• I am ...

    Yuki Okafuji / 岡藤 勇希

    Ph. D. in Engineering / 博士(工学)


    Assistant Professor at Ritsumeikan University


    Playful Lab.





    Human Robotics Lab.​



    E-mail: yokafuji [at] fc.ritsumei.ac.jp

  • RESEARCH on Vehicle Control / Driving Behavior

    Automated driving control based on optical flow



    In order to construct human-like automated driving systems, we focused on optical flow that is a velocity vector generated by the surrounding environment. Humans can perceive the direction of self-motion based on optic flow, and they can track a target path by matching their direction to a point of "they want to go" on the target path. This is a human (animal)-like control method. Therefore, we modeled optic flow generated by the vehicle state and we verified that the modeling result can strictly reflect the direction of self-motion that has been only verified through the experiments. Then, we introduced a mathematical model of optic flow into the vehicle steering control based on a nonlinear control method in order to construct human-like control method. From the results of the simulations and vehicle experiments, we confirmed this method is effective for the automated steering controller and can reproduce human's steering behaviour in terms of steering accuracy.

    Examine the influence of optic flow for driving behavior



    From the results of our proposed automated driving control method, we got a hypothesis: the usefulness of a region of optic flow (for instance, far and near, or central and peripheral vision) for driver's steering behavior is not consistent. Then, we made a unique simulation environment that can selectively mask either the optic flow or the road edge information to analyze driving behavior. Then, we verified how this two information affects the steering performance of the driver within the scope of Two-point steering model. Amazingly, a part of the results is the same as the results produced by the optical flow control. This conclusion could give us some intuition: driver models capturing driver characteristics can figure out new driver behavior even if we do not conduct the psychological experiments.

    Analyzing the driver's gaze behavior



    Drivers’ gaze behaviors in naturalistic and simulated driving tasks have been investigated for decades. Many research studies focus on the road geometrical environment to explain a driver’s gaze. On the other hand, we focused on vehicle states such as optical flow and the vehicle position to explain the driver's gaze behavior. We show that drivers' gaze strategy can be interpreted by optical flow theory that is a method to quantify the extent to which they can perceive the future path of the vehicle. In addition, we assume that the drivers' gaze behavior is influenced by two aspects: the importance of Lane Keeping and Route Prediction. Then, we modeled the driver's gaze behavior in order to apply for constructing advanced intelligent vehicle systems. The results can simulate the driver's gaze behavior.

    Investigation of visual region influencing driving behavior using machine learning



    One aspect of the drivers' cognitive behavior is to understand what information in which visual regions are used for steering/throttle control. In previous research, these behaviors were analyzed using a special simulator environment. Therefore, we proposed a CNN model with human physical characteristics, which can analyze cognitive behavior in a real environment. We have established a new method for human analysis by verifying that the analytical results by the proposed model can correctly reflect human cognitive behavior even in machine learning models that are considered to be black boxes.

  • RESEARCH on Human Robot Interaction

    Human motion prediction to reduce mechanical delays of robot



    Face-to-Face contact is an important functional behavior for Humanoid robots. However, it is difficult due to the mechanical delay to generate Face-to-Face contact without delay. So, we make robot motion with little/no delay during face-to-face contact using the predicted human face position by both of the fast machine learning methods and conventional image processing methods.

    Robot behavior to stop pedestrians in commercial facilities



    In order to spread the robot in the real world, it is necessary to create a robot that can be used by humans. However, it is known that even if a robot is implemented in a real environment, robots tend to be ignored. Therefore, we installed a robot in a shopping mall and investigated what kind of robot behavior could attract a passerby and stop the passerby.



    • June 2017 - November 2017, Visiting Researcher, University of Leeds, UK
    • August 2018 - September 2018, Research Intern, CyberAgent AI Lab
      研究インターン,株式会社サイバーエージェント AI Lab
    • April 2018 - September 2018, JSPS Research Fellow (DC2), Kobe University
      日本学術振興会 特別研究員(DC2)(受入研究機関:神戸大学)
    • October 2018 - March 2019, JSPS Research Fellow (PD), Ritsumeikan University
      日本学術振興会 特別研究員(PD)(受入研究機関:立命館大学)
    • October 2018 - March 2019, Research Scientist, CyberAgent AI Lab
      リサーチサイエンティスト,株式会社サイバーエージェント AI Lab
    • November 2018 -March 2019, Visiting Researcher, Osaka University
    • April 2019 - Current, Assistant Professor, Ritsumeikan University


    • April 2007 - March 2012, Associate's Degree, Department of Mechanical and Electrical Engineering, National Institute of Technology, Tokuyama College, Japan
      徳山工業高等専門学校 機械電気工学科
    • April 2012 - March 2014, Bachelor's Degree, Department of Mechanical Engineering, Faculty of Engineering, Kobe University, Japan
      神戸大学 工学部機械工学科
    • April 2014 - September 2015, Master's Degree, Department of Mechanical Engineering, Graduate School of Engineering, Kobe University, Japan
      神戸大学 工学研究科機械工学専攻 修士課程
    • October 2015 - September 2018, Ph. D. Degree, Department of Mechanical Engineering, Graduate School of Engineering, Kobe University, Japan
      神戸大学 工学研究科機械工学専攻 博士課程
    • April 2016 - September 2018, Research Student, Graduate School of Science and Engineering, Ritsumeikan University, Japan
      立命館大学 理工学研究科 特別研究学生
    • September 2016 - February 2017, Visiting Research Student, Institute for Transport Studies, Faculty of Environment, University of Leeds, UK


    1. 山口遊,岡藤勇希,和田隆広,村上一臣,石田裕之,”路面描画に影響されるドライバの注視特性の検証”,自動車技術会論文集 (to appear)
    2. Y. Okafuji, T. Sugiura, R. Osugi, C. Zhang, and T. Wada, “A machine learning-based approach to analyze information used for steering control,” IEEE Access, vol. 9, pp. 94239-94250, 2021
    3. C. Zhang, Y. Okafuji, and T. Wada, “Reliability evaluation of visualization performance of convolutional neural network models for automated driving,” International Journal of Automotive Engineering, Vol. 12, No. 2, pp. 41-47, 2021, DOI: http://doi.org/10.20485/jsaeijae.12.2_41
    4. 尾杉竜正,岡藤勇希,和田隆広,”深層学習を用いた車両の速度制御に関するドライバの認知特性の解析”,自動車技術会論文集,Vol. 52, No. 2, pp. 355-362, 2021, DOI: 10.11351/jsaeronbun.52.355
    5. Y. Okafuji, T. Fukao, “Theoretical interpretation of drivers' gaze strategy influenced by optical flow,” Scientific Reports, 11, 2389, 2021, DOI: 10.1038/s41598-021-82062-1
    6. Y. Okafuji, J. Baba, J. Nakanishi, I. Kuramoto, K. Ogawa, Y. Yoshikawa, H. Ishiguro, “Can a humanoid robot continue to draw attention in an office environment?,” Advanced Robotics, Vol. 34, No. 14, pp. 931-946, 2020, DOI: 10.1080/01691864.2020.1769724
    7. Y. Okafuji, C. D. Mole, N. Merat, T. Fukao, Y. Yokokohji, H. Inou, and R. M. Wilkie, “Steering bends and changing lanes: the impact of optic flow and road edges on two point steering control,” Journal of Vision, Vol. 18. No. 14, 2018, DOI: 10.1167/18.9.14
    8. Y. Okafuji, T. Fukao, Y. Yokokohji, H. Inou, “Design of a preview driver model based on optical flow,” IEEE Transaction on Intelligent Vehicles, Vol. 1, No. 3, pp.266-276,2016, DOI: 10.1109/TIV.2017.2658188
    9. Y. Okafuji, T. Fukao, H. Inou, “Development of automatic steering system by modeling human behavior based on optical flow,” Journal of Robotics and Mechatronics, Vol. 27, No. 2, pp.136-145, 2015, DOI: 10.20965/jrm.2015.p0136
    10. 伊能寛,深尾隆則,戸塚誠司,岡藤勇希,”オプティカル・フロー・モデルを利用した操舵制御システムの開発”,自動車技術会論文集,Vol. 46, No. 2, pp.443-448, 2015, DOI: 10.11351/jsaeronbun.46.443

    International Conference

    1. [Oral] Y. Okafuji, J. Baba, J. Nakanishi, J. Amada, Y. Yoshikawa, H. Ishiguro, “Persuasion Strategies for Social Robot to Keep Humans Accepting Daily Different Recommendations,” IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Virtual Conference, September 2021

    2. [Oral] J. Amada, Y. Okafuji, T. Wada, J. Baba, J. Nakanishi, Y. Yoshikawa, “Behavioral Changes in Passersby by Expanding Embodiment of a Calling Robot,” IEEE International Conference on Robot & Human Interactive Communication (RO-MAN), Virtual Conference, August 2021

    3. [Oral] C. Zhang, Y. Okafuji, T. Wada, “Evaluation of visualization performance of CNN models using driver model,” IEEE/SICE International Symposium on System Integration (SII), Virtual Conference, January 2021

    4. [Oral] Y. Okafuji, T. Sugiura, T. Wada, “Preliminary investigation of visual information influencing driver’s steering control based on CNN”, IEEE International Conference on Systems, Man, and Cybernetics (SMC), Virtual Conference, October 2020

    5. [Oral] R. Ukita, Y. Okafuji, T. Wada, “A simulation study on lane-change control of automated vehicles to reduce motion sickness based on a computational model”, IEEE International Conference on Systems, Man, and Cybernetics (SMC), Virtual Conference, October 2020

    6. [Oral] T. Wada, J. Kawano, Y. Okafuji, A. Takamatsu, M. Makita, “A computational model of motion sickness considering visual and vestibular information”, IEEE International Conference on Systems, Man, and Cybernetics, Virtual Conference (SMC), October 2020

    7. [Oral] Y. Okafuji, T. Wada, T. Sugiura, K. Murakami, H. Ishida, “Drivers' gaze behaviors are influenced by vehicle position”, 64th Annual Meeting of Human Factors and Ergonomics Society (HFES), Virtual Conference, October 2020

    8. [Poster] Y. Okafuji, Y. Ozaki, J. Baba, A. Kitahara, J. Nakanishi, K. Ogawa, Y. Yoshikawa, H. Ishiguro, “Please listen to me: How to make passersby stop by a humanoid robot in a shopping mall”, ACM/IEEE International Conference on Human-Robot Interaction (HRI), Cambridge, UK, March 2020

    9. [Oral] Y. Okafuji, T. Fukao, H. Inou, “Theoretical interpretation of driver’s gaze considering optic flow and seat position”, IFAC Symposium on Analysis, Design, and Evaluation of Human-Machine Systems (IFAC-HMS), Tallinn, Estonia, September 16-19, 2019

    10. [Oral] C. Mole, G. Markkula, O. Giles, Y. Okafuji, R. Romano, N. Merat, R. Wilkie, “Drivers fail to calibrate to optic flow speed changes during automated driving”, Driving Assessment Conference, New Mexico, USA, June 24-27, 2019

    11. [Demo] Y. Okafuji, J. Baba, J. Nakanishi, “Face-to-Face contact method for humanoid robots using face position prediction”, ACM/IEEE International Conference on Human-Robot Interaction (HRI), Daegu, Korea, March 2019

    12. [Oral] Y. Okafuji, C. D. Mole, R. M. Wilkie, N. Merat, “Examining how driver steering behaviour is affected by optic flow after resuming control from a highly automated vehicle”, The Human Factors and Ergonomics Society Europe Annual Meeting (HFES Europe), Rome, Italy, September 2017
    13. [Oral] Y. Okafuji, T. Fukao, Y. Yokokohji, H. Inou, “Optical flow-based control for automatic steering systems”, 2015 IEEE/SICE International Symposium on System Integration (SII2015), Japan, December 2015, DOI: 10.1109/SII.2015.7405027
    14. [Oral] H. Inou, T. Fukao, S. Totsuka, Y. Okafuji, “Development of automatic steering system based on optical flow model”, 12th International Symposium on Advanced Vehicle Control (AVEC’14), Japan, September 2014

    Invited Talks

    1. 岡藤勇希,”自動運転に向けたドライバの視覚特性解明”,産学連携テックミーティング,202X年XX月 (to appear)
    2. 岡藤勇希,”実社会で活動するサービスロボットの研究”,ふれデミックカフェ@KRP,2020年11月
    3. 岡藤勇希,”Convolutional Neural Networkを用いたドライバ操舵に影響する視覚情報の理解”,自動車技術会ヒューマンファクター部門委員会「ヒューマンファクター研究最前線」,2020年8月
    4. 岡藤勇希,”オプティカルフロー理論に基づいたドライバの注視点の解明”,自動車技術会 車両運動性能委員会,2020年1
    5. 岡藤勇希,”オプティカルフローに着目した自動車制御と人間の行動解析”,日本バーチャルリアリティ学会 第14回テレイグジスタンス研究会,2019年7月
    6. 岡藤勇希,”オプティカルフローに基づいたドライバモデル・ドライバの特性解析に関する研究”,自動車技術会 第5回ヒューマンファクター部門委員会,2018年12月

    Technical Report

    1. 岡藤勇希,” 自動/手動運転の切り替わり時におけるオプティックフローに影響されるドライバの操舵特性の解析”, 神戸大学大学院工学研究科・システム情報学研究科紀要,第9号,2017
    2. 伊能寛,深尾隆則,戸塚誠司,岡藤勇希,”オプティカル・フロー・モデルを利用した操舵制御システムの開発”,デンソーテクニカルレビュー,Vol. 20, pp.123-130, 2015

    Domestic Conference (in Japan)

    1. [Oral] 岡藤勇希,山口遊,和田隆広,村上一臣,石田裕之,”Potential Attentionを用いたHMI使用時のドライバの注視推定”,自動車技術会秋季大会学術講演会,2021年10月
    2. [Oral] 伊藤智樹,岡藤勇希,和田隆広,”主成分分析を用いたドライバの注視位置推定”,自動車技術会秋季大会学術講演会,2021年10月
    3. [Oral] 山口遊,岡藤勇希,和田隆広,村上一臣,石田裕之,”路面描画に影響されるドライバの注視特性の検証”,自動車技術会春季大会学術講演会,2021年5月
    4. [Oral] 天田穣一朗,岡藤勇希,和田隆広,馬場惇,中西惇也,吉川雄一郎,”呼びかけロボットの身体性拡張による通行人の行動促進”,HAIシンポジウム,2021年3月
    5. [Poster] 河野隼一郎,和田隆広,岡藤勇希,高松敦,牧田光弘,”視覚運動と頭部運動を入力とする動揺病計算モデル”,計測自動制御学会 システム・情報部門 学術講演会(SSI),2020年10月
    6. [Oral] 岡藤勇希,和田隆広,村上一臣,”予測-車線維持を考慮したポテンシャルによるドライバの注視行動の理解”,自動車技術会秋季大会学術講演会,2020年10月
    7. [Oral] 尾杉竜正,岡藤勇希,和田隆広,”深層学習を用いた車両の速度制御に関するドライバの認知特性の解析”,自動車技術会秋季大会学術講演会,2020年10月
    8. [Oral] 杉浦敏仁,岡藤勇希,和田隆広,”Convolutional Neural Networkを用いたドライバ操舵に影響する視覚情報の理解”,自動車技術会春季大会学術講演会,2020年5月
    9. [Poster] 浮田凌佑,岡藤勇希,和田隆広,”車両の追従軌道を考慮した動揺病軽減のためのレーンチェンジ軌道生成手法”,計測自動制御学会 システム・情報部門 学術講演会(SSI),2019年11月
    10. [Oral] 岡藤勇希,深尾隆則,”オプティカルフロー理論に基づいたドライバの注視点の解明”,自動車技術会秋季大会学術講演会,2019年10月
    11. [Poster] 岡藤勇希,​馬場惇,中西惇也,倉本到,”ヒューマノイドロボットのための顔位置予測を用いた人の顔追従制御”,HAIシンポジウム,2019年3月
    12. [Oral] 岡藤勇希,深尾隆則,伊能寛,”座席位置の影響を考慮したドライバの注視点に関する理論的解釈”,自動車技術会秋季大会学術講演会,2018年10月​
    13. [Poster] ​岡藤勇希,深尾隆則,横小路泰義,伊能寛,”車両の横方向制御の相関に関する考察”,ロボティクス・メカトロニクス講演会 (ROBOMECH2017),2017年5月
    14. [Oral] ​岡藤勇希,深尾隆則,横小路泰義,伊能寛,”オプティカルフローに基づく自動操舵のための実環境計測を考慮したシミュレータ構築”,システム制御情報学会研究発表講演会 (SCI’16),2016年5月
    15. [Oral] ​岡藤勇希,深尾隆則,横小路泰義,伊能寛,”カメラ運動を考慮したオプティカルフローに基づく自動操舵システム”,第58回自動制御講演会,2015年11月
    16. [Oral] ​岡藤勇希,深尾隆則,横小路泰義,伊能寛,”オプティカルフローに基づいた前方注視モデルの理解と応用”,システム制御情報学会研究発表講演会 (SCI’15),2015年5月
    17. [Poster]岡藤勇希,深尾隆則,伊能寛,”オプティカルフローに基づいた自動操舵システム”,ロボティクス・メカトロニクス講演会 (ROBOMECH2014),2014年5月

    18. [Oral] 伊能寛,深尾隆則,戸塚誠司,岡藤勇希,”オプティカル・フロー・モデルを利用した操舵制御システムの開発”,自動車技術会春季講演会,2014年5月

    Other Talks

    1. 岡藤勇希,”自動運転に向けたドライバの視覚特性解明”,「人工知能と記号学」R-GIROシンポジウム,2020年2月
    2. Y. Okafuji,”Driving Behavior Analysis based on Psychological Model”,Colloquium in R-GIRO Project AI and Semiotics,December, 2017


    1. March 2019, Most Impressive Poster Award in HAI Symposium 2018
      HAIシンポジウム2018 最優秀ポスター賞
    2. June 2017, Kobe University Outstanding Student Award
    3. May 2016, The Excellent Student Presentation in the 60th Annual Conference of the Institute of Systems, Control, and Information Engineers
      第60回システム制御情報学会研究発表講演会 SCI学生発表賞
    4. May 2016, ISCIE Encouragement Award from the Institute of Systems, Control and Information Engineers
      システム制御情報学会賞 奨励賞
    5. March 2016, Miura Prize (Excellent Postgraduate Student Award) from The Japan Society of Mechanical Engineers
      日本機械学会 三浦賞
    6. December 2015, IEEE/SICE International Symposium on System Integration, Best Paper Award Finalist
    7. March 2014, Isamu Yamashita Prize (Excellent Undergraduate Student Award) from The Japan Institute of Marine Engineering
      日本マリンエンジニアリング学会 山下勇賞​

    8. Feb 2020, Excellent poster award in R-GIRO Interim report meeting
      優秀ポスター賞,立命館大学R-GIRO「次世代人工知能と記号学の国際融合研究拠点」 2019年度中間報告シンポジウム(杉浦敏仁)
    9. Nov 2019, SSI Research Encouragement Award in SSI2019
      計測自動制御学会 システム・情報部門学術講演会2019 研究奨励賞(浮田凌佑)
    10. May 2014, JSAE Annual Congress (spring) Excellent Technical Paper Presentation Awards


    Principal Investigator / 研究代表

    1. 2020 - 2023, JSPS Grant-in-Aid for Young Scientists
      科学研究費助成事業 若手研究
    2. 2020 - 2021, SUZUKI FOUNDATION
      スズキ財団 若手科学技術研究助成
    3. 2018 - 2019, JSPS Research Fellowship
      日本学術振興会 特別研究員奨励費
    4. 2016 - 2017, Kobe University, Graduate School of Engineering, Premium Program
      神戸大学大学院工学研究科 プレミアム・プログラム
    Co-Investigator / 研究分担
    1. 2020 - 2023, Adaptable and Seamless Technology transfer Program through target-driven R& D (A-STEP)
      科学技術振興機構 研究成果最適展開支援プログラム(A-STEP)
    2. 2017 - 2022,立命館大学R-GIRO「次世代人工知能と記号学の国際融合研究拠点」


    1. October 2020, submitted
    2. August 2019, submitted