Cited 0 time in webofscience Cited 0 time in scopus

HD-MAP 기반 Vectormap(Road Network Map) 구조를 활용한 주행 판단 및 행동 상태 생성 모델 설계

Title
HD-MAP 기반 Vectormap(Road Network Map) 구조를 활용한 주행 판단 및 행동 상태 생성 모델 설계
Translated Title
Design of a Model for Driving Decision and Behavior State Generation Using HD-MAP Based Vectormap(Road Network Map) Structure
Authors
박성민이진희황종락아재이 쿠마권순
DGIST Authors
이진희; 권순
Issue Date
2019-11-16
Citation
2019 대한임베디드공학회 추계학술대회, 264-266
Type
Conference
ISBN
9788996655312
Abstract
As research on self-driving technologies has become more active in recent years, technologies that are applied to self-driving decision have been actively researched through structural transformation of HD-MAP, which is static information. HD-MAP is a road map that shows static characteristics of a road (lane, road center, cross walk, traffic light signal, and stop line) through drawing after converting Point Cloud Data obtained by Multi Mapping System(MMS) into Point Cloud Data with Coordinate System. These HD-MAP are converged with V2X(Vehicle to Everything) technology and are used for LDM(Local Dynamic Map). In addition, they are useful in a variety of areas from driving judgement to creating Waypoint, which tests the reliability of perception data based on its static position and the results. This paper introduces the Vectormap with MAP structure available in self-driving and presents the method of Vectormap structuralization based on HD-MAP, and the model of driving decision and behavior state generation using it.
URI
http://hdl.handle.net/20.500.11750/14149
Publisher
대한임베디드공학회
Related Researcher
  • Author Kwon, Soon  
  • Research Interests computer vision; deep learning; autonomous driving; parallel processing; vision system on chip
Files:
There are no files associated with this item.
Collection:
Division of Automotive Technology2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE