Tuesday, September 15, 2026

HW#1

Use Claude cowork Opus 5Max or ChatGPT-6 Astra

 課堂練習 

Deadline: This Saturday at 23:59

Send all the share links to  me chang212@gmail.com by email with subject HW#1  [your id, your name]

How to share a link


conduct a research given drone research directions

literature survey
SOTA
methods
coding
Stats
benchmark with SOTA apples-to-apples
Write a Paper with figs/tabs (or simply a proposal)

Tuesday, May 26, 2026

場域應用與服務設計 Syllabus 2026 Fall

張耀仁教授

課程規定

  1. 所有主題皆以 AI 輔助,不需自行撰寫底層程式。
  2. 為了教學與示範、便於助教支援、確保功能與介面一致、評分與範例可重現,本課程限定使用 Claude AI。有特殊原因必須使用其他 AI 者,需在選課前與老師商量。

課程進度

日期 主題
9/15Introduction
9/22Introduction
9/29Prompts
10/6Visualization
10/13Analog IC Design
10/20Robot: 3D Models
10/27、11/3Robot: Navigation for Robots and BLV (Blind and Low Vision)
11/10期中考,暫停上課
11/17Robot: 環境安全檢測與評估視覺化
11/24、12/1RL
12/8、12/15、12/22World Model for AGI

各週教材

9/15 Introduction

9/22 Introduction

9/29 Prompts

10/6 Visualization

10/13 Analog IC Design

10/20 Robot: 3D Models

10/27   Robot: Navigation for Robots and BLV 


11/3 Robot: 環境安全檢測與評估視覺化


11/10 期中考,暫停上課一次


11/17 Prediction of Motion


    11/24 Machine Learning for Asset Management

    12/8, 12/15, 12/22 World Model for Artificial General Intelligence (AGI)

    End of Class


    Backup 閱讀

    Tuesday, January 27, 2026

    學生回饋意見

      (稍微改寫去可辨視化)


    Monday, January 26, 2026

    AI 戰爭模擬

    使用對局理論(game theory) 模擬台海衝突

    3D 強化版

    台海衝突賽局理論分析模擬器 (連結)
    • 多方參與者:中國、台灣、美國、日本
    • 情境模擬:封鎖、入侵、灰色地帶、導彈打擊
    • 策略互動與升級風險分析
    台灣AI防禦戰略模擬 (連結)
    • 敵方導彈攻擊與攔截系統
    • 升級機制:無人機部署→雷達啟動→導彈發射
    俄羅斯無人機攻擊 vs 烏克蘭防空模擬 (連結)
    • 3D整合空戰防禦模擬系統
    • 攻擊與防禦系統的動態互動

    Tuesday, December 16, 2025

    HW#13 Reinforcement Learning (RL) 3

      自行決定是否做作業,做的話任選一題即可


    1. 市區交通模擬,如何控制燈號以增進運輸量 (RL)

     (credit: 與專題生共同創作)






     2. Use RL to train Submarine to avoid unmanned torpedo from attaching and attacking


    hi accomp share (artifact)


    3. Use RL to optimize a Manufacturing Process overcoming a failure,  artifact (share) (inspired by Edward Chang)






    4. Use RL to train inverted pendulum



    5. Train the robot in the following scenario to cross the road.

    scenario setting artifact









    6. Use RL to train submarine maneuvers







    7. Use TL to train the AI manager of  Supermarket (share)



    8. Use RL to train F1 racing


    9. Use RL to train TESLA FSD.