• 로봇학회논문지
• /
• 제14권2호
• /
• pp.122-130
• /
• 2019

Collecting a rich but meaningful training data plays a key role in machine learning and deep learning researches for a self-driving vehicle. This paper introduces a detailed overview of existing open-source simulators which could be used for training self-driving vehicles. After reviewing the simulators, we propose a new effective approach to make a synthetic autonomous vehicle simulation platform suitable for learning and training artificial intelligence algorithms. Specially, we develop a synthetic simulator with various realistic situations and weather conditions which make the autonomous shuttle to learn more realistic situations and handle some unexpected events. The virtual environment is the mimics of the activity of a genuine shuttle vehicle on a physical world. Instead of doing the whole experiment of training in the real physical world, scenarios in 3D virtual worlds are made to calculate the parameters and training the model. From the simulator, the user can obtain data for the various situation and utilize it for the training purpose. Flexible options are available to choose sensors, monitor the output and implement any autonomous driving algorithm. Finally, we verify the effectiveness of the developed simulator by implementing an end-to-end CNN algorithm for training a self-driving shuttle.

• 자동차안전학회지
• /
• 제11권3호
• /
• pp.19-29
• /
• 2019

Recently, autonomous vehicles have been studied actively. Autonomous vehicles can detect objects around them using their on board sensors, estimate collision probability and maneuver to avoid colliding with objects. Many algorithms are suggested to prevent collision avoidance. However there are limitations of complex and diverse environments because algorithm uses only the information of attached environmental sensors and mainly depends on TTC (time-to-Collision) parameter. In this paper, autonomous driving algorithm using I2V communication-based cooperative sensing information is developed to cope with complex and diverse environments through sensor fusion of objects information from infrastructure camera and object information from equipped sensors. The cooperative sensing based autonomous driving algorithm is implemented in autonomous shuttle bus and the proposed algorithm proved to be able to improve the autonomous navigation technology effectively.

• 한국ITS학회 논문지
• /
• 제19권2호
• /
• pp.135-148
• /
• 2020

현재 진행되고 있는 자율주행 관련 기술 발전은 실제 도로를 사용한 자율주행 테스트 시 다양한 안전사고가 발생할 가능성이 존재한다. 특히 자율주행자동차법 시행으로 실제 도로에서의 자율주행 실증은 증가할 것이며, 안전사고 예방을 위해 국내 도로환경에 적합한 운행설계영역에 대한 연구가 요구된다. 따라서 본 연구는 도심부 자율주행셔틀 실증을 위한 운행설계영역을 정의하고, 안양시 도심부도로를 중심으로 자율주행 운행 가능여부 등의 운행설계영역 평가를 실시한다. 본 연구의 자율주행 운행설계영역은 국내의 도로환경과 안전을 우선적으로 고려하였으며, 기하구조적 요인, 운영적 요인, 환경적 요인을 포함한다. 분석결과 노드기준에서는 노드유형 및 신호-통신 여부를 통해서 30개 노드에서 자율주행셔틀 실증이 가능한 것으로 분석되었다. 링크기준에서는 오전첨두(8-9시) 42개, 비첨두(12-13시) 39개, 그리고 오후첨두(18-19시) 40개 방향별 링크구간에서 자율주행 제한으로 분석되었다. 본 연구결과는 향후 자율주행 실증테스트가 이루어지는 도심부도로에서 사전 안전성 평가의 수범사례로 활용될 가치가 있다.