban roads considering the 12 links corresponding to three downstream intersections and 700 m on uninterrupted traffic road associated with the 10 km sum of link lengths, respectively.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.299-312
• /
• 2021

Autonomous vehicles using V2X can drive safely information on areas outside the sensor coverage of autonomous vehicles conventional autonomous vehicles. As V2X technology has emerged as a key component of autonomous vehicles, research on V2X security is actively underway research on risk analysis due to failure of V2X communication is insufficient. In this paper, the service scenario and function of autonomous driving system V2X were derived by presenting the intersection scenario of the autonomous vehicle, the malfunction was defined by analyzing the hazard of V2X. he ISO26262 Part3 process was used to analyze the risk of malfunction of autonomous vehicle V2X. In addition, a fault injection scenario was presented to verify the fail-safe of the simulation-based intersection scenario.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.219-222
• /
• 2002

본 논문에서는 미지의 환경에서 이동로봇의 자율 주행이 가능하도록 비전 시스템과 퍼지규칙을 이용한 경로 설정과 장애물 회피를 위한 알고리즘을 소개 하고자 한다. 한편 원격지에서도 로봇의 움직임을 파악할 수 있도록 인터넷을 통한 원격운용 기능을 추가함으로써 로봇의 효율적인 운용이 가능하도록 하였다. 소벨 연산자를 이용한 장애물의 윤곽선 추출과 퍼지규칙을 이용하여 경로 계획과 장애물 회피를 위한 알고리즘을 생성하였으며, 컴퓨터 시뮬레이션으로 그 효율성을 검증하였다. 또한 실제 이동 로봇을 제작하여 실험한 결과에서도 제안된 알고리즘이 우수한 성능을 발휘함을 확인할 수 있었다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.280-298
• /
• 2021

As the development automated vehicles(AV) actively progresses around the world, the demand for a reasonable and systematic evaluation method for AVs is increasing. Research on scenarios, evaluation procedures, and methods for evaluating AVs conducted in simulations and proving ground(PG) is actively conducted internationally. In contrast, methods and procedures for evaluations on real roads are still in their infancy internationally. Therefore, it is necessary to conduct research on evaluating AVs on real roads in preparation for future use of AVs. This study aims to define the basic direction for evaluating the driving safety of AVs on real roads. To this end, the evaluation direction and process of AVs were presented on the real roads, and qualitative and quantitative evaluation indicators were selected to evaluate driving safety. A total of 38 items were selected based on the Road Traffic Act as qualitative evaluation items for evaluating the driving safety of AVs on real roads.

• Journal of Auto-vehicle Safety Association
• /
• v.14 no.1
• /
• pp.39-44
• /
• 2022

This paper presents a development of throttle and brake controller for autonomous vehicle simulation environment. Most of 3D simulator control autonomous vehicle by throttle and brake command. Therefore additional longitudinal controller is required to calculate pedal input from desired acceleration. The controller consists of two parts, feedback controller and feedforward controller. The feedback controller is designed to compensate error between the actual acceleration and desired acceleration calculated from autonomous driving algorithm. The feedforward controller is designed for fast response and the output is determined by the actual vehicle speed and desired acceleration. To verify the performance of the controller, simulations were conducted for various scenarios, and it was confirmed that the controller can successfully follow the target acceleration.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.97-100
• /
• 2023

차량 인터넷은 목적지까지 스스로 주행하는 자율 주행 자동차의 최적 경로 설정을 도와주는 차세대 네트워크이다. 자율 주행 자동차의 원활한 자율 주행을 위해서는 도로 위 객체 인지뿐만 아니라 실시간 교통 정보가 수신되어야 한다. 공격자는 자동차로 전달되는 메시지를 탈취하여 내용을 변경하거나 메시지를 제거하는 중간자 공격을 시도할 수 있다. 중간자 공격을 탐지하기 위해 MARINE 기법이 제안되었지만, 주행하는 자동차가 적은 환경에서 중간자 공격을 탐지하기 어렵다. 제안 방법은 이러한 문제를 해결하기 위해 교통 정보 센터에 축적된 교통 정보를 이용하여 자동차에 전달되는 메시지를 분석하고 중간자 공격을 탐지하는 방법을 제안한다.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1997.06c
• /
• pp.232-237
• /
• 1997

• 전기의세계
• /
• v.56 no.1
• /
• pp.42-44
• /
• 2007

• Journal of Drive and Control
• /
• v.19 no.1
• /
• pp.86-89
• /
• 2022