人工智慧導論
Introduction to Artificial Intelligence (Robotics)
| 節 | 週一 | 週四 |
|---|---|---|
5 13:20–14:10 | 人工智慧導論 EE632 2 節連堂 | |
6 14:20–15:10 | ||
A 18:30–19:20 | 人工智慧導論 EE632 3 節連堂 | |
B 19:30–20:20 | ||
C 20:30–21:20 |
* 根據陽明交大上課時間表所列
本課程是一門為AI機器人領域設計之基礎課程,強調機器人領域重要之人工智慧演算法,並以Python與演算法實作為主,將使用Jupyter Notebook進行互動式做中學,讓課程所學習之演算法可以快速轉移至實體機器人上實現。本課程為導論課程,將以主題式介紹機器人各種應用領域,包括:教育、救難、輔助、水域、機器手臂等。
C++或Python基礎物件導向程式語言能力,包含迴圈、陣列、類別的宣告與使用 Basic Probability, Linear Algebra, Data Structure
本課程將分為兩部分: 1EF時段(EE632教室): 1-1 課程講授(Lecture) 1-2 Python程式演練(請參考:https://github.com/aimacode/aima-python) 學生將分組進行課程討論,每位同學上課須攜帶筆電。 本課程將使用Google Colab。 4IJK時段: 本學期共六次,安排實作、實體機器人展示,強調課程介紹之演算法如何用於機器人任務, 或以主題式介紹機器人相關研究、競賽分享與深度討論。 課程網路資料夾: https://drive.google.com/drive/u/1/folders/1-KJK5rbyZaV2eqlt2eKCM-AuIOE8S4ck
1. 學期作業: There are in-class tutorials (in Python and Jupyter Notebook), and each includes 3 checkpoints/exercises. 2. 期中報告: 個人報告,繳交書面報告與一分鐘影片 3. 期末考試: 3.評量方法: - Class Participation 10 (%) - In-class tutorials (Python and Jupyter Notebook checkpoints/exercises) 60 (%) - Midterm Report 20 (%) - Final Exam 10 (%)
- AI Agent
- Robot Perception & Machine Learning
- Robot Control and Reinforcement Learning
| 週次 | 主題 |
|---|---|
| 第 1 週 | [Lec] Introduction to Artificial Intelligence |
| 第 2 週 | [Lec] Guest Lecture: Prof. Young - Introduction to Robotics [Lab] Ubuntu, Git, Docker |
| 第 3 週 | [Lec] AI Agents [Lab] Python, OpenCV, Colab 中秋節無課程 |
| 第 4 週 | [Lec, Lab] Search BFS, DFS |
| 第 5 週 | [Lec, Lab] Robot Navigation with A* Search |
| 第 6 週 | [Lec, Lab] OpenAI Gym, Taxi Problem, Q-Learning [Lab] Real Robot Navigation with Locobot |
| 第 7 週 | [Lec] Robot Perception, [Lab] Machine Learning Overview (MLP) |
| 第 8 週 | Midterm Week, No Class. PyTorch Material Available |
| 第 9 週 | [Lec, Lab] Convolutional Neural Network, Classification [Lec] SubT Competition Sharing, Midterm Report Due |
| 第 10 週 | [Lec, Lab] Classification, Transfer Learning |
| 第 11 週 | [Lec, Lab] Object Detection |
| 第 12 週 | [Lec] Robot Control [Lec] Locobot II - Learning-based Trail Following |
| 第 13 週 | [Lec] Imitation Learning and Behavior Cloning |
| 第 14 週 | [Lec, Lab] DeepRL & Deep Q-Network |
| 第 15 週 | [Lec, Lab] Deep Deterministic Policy Gradients (DDPG) & Actor–Critic Methods |
| 第 16 週 | [Lec, Lab] Recurrent Deterministic Policy Gradients (RDPG) and Demo for Learning-based Navigation Report Revision Due |
| 第 17 週 | Review session. Cheatsheet, guideline, and available spots available. Final Exam Preparation |
| 第 18 週 | Final Exam Preparation Final Exam Preparation |
教科書 • Artificial Intelligence: A Modern Approach 3rd Edition (Stuart Russell, Peter Norvig) 參考書目 • Probabilistic Robotics (Sebastian Thrun) • I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, 1st Ed., MIT Press, Dec. 2016 • R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, Nov. 2017 • Adnan Aziz, Amit Prakash, and Tsung-Hsien Lee, Elements of Programming Interviews in Python: The Insiders' Guide. 2016