• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.242-263
• /
• 2021

This paper presents a method to implement a low-cost driving simulator for developing autonomous driving algorithms. This is implemented by using GTA V, a physical engine-based commercial game software, containing a function to emulate output and data of various sensors for autonomous driving. For this, NF of Script Hook V is incorporated to acquire GT data by accessing internal data of the software engine, and then, various sensor data for autonomous driving are generated. We present an overall function of the developed driving simulator and perform a verification of individual functions. We explain the process of acquiring GT data via direct access to the internal memory of the game engine to build up an autonomous driving algorithm development environment. And, finally, an example applicable to artificial neural network training and performance evaluation by processing the emulated sensor output is included.

• Proceedings of the KIEE Conference
• /
• 2009.07a
• /
• pp.1837_1838
• /
• 2009

본 논문에서는 Particle Swarm Optimization(PSO)을 이용하여 지능형 로봇의 주행 제어 방법을 제안한다. 지능형 로봇의 주행을 위한 퍼지 제어기를 설계하고 퍼지 규칙을 구성하고 있는 멤버쉽 함수의 매개 변수를 PSO를 이용하여 동정한다. 최종 PSO로 동정된 매개변수를 이용하여 벽면 주행을 수행한다. 마지막으로, 실험을 통해 그 응용 가능성을 증명한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10a
• /
• pp.102-104
• /
• 1999

인터넷의 발전으로 WWW상에서 지도 정보를 서비스하는 사이트들이 늘어나고 있다. 본 논문은 이러한 WWW상의 지리 정보 서비스를 확장한 도로 주행 안내 시스템의 구현에 관하여 기술한다. 도로 주행 안내 시스템은 도로, 건물 등의 지리 정보를 표시해주며 사용자의 최단 경로질의를 받고 빠른 시간내에 최단경로를 탐색할 수 있어야 한다. 본 연구에서는 이러한 요구를 수용할 수 있도록 OODBMS, CORBA, Java를 사용하여 WWW상의 도로 주행 안내 시스템을 설계 및 구현하였다. 이를 위해 이 논문에서는 도로 데이터 캐싱과 그래프 모델링, HEPV (Hierarchical Encoded Path View) 알고리즘 구현 등의 사항을 기술하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.01a
• /
• pp.7-10
• /
• 2012

본 논문에서는 스마트폰을 이용하여 도로 주행 정보를 기록하고 운전자에게 패턴 별 주행정보를 제공하는 라이프로그(Lifelog) 형태의 서비스에 목적을 두고 있다. 운전자의 도로 주행 데이터를 데이터베이스화한 이 정보는 다양하게 이용될 수 있다. 주행 패턴 인식은 이벤트 구간 검출 과정을 통한 패턴 구간을 검출하고 가속도 센서와 방향 센서, 즉 멀티 센서 기반으로 주행패턴을 인식한다. 주행 패턴을 분석 후 시간 정보를 이용하여 촬영된 영상 데이터에서의 패턴 구간 영상을 같이 제공한다. 이렇게 패턴 구간의 센서 스트리밍 정보와 영상을 제공하면 운전자의 운전 성향 및 주행 기록을 분석하는데 이용될 수 있다. 따라서 주행패턴 인식 알고리즘을 프로토타입으로 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.80-82
• /
• 2020

최근 자율주행차량의 기술 개발이 확대되면서 이를 기반으로 운전자, 인프라 등 다양한 관점에서 효과를 기대할 수 있는 군집주행에 대한 관심도 점차 높아지고 있다. 현재 고속도로에서만 적용 가능한 군집주행 기술이 상용화 되면서 교차로가 많은 도시 도로 환경에서도 이를 적용하기 위해 여러 자동차 업체에서 시스템을 개발 중이다. 하지만 기존 군집주행 방식은 군집이 해체될 경우 차량이 다시 군집을 형성하고 다른 군집에 가입하는 과정에서 발생하는 시간이나 비용적인 측면에서 도로 처리량과 시간 단축이라는 본래 군집주행의 목표에 미치지 못한다. 따라서 본 논문은 차량 간에 주고받는 메시지를 개선하여 군집주행 알고리즘을 새롭게 설계해 도시 도로 환경에서도 적용 가능한 동적 군집주행에 대해 제안하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1483-1490
• /
• 2009

This parer is presented multiple path-planning of unmanned autonomous forklift using modified genetic algorithm and fuzzy inference system. There are a task-level feedback method and a method that path is dynamically replaned in realtime while the autonomous vehicles are moving by means of an optimal algorithm for existing multiple path-planning. However, such methods cause malfunctions and inefficiency in the sense of time and energy, and path-planning should be dynamically replanned in realtime. To solve these problems, we propose multiple path-planning using modified genetic algorithm and fuzzy inference system and show the performance with autonomous vehicles. For experiment, we designed and built two autonomous mobile vehicles that equipped with the same driving control part used in actual autonomous forklift, and test the proposed multiple path-planning algorithm. Experimental result that actual autonomous mobile vehicle, we verified that fast optimized path-planning and efficient collision avoidance are possible.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.4
• /
• pp.67-80
• /
• 2020

High-speed weigh in motion (HS-WIM) is a real-time unmanned system for measuring the weight of a freight-carrying vehicle while it is in motion without controlling vehicle traffic flow or deceleration. In Korea, HS-WIM systems are installed on the national highways and general national ways for pre-selection by law enforcement. In this study, to improve the measurement accuracy of HS-WIM, we devise improvements to the existing integral and peak weight conversion algorithms, and we provide a new fusion algorithm that can be applied to the mat-type HS-WIM. As a result of analyzing vehicle driving tests at a real site, we confirmed the highest level of weight-measuring accuracy.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.689-698
• /
• 2021

In this paper, lane recognition, steering control and speed control algorithms were developed using Bluetooth wireless communication and image processing techniques. Instead of recognizing road traffic signals based on image processing techniques, a methodology for recognizing the permissible road speed by receiving speed codes from electronic traffic signals using Bluetooth wireless communication was developed. In addition, a steering control algorithm based on PWM control that tracks the lanes using the Canny algorithm and Hough transform was developed. A vehicle prototype and a driving test track were developed to prove the accuracy of the developed algorithm. Raspberry Pi and Arduino were applied as main control devices for steering control and speed control, respectively. Also, Python and OpenCV were used as implementation languages. The effectiveness of the proposed methodology was confirmed by demonstrating effectiveness in the lane tracking and driving control evaluation experiments using a vehicle prototypes and a test track.

• Journal of Advanced Marine Engineering and Technology
• /
• v.32 no.1
• /
• pp.192-199
• /
• 2008

In order for a mobile robot to move under unknown or uncertain environment. it is very important to collect environmental information. This paper suggests a traveling algorithm which leads to the map building algorithm and the $A^*$ algorithm under the assumption that environmental information should already be collected. In order to apply the proposed traveling algorithm to a real mobile robot. this paper additionally discusses a path amendment algorithm. For the purpose of verifying the proposed algorithms, several simulations are executed based on a UI host program-based simulation interface and an experiment is executed using a mobile robot under a real unknown environment.

• Convergence Security Journal
• /
• v.18 no.3
• /
• pp.3-9
• /
• 2018

The Deep Deterministic Policy Gradient (DDPG) algorithm is an algorithm that learns by using artificial neural network s and reinforcement learning. Among the studies related to reinforcement learning, which has been recently studied, the D DPG algorithm has an advantage of preventing the cases where the wrong actions are accumulated and affecting the learn ing because it is learned by the off-policy. In this study, we experimented to control the bicycle autonomously by applyin g the DDPG algorithm. Simulation was carried out by setting various environments and it was shown that the method us ed in the experiment works stably on the simulation.