Autonomous Driving Simulator Framework base on Low-cost 3D LIDAR
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Self-driving simulators have a higher cost-saving effect compared to reality in testing and verifying autonomous driving, but they require a lot of hardware devices due to high computer computation. In some cases, learning data necessary for autonomous driving may be obtained using a game. Games are used as low-cost simulators, but they are limited in simulating specific situations outside the game and obtaining necessary data. As another method, a simulation study of the virtual environment through a game engine is being conducted. However, in game engines, development costs are high because users have to model themselves. In particular, 3D LIDAR requires real-time acquisition of a precise distance of at least 10 Hz by shooting Ray at 360 degrees. Acquiring 3D LIDAR data in real time is a task that consumes a lot of graphics processing unit (GPU), so a low-cost 3D LIDAR simulator requires a low-cost 3D LIDAR simulation. In this paper, we propose a C++-based 3D LIDAR simulation framework using low computer operations. The proposed 3D LIDAR verified its performance in an unpaved map composed of many hills, and introduced a simple local path planning (LPP) generation method with 3D LIDAR generated in this paper by performance verification. We hope that the proposed 3D LIDAR framework will be actively used in autonomous driving fields that require low-cost real-time simulations.
Abstract
Self-driving simulators have a higher cost-saving effect compared to reality in testing and verifying autonomous driving, but they require a lot of hardware devices due to high computer computation. In some cases, learning data necessary for autonomous driving may be obtained using a game. Games are used as low-cost simulators, but they are limited in simulating specific situations outside the game and obtaining necessary data. As another method, a simulation study of the virtual environment through a game engine is being conducted. However, in game engines, development costs are high because users have to model themselves. In particular, 3D LIDAR requires real-time acquisition of a precise distance of at least 10 Hz by shooting Ray at 360 degrees. Acquiring 3D LIDAR data in real time is a task that consumes a lot of graphics processing unit (GPU), so a low-cost 3D LIDAR simulator requires a low-cost 3D LIDAR simulation. In this paper, we propose a C++-based 3D LIDAR simulation framework using low computer operations. The proposed 3D LIDAR verified its performance in an unpaved map composed of many hills, and introduced a simple local path planning (LPP) generation method with 3D LIDAR generated in this paper by performance verification. We hope that the proposed 3D LIDAR framework will be actively used in autonomous driving fields that require low-cost real-time simulations.
참고문헌 (19)
- LEE, Yun-Gil, "Establishing an intelligent virtual environment for autonomous driving of virtual characters", Korea Multimedia Society, 13(3), pp.34~42 (2009)
- 박해리, "HILS를 위한 시뮬레이션 프로그램 설계 기법", 한국군사과학기술학회지, 16(4), pp.435~440 (2013), 한국군사과학기술학회
- 임지웅, "자율주행 인공지능 알고리즘 연구를 위한 상용 게임 엔진 기반 초저가 드라이빙 시뮬레이터 개발", 한국ITS학회 논문지, 20(6), pp.242~263 (2021), 한국ITS학회[DOI]
- 이용범, "라이다를 이용한 장애물 검출 및 자동차 경로계획에 관한 연구", 한국지능시스템학회 논문지, 29(1), pp.30~35 (2019), 한국지능시스템학회
- Hong-ryul Jung, "Development of Simulator for Multiple Mobile Robots using Unreal Engine", Journal of Mechanical Science and Technology conference, pp.1256~1259 (2019)
- 김준, "3D LIDAR 반사율을 이용한 무인지상차량의 주행가능 후보 영역 분석", 대한기계학회논문집 A, 41(11), pp.1047~1053 (2017), 대한기계학회
- 황종락, "3D 라이다 센서와 도로 환경 지도의 비교를 통한자율주행 자동차 위치인식 기법 검증", 제어.로봇.시스템학회 논문지, 25(6), pp.557~564 (2019), 제어·로봇·시스템학회[DOI]
- 변예림, "라이다 기반 과속 방지턱 인식 및 지면 제거", 전자공학회논문지, 58(12), pp.65~73 (2021), 대한전자공학회
- Soo-yeon Kim, "A Autonomous Vehicle Localization System Based on Noise-free Point Cloud Map and LiDAR", Korea Automotive Engineering Society Autumn Conference and Exhibition, pp.542~545 (2020)
- 박재웅, "차량 모델 및 LIDAR를 이용한 맵 매칭 기반의 야지환경에 강인한 무인 자율주행 기술 연구", 제어.로봇.시스템학회 논문지, 17(5), pp.451~459 (2011), 제어·로봇·시스템학회
- In Yub Kim, "Environment Perception Using LiDAR Sensor Tilting Mechanism for Autonomous Vehicle", Journal of Mechanical Science and Technology conference, pp.3087~3091 (2013)
- Min Woo Jeong, "Object Perception Algorithm based on LiDAR for Autonomous Vehicle", Korea Automotive Engineering Society Autumn Conference, pp.639~642 (2017)
- 송현우, "무인선박의 자율운항을 위한 저가형 LiDAR센서 기반의 장애물 회피 시스템 구현", 전기학회논문지, 68(3), pp.480~488 (2019), 대한전기학회
- 백승범, "Solid-State LiDAR 기반 밭 농업용 자율주행 로봇의 두둑 감지를 통한 실시간 주행 경로 생성 알고리즘", 제어.로봇.시스템학회 논문지, 28(2), pp.146~152 (2022), 제어·로봇·시스템학회[DOI]
- 조든솔, "3D 자동차 시뮬레이터 기반 상호작용형 ADAS 개발 및 검증 프레임워크", 전기전자학회논문지, 22(4), pp.970~977 (2018), 한국전기전자학회[DOI]
- Kyungho Sohn, "A study on Development of PC-based Ship Handling Simulator", Korean Institute of Navigation and Port Research, 4(2), pp.25~33 (1998)
- SoonWoong Kwon, "A Study on the Improvement of Object Detection Algorithm for Autonomous Vehicles Using LiDAR based V2I", Korea Automotive Engineering Society Autumn Conference and Exhibition, pp.674~678 (2020)
- SHREINER, Dave, "OpenGL programming guide: the official guide to learning OpenGL, versions 3.0 and 3.1" (2009), Pearson Education
- YUN, In-Ho, "Function Development and Implementation Method of Editor for creating VR Contents", Proceedings of the Korea Information Processing Society Conference, pp.513~516 (2019), Korea Information Processing Society