• Journal of Drive and Control
• /
• v.18 no.4
• /
• pp.9-18
• /
• 2021

This study proposes a method for creating learning datasets to recognize obstacles using deep learning algorithms in automated construction machinery or an autonomous vehicle. Recently, many researchers and engineers have developed various recognition algorithms based on deep learning following an increase in computing power. In particular, the image classification technology and image segmentation technology represent deep learning recognition algorithms. They are used to identify obstacles that interfere with the driving situation of an autonomous vehicle. Therefore, various organizations and companies have started distributing open datasets, but there is a remote possibility that they will perfectly match the user's desired environment. In this study, we created an interface of the virtual simulator such that users can easily create their desired training dataset. In addition, the customized dataset was further advanced by using the RDBMS system, and the recognition rate was improved.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.2
• /
• pp.79-94
• /
• 2021

A GNSS receiver installed in autonomous vehicles is the most essential device for its navigation. However, if an intentional jamming signal is generated, there is a risk of exposure to an accident risk due to deterioration of the GNSS sensor's performance. Research is required to prevent this, and accordingly, a jamming generating device must be provided. However, according to the provisions of the law related to jamming, this is illegal. In this paper, we implement an in-vehicle jamming device that complies with the provisions of the law and does not affect the surrounding GNSS sensors. Driving simulation is used to evaluate the performance of the GNSS algorithm, and the malfunction of autonomous vehicles occurring in the interference environment and data errors output from the GNSS sensor are analyzed.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.5
• /
• pp.162-177
• /
• 2020

The perception of traffic environment based on various sensors in autonomous driving system has a direct relationship with driving safety. Recently, as the perception model based on deep neural network is used due to the development of machine learning/in-depth neural network technology, a the perception model training and high quality of a training dataset are required. However, there are several realistic difficulties to collect data on all situations that may occur in self-driving. The performance of the perception model may be deteriorated due to the difference between the overseas and domestic traffic environments, and data on bad weather where the sensors can not operate normally can not guarantee the qualitative part. Therefore, it is necessary to build a virtual road environment in the simulator rather than the actual road to collect the traning data. In this paper, a training dataset collection process is suggested by diversifying the weather, illumination, sensor position, type and counts of vehicles in the simulator environment that simulates the domestic road situation according to the domestic situation. In order to achieve better performance, the authors changed the domain of image to be closer to due diligence and diversified. And the performance evaluation was conducted on the test data collected in the actual road environment, and the performance was similar to that of the model learned only by the actual environmental data.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.45-56
• /
• 2021

In platoon driving, several autonomous vehicles communicate to exchange information with each other and drive in a single cluster. The platooning technology has various advantages such as increasing road traffic, reducing energy consumption and pollutant emission by driving in short distance between vehicles. However, the short distance makes it more difficult to cope with an emergency accident, and accordingly, it is difficult to ensure the safety of platoon driving, which must be secured. In particular, the unexpected situation, i.e., variability that may appear during driving can adversely affect the safety of platoon driving. Because such variability is difficult to predict and reproduce, preparing safety guards to prevent risks arising from variability is a challenging work. In this paper, we studied a simulation method to avoid the risk due to the variability that may occur while platoon driving. In order to simulate safe platoon driving, we develop diverse scenarios considering the variability, design and apply safety guards to handle the variability, and extends the detail functions of VENTOS, an open source platooning simulator. Based on the simulation results, we have confirmed that the risks caused form the variability can be removed, and safe platoon driving is possible. We believe that our simulation approach will contribute to research and development to ensure safety in platoon driving.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.101-111
• /
• 2022

Conditional autonomous vehicles should hand over control to the driver according on driving situations. However, if the driver is immersed in a non-driving task, the driver may not be able to make suitable decisions. Previous studies have confirmed that the cues enhance take-over performance with a directional information on driving. However, studies on the effect of take-over cues on the driver's brain activities are rigorously investigated yet. Therefore, this study we evaluates the driver's brain activity according to the take-over cue. A total of 25 participants evaluated the take-over performance using a driving simulator. Brain activity was evaluated by functional near-infrared spectroscopy, which measures brain activity through changes in oxidized hemoglobin concentration in the blood. It evaluates the activation of the prefrontal cortex (PFC) in the brain region. As a result, it was confirmed that the driver's PFC was activated in the presence of the cue so that the driver could stably control the vehicle. Since this study results confirmed that the effect of the cue on the driver's brain activity, and it is expected to contribute to the study of take-over performance on biomakers in conditional autonomous driving in future.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.19 no.5
• /
• pp.22-30
• /
• 2015

A gas generator which generates turbine driving gas by burning a part of propellants is used in an open cycle liquid rocket engine and as a main component of an open cycle liquid rocket engine autonomous hot firing tests are required to investigate the combustion performance and characteristics of the gas generator. However, since the combustion gas generated by a gas generator is choked at the turbine nozzle in the turbine manifold, it is necessary to consider the internal volume of turbine manifold as well as that of the gas generator for correct investigation of the combustion performance, characteristics, and acoustic characteristics of the gas generator. Therefore, in the paper hot firing test results of a gas generator with a turbine manifold simulator are described and characteristic prediction using the autonomous test of a gas generator is explained.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.126.2-126
• /
• 2001

This paper, the integration of driving simulator and unmanned vehicle by means of new concept for better performance through a tele-operated system is suggested. But autonomous system is one of the most difficult research topics from the point of view of several constrains on mobility, speed of vehicle and lack of environmental information. In these days, however, many innovations on the vehicle provide the appropriate automatic control in vehicle subsystem for reducing human error. This tendency is toward to the unmanned vehicle or the tele-operated vehicle ultimately. This paper describes the motion system ...

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2017.07a
• /
• pp.17-18
• /
• 2017

본 논문은 스마트 팩토리의 중요 요소인 무인반송차(AGV)를 자율 주행시키기 위해 오픈 소스 자율 주행차 시뮬레이터인 udacity를 이용해 머신 러닝시키는 시스템을 개발하였다. 공장의 운행 루트를 자율주행 시뮬레이터의 전경으로 가공하고, 3개의 카메라를 부착시킨 AGV를 운행시키면서 머신 러닝시킨다. AGV를 주행하여 얻어진 여러 학습 데이터를 통해 도출된 결과들을 각각 비교하여 우수한 모델을 선정하고 운행시킨 결과 AGV가 정해진 운행 루트를 정확하게 주행하는 것을 확인하였다. 이를 통해, 가상 운행 환경에서 저비용으로 AGV 운행 학습이 가능하다는 것을 보였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.702-704
• /
• 2022

자율주행 시뮬레이터를 위한 대체재로 게임 엔진을 통한 가상 환경 모의 연구가 수행되고 있다. 하지만 게임 엔진에서는 자율 주행에 필요한 센서를 기기에 맞게 사용자가 직접 모델링을 해줘야 하기 때문에 개발 비용이 크게 작용된다. 특히, Ray 를 활용한 3D LIDAR 는 GPU(Graphics Processing Unit) 사용량이 많은 작업이기 때문에 저비용 시뮬레이터를 위해서는 저비용 3D LIDAR 모의가 필요하다. 본 논문에서는 낮은 컴퓨터 연산을 사용하는 C++ 기반 3D LIDAR 모의 프레임 워크를 제안한다. 제안된 3D LIDAR 는 다수의 언덕으로 이루어진 비포장 Map 에서 성능을 검증 하였으며, 성능 검증을 의해 본 논문에서 생성된 3D LIDAR 로 간단한 LPP(Local Path Planning) 생성 방법도 소개한다. 제안된 3D LIDAR 프레임 워크는 저비용 실시간 모의가 필요한 자율 주행 분야에 적극 활용되길 바란다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.880-881
• /
• 2023

본 연구는 차량 동역학이 적용된 자율주행 시뮬레이터에서 구현된 차량의 거동이 실제 차량과 유사한지 검증하는 것이다. 이를 위해 실제 차량모델에 외력을 가할 수 있는 기구를 개발하여 데이터를 획득하고 분석하고자 한다. 시뮬레이터에서 구현된 차량과 유사한 서스펜션 구조를 가진 차량 모델을 만들고 센서를 달아 차량의 운동 모델을 모사했으며, 캠과 감속기어를 활용해 외력을 모사하기 위한 기구를 제작하였다.