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

Continuous and Responsive Motion Generation for Virtual Humans

Research Project

Project/Area Number 21K12192
Research Category

Grant-in-Aid for Scientific Research (C)

Allocation TypeMulti-year Fund
Section一般
Review Section Basic Section 62040:Entertainment and game informatics-related
Research InstitutionKyushu Institute of Technology

Principal Investigator

Masaki Oshita  九州工業大学, 大学院情報工学研究院, 教授 (20363400)

Project Period (FY) 2021-04-01 – 2024-03-31
Project Status Completed (Fiscal Year 2023)
Budget Amount *help
¥4,030,000 (Direct Cost: ¥3,100,000、Indirect Cost: ¥930,000)
Fiscal Year 2023: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2022: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2021: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Keywords動作生成 / 深層学習 / 遷移動作 / 動作遷移 / 仮想人間 / コンピュータゲーム
Outline of Research at the Start

現在、コンピュータゲームなどの用途では、あらかじめモーションキャプチャ機器等を用いて作成された短い基本動作データを順番に再生することでキャラクタの連続的な動作を実現する方法が一般的に用いられている。この方法では、あらかじめ準備された動作間・タイミングでの動作遷移しか行うことができず、現実の人間のように現在の動作から次の動作への急激な動作遷移を含むような即応的な動作生成は実現できない。本研究で開発する手法では、高レベルの足や重心の軌道を生成する機械学習モデルと、低レベルの全身動作生成のための機械学習モデルを組み合わせることで、連続的・即応的な動作生成を実現する。

Outline of Final Research Achievements

In this research project, we worked on the development of a method for generating transitional motions that connect between input motions in order to realize continuous and immediate movement generation for virtual humans. We worked on the development of methods using two approaches: a method for motion generation using foot and hip trajectory data as inputs and outputs for deep learning, and a method for motion generation using posture and motion data as inputs and outputs for deep learning models. Although we were unable to achieve an effective method compared to conventional methods, we developed a crowd simulation method for navigating virtual humans using deep learning with surrounding situation images as input and output.

Academic Significance and Societal Importance of the Research Achievements

深層学習を用いて遷移動作を生成する方法として、研究開発当初に計画していた足や腰の軌道データを深層学習の入出力として動作生成を行う手法と、姿勢・動作データを深層学習モデルの入出力として動作生成を行う方法の、両方のアプローチを示した。また、本研究で開発した深層学習による移動制御手法は、コンピュータアニメーションやメタバースなどでの、群衆のアニメーション生成への応用が期待される。

Report

(4 results)
  • 2023 Annual Research Report   Final Research Report ( PDF )
  • 2022 Research-status Report
  • 2021 Research-status Report
  • Research Products

    (5 results)

All 2024 2023 2022

All Journal Article (2 results) (of which Peer Reviewed: 2 results) Presentation (3 results) (of which Int'l Joint Research: 3 results,  Invited: 1 results)

  • [Journal Article] Crowd Simulation Using Velocity Field Map and LSTM Neural Network2023

    • Author(s)
      Yuanyuan Peng, Masaki Oshita
    • Journal Title

      The 3rd International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) 2023

      Volume: 3 Pages: 165-169

    • DOI

      10.1109/icicyta60173.2023.10429028

    • Related Report
      2023 Annual Research Report
    • Peer Reviewed
  • [Journal Article] Crowd Simulation with Feedback Based on Locomotion State2022

    • Author(s)
      Oshita Masaki, Harazono Jumpei, Yamamoto Kunio
    • Journal Title

      International Conference on Cyberworlds 2022

      Volume: NA Pages: 118-121

    • DOI

      10.1109/cw55638.2022.00026

    • Related Report
      2022 Research-status Report
    • Peer Reviewed
  • [Presentation] Physical Simulation of Human Body Model Considering Joint Range of Motion2024

    • Author(s)
      Shuhei Era, Kunio Yamamoto, Masaki Oshita
    • Organizer
      The 8th IIEEJ International Conference on Image Electronics and Visual Computing (IEVC 2024)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Editing Camera Work with Virtual Camera and 3D Printed Figures2024

    • Author(s)
      Shuntaro Kono, Kunio Yamamoto, Masaki Oshita
    • Organizer
      The 8th IIEEJ International Conference on Image Electronics and Visual Computing (IEVC 2024)
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research
  • [Presentation] Making a Connection Between Yourself and Your Avatar in Metaverse2023

    • Author(s)
      Masaki Oshita
    • Organizer
      The 3rd International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) 2023
    • Related Report
      2023 Annual Research Report
    • Int'l Joint Research / Invited

URL: 

Published: 2021-04-28   Modified: 2025-01-30  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi