English  |  正體中文  |  简体中文  |  Items with full text/Total items : 18074/20272 (89%)
Visitors : 2218711      Online Users : 486
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://ir.cnu.edu.tw/handle/310902800/33568


    標題: 基於機器學習之適應性健身虛擬實境運動開發
    Adaptive Virtual Reality game development based on machine learning
    作者: 劉川綱
    江啟惠
    貢獻者: 嘉藥學校財團法人嘉南藥理大學資訊多媒體應用系
    關鍵字: 機器學習
    虛擬實境
    machine learning
    virtual reality
    日期: 2020
    上傳時間: 2022-01-13 16:21:54 (UTC+8)
    摘要: 本計畫主要要發展一套智慧型虛擬實境運動健身軟體應用程式,該計畫預計開發的運動健身程式可以借助虛擬實境不受時空限制之特性,利用VR創新的人工智慧仿生技術結合樂齡健身應用,發展創新的運動休閒新應用。該計畫中,我們設計一個運動健身主題-羽球遊戲,該項運動項目老少皆宜,該項遊戲會利用虛擬實境的追蹤感測器去追蹤羽球拍的揮動的力道與方向,在此運動項目中會擬真去模擬對手的擊拍速度以及技能,並且加入評分以及賽制制度增加運動真實性以及刺激感,並且為了可以切合運動者之運動強度與習性,計畫也將利用機器學習去追縱觀察運動者之運動強度與反應力,且此調整對手的強度,除此之外也可以因應運動者的運動習性進行各種關節的運動強度,本計畫重要的實務創新就是利用機器學習導入到遊戲中,目前最大遊戲引擎Unity 3D在2017年 9月發布了機器學習的套件,稱為ML-Agent,這個套件中提供遊戲中的各個非玩家操控的角色物件可以類似人類學習遊戲方式的各種機器學習機制,這樣的運動健身方式可以解決樂齡者在運動時的時空限制,亦可達到健身效果,透過計畫,合作廠商也可以掌握此項技術的應用方式與模式,提供未來開發類似之創新應用也很好的參考依據,真實達到?實產、學合作效益。
    This project is to develop a smart virtual reality exercise game. This game employs the features of virtual reality, a free and wide virtual environment without limited cost and space. This project integrates Artificial intelligence and virtual reality to propose an aging exercise game. This aging exercise game is developed based on badminton game, which is popular for many people in Taiwan. This project makes use of trackers to follow the trace of badmintom racket and the power of the player. Furthermore, the exercise game in this project can imitate the rules of real game. In order to adapt to the characteristics of the players, the game employs machine learning to learn the behavior of the player and to predict the energy of this player. After learning the characteristics of this player, the game can modify the strength of excise game in order to fit the capacity of the aging players. This project also utilizes a famous game engine, Unity, to design this excise game. This game engine has a machine learning tool package, ML-Agent, which contains many machine learning algorithms. This project will combine the resource of academia and industry to develop this novel game. In the future, the result of this project can also provide a very good case for Industry-University Cooperation.
    關聯: 計畫編號:MOST109-2622-E041-005
    計畫年度:109
    執行起迄:2020-11~2021-10
    Appears in Collections:[多媒體與遊戲發展系] 科技部計畫
    [資訊管理系] 科技部計畫

    Files in This Item:

    File Description SizeFormat
    1092622E041005(第1年).pdf917KbAdobe PDF562View/Open
    基於機器學習之適應性健身虛擬實境運動開發2.pdf917KbAdobe PDF269View/Open


    All items in CNU IR are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback