• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2018 Fiscal Year Final Research Report

Research on Automated Driving in Urban Scenarios in Multiple Environments

Research Project

  • PDF
Project/Area Number 16H02843
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Perceptual information processing
Research InstitutionThe University of Tokyo

Principal Investigator

Kamijo Shunsuke  東京大学, 大学院情報学環・学際情報学府, 准教授 (70334357)

Project Period (FY) 2016-04-01 – 2019-03-31
Keywords自動運転 / デジタル地図 / 統合センシング
Outline of Final Research Achievements

An integration method of 3D-GNSS, IMU, and Vision sensor was developed in this research. This method has been proved to achieve 1.5m for positioning accuracy in urban canyon. Positioning method under the bridge of Metropolitan Expressway was developed. In this scenario, GNSS is invisible and face the difficulty of localization because of monotonous scape of the structures.
Automated method for map creation was developed with automated alignment method of SLAM data to airborne images. Such the created digital map achieved 25cm level accuracy in absolute coordinate. Finally, we proposed the specific vector data format of the digital map for autonomous driving, and proved that it maintain the equivalent accuracy of localization compared with the case employing point cloud data format.

Free Research Field

知能情報処理

Academic Significance and Societal Importance of the Research Achievements

自動運転の研究は国際的な競争と共同研究の両立が重要である。これまでの研究は、自身によるデモを主目的としたものが多いが、今後の自動運転の国際的普及には、科学的な見地からの技術標準化が不可欠である。本研究では、self-localizationを目的として、様々な劣悪な環境でのセンシングとデジタル地図の在り方について、自ら提案し可能性を検証したものである。本研究の成果は学術的にも社会的にも先進性が評価されてつつある。

URL: 

Published: 2020-03-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi