• 研究課題をさがす
  • 研究者をさがす
  • KAKENの使い方
  1. 課題ページに戻る

2019 年度 実施状況報告書

Driver behavior modeling and its application to a guidance-as-needed steering system for individualized lane change assistance

研究課題

研究課題/領域番号 19K20318
研究機関東京大学

研究代表者

王 正  東京大学, 生産技術研究所, 特任研究員 (20837497)

研究期間 (年度) 2019-04-01 – 2021-03-31
キーワードHaptic interface / Driver behavior modeling / Lane change assistance / Shared control / Guidance-as-needed
研究実績の概要

Our research focuses on modeling lane change behavior of individual driver and designing a guidance-as-needed steering system through haptic interface.
In FY 2019, our research achievements are summarized as follows:
1. A discrete lane change model based on gap acceptance was developed through a driving simulator experiment with a number of subjects.
2. A deep reinforcement learning based haptic guidance algorithm was developed and its effectiveness on individual driver steering assistance was verified by numerical simulations.
3. A driving simulator experiment with a number of subjects was conducted to evaluate a proposed intention-based haptic guidance system for lane change tasks. The results demonstrate that the designed system is adaptive and capable to improve driving safety and comfort.

現在までの達成度 (区分)
現在までの達成度 (区分)

2: おおむね順調に進展している

理由

1. A driving simulator experiment with a number of participants was conducted to collect the driving data, which are used to analyze the driver behavior, and a discrete lane change model based on gap acceptance was developed.
2. By real-time measuring driver eye movement, an intention-based haptic guidance system was designed to assist individual drivers for lane change tasks. The results from a driving simulator experiment with a number of participants demonstrate that the system is adaptive and capable to improve driving safety and comfort.
3. A driving simulator experiment with more complex traffic situation for a merging task has been designed and will be conducted in the next fiscal year. The haptic guidance system was implemented in an electric car for future real-vehicle experiments.

今後の研究の推進方策

In the next fiscal year, our research activities will focus on the following aspects:
1. The designed guidance-as-needed steering system will be evaluated in a more complex traffic situation by driving simulator experiments.
2. Real vehicle experiments will be conducted to evaluate the the effectiveness of guidance-as-needed steering system on lane change performance and driver acceptance.
3. The driver behavior measrued in the driving simulator and real-vehicle experiments will be analyzed for better understanding of driver's integration of visual and haptic information during a lane change task.

次年度使用額が生じた理由

In this fiscal year, we have focused on driver model development, numerical simulation, and driving simulator experiments. Thus, we purchased experimental equipment, hired research assistant for data analysis and recruited subjects for the experiments. Meanwhile, we used relatively less money for the travel. In the next fiscal year, we will conduct driving simulator and real vehicle experiments by recruiting subjects, and will spend travel expense to present the findings.

  • 研究成果

    (2件)

すべて 2019

すべて 雑誌論文 (1件) (うち国際共著 1件、 査読あり 1件) 学会発表 (1件) (うち国際学会 1件)

  • [雑誌論文] Comfort-oriented Haptic Guidance Steering via Deep Reinforcement Learning for Individualized Lane Keeping Assist2019

    • 著者名/発表者名
      Wang Zheng、Yan Zhanhong、Nakano Kimihiko
    • 雑誌名

      IEEE International Conference on Systems, Man and Cybernetics

      巻: - ページ: 4283-4289

    • DOI

      10.1109/SMC.2019.8914219

    • 査読あり / 国際共著
  • [学会発表] Comfort-oriented Haptic Guidance Steering via Deep Reinforcement Learning for Individualized Lane Keeping Assist2019

    • 著者名/発表者名
      Zheng Wang
    • 学会等名
      2019 IEEE International Conference on Systems, Man and Cybernetics (SMC)
    • 国際学会

URL: 

公開日: 2021-01-27  

サービス概要 検索マニュアル よくある質問 お知らせ 利用規程 科研費による研究の帰属

Powered by NII kakenhi