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

A research of motipn planning system for automated vehicles based on a prediction method of potential risk factors for urban driving.

Research Project

Project/Area Number 17K06252
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Research Field Intelligent mechanics/Mechanical systems
Research InstitutionNagoya University (2018-2019)
Tokyo University of Agriculture and Technology (2017)

Principal Investigator

Akagi Yasuhiro  名古屋大学, 未来社会創造機構, 特任准教授 (90451989)

Project Period (FY) 2017-04-01 – 2020-03-31
Project Status Completed (Fiscal Year 2019)
Budget Amount *help
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2019: ¥650,000 (Direct Cost: ¥500,000、Indirect Cost: ¥150,000)
Fiscal Year 2018: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2017: ¥2,990,000 (Direct Cost: ¥2,300,000、Indirect Cost: ¥690,000)
Keywords運転行動データベース / 自動運転 / マルコフ連鎖モンテカルロ / 安全性評価 / 運転行動分析 / ヒヤリハット / 交通事故分析 / サンプリング / リスク予測 / 運転支援 / 交通事故予測 / オントロジー / 知能機械 / 知能ロボティックス / 機械学習 / 高度道路交通システム(ITS) / 交通事故
Outline of Final Research Achievements

This research project consists of three part : to collect and analyse urban driving behavior data, a sampling method for dangerous driving behavior models from the driving data and applied the dangerous driving index to an automated driving system and conducted an urban driving experiment.
For the collection of driving behavior data, we proposed a new annotation method based on traffic ontology and increased the search efficiency by more than 10 times. In the sampling method of dangerous driving behavior, we constructed a method to extract only dangerous samples from driving behavior dataset and verified its effect using domestic and foreign dataset. In an urban driving experiment, a decision-making algorithm of an automated vehicle to start a right turn is implemented, and a subject experiment is conducted to investigate the degree of danger given to traffic participants. Then 5% of the subjects felt that the right turn behavior of the automated vehicle was dangerous.

Academic Significance and Societal Importance of the Research Achievements

本研究の成果のうち、人間の運転行動データから危険な運転行動の特徴を抽出し、その行動範囲を予測する手法は、自動運転車の行動判断機能の設計や、安全性評価試験のサンプルデータとして有用である。近年、自動走行機能をもつ車が次々と市販されている中で、その安全性を客観的に評価する手法の開発が求められており、本手法により試験サンプルを客観的かつ自動的に生成することで、課題解決に貢献できる点は社会的意義がある。また、自動運転車に搭載される行動判断機構がどのような指標により動作しているのかを客観的に示すことができる点は、自動運転車による公共的な交通サービスの実現に貢献できる。

Report

(4 results)
  • 2019 Annual Research Report   Final Research Report ( PDF )
  • 2018 Research-status Report
  • 2017 Research-status Report
  • Research Products

    (5 results)

All 2019 2018 2017

All Journal Article (1 results) (of which Peer Reviewed: 1 results,  Open Access: 1 results) Presentation (4 results) (of which Int'l Joint Research: 2 results)

  • [Journal Article] A Study on the Enhancement of Traffic Near-miss Incident Database for Various Usage2019

    • Author(s)
      赤木 康宏、大北 由紀子、那住 正樹、菅沢 深、毛利 宏
    • Journal Title

      Transactions of Society of Automotive Engineers of Japan

      Volume: 50 Issue: 2 Pages: 629-635

    • DOI

      10.11351/jsaeronbun.50.629

    • NAID

      130007618762

    • ISSN
      0287-8321, 1883-0811
    • Related Report
      2018 Research-status Report
    • Peer Reviewed / Open Access
  • [Presentation] A Risk-index based Sampling Method to Generate Scenarios for the Evaluation of Automated Driving Vehicle Safety*2019

    • Author(s)
      Akagi Yasuhiro、Kato Ryosuke、Kitajima Sou、Antona-Makoshi Jacobo、Uchida Nobuyuki
    • Organizer
      2019 IEEE Intelligent Transportation Systems Conference (ITSC)
    • Related Report
      2019 Annual Research Report
    • Int'l Joint Research
  • [Presentation] 多様な利用法を受容するためのヒヤリハットデータベースの機能拡張に関する研究2018

    • Author(s)
      赤木康宏
    • Organizer
      自動車技術会2018年春季大会学術講演会
    • Related Report
      2018 Research-status Report
  • [Presentation] 多様な利用法を受容するためのヒヤリハットデータベースの機能拡張に関する研究2018

    • Author(s)
      赤木康宏, 大北 由紀子, 那住正樹, 菅沢深, 毛利宏
    • Organizer
      自動車技術会
    • Related Report
      2017 Research-status Report
  • [Presentation] Ontology based collection and analysis of traffic event data for developing intelligent vehicles2017

    • Author(s)
      Y. Akagi
    • Organizer
      IEEE 6th Global Conference on Consumer Electronics
    • Related Report
      2017 Research-status Report
    • Int'l Joint Research

URL: 

Published: 2017-04-28   Modified: 2021-02-19  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi