機器導航與探索
Robotic Navigation and Exploration
| 節 | 週一 |
|---|---|
A 18:30–19:20 | 機器導航與探索 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
本課程為AI聯盟課程,對應人工智慧探索應用學分學程(人工智慧應用課程)、人工智慧工業應用學分學程(機器人專題)、人工智慧視覺技術學分學程(人工智慧影像應用課程) 本課程模組分為三個主要的部分,分別為即時追蹤與地圖建置(SLAM)、基於機器學習之場景理解(Scene Understanding)與探索導航的動作控制(Action Control)。即時追蹤與地圖建置部分包含機率模型與相機模型等理論基礎,也包含基於深度學習之RGB-based的3DSLAM方法。場景理解的部分包含機器學習的基本概念,再帶到深度學習的技術與目前的物件偵測與語意切割技術。動作控制的部分則包含路徑規劃與導航演算法,並帶入強化學習的概念來引導行進的路徑。
建議學生需已修過Python程式設計、影像處理、深度學習。
遠距上課位置:國立清華大學台達館106教室 (遠距連結 meet.google.com/wbh-oihg-jsn) 學生須自備具GPU顯卡之電腦。 本課程期末專題採分組開發,為避免影響同組修課同學之權益,本課程不接受期中退選,請謹慎評估可投入的時間再選課。
作業(60%)(15% for each HW)、論文閱讀報告(10%) 自走車期末專題(含實作、書面報告、口頭報告):30%
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction to Robotic Navigation and Exploration |
| 第 2 週 | Kinematic Model and Path Tracking Control * Control System Basics * PID Control * Basic Kinematic Model * Differential Drive Vehicle * Pure Pursuit Control * Kinematic Bicycle Model |
| 第 3 週 | Motion Planning * Motion Planning Introduction * Path Planning * Curve Interpolation * Trajectory Planning * Path Planning |
| 第 4 週 | Reinforcement Learning (I) * MDP * Value Function * Bellman Equation * Reinforcement Learning |
| 第 5 週 | Reinforcement Learning (II) * Q-Learning / Sarsa / DQN * Policy Gradient / Actor-Critic |
| 第 6 週 | Project Environment Building (I) |
| 第 7 週 | Project Environment Building (I) |
| 第 8 週 | Project Environment Building (III) |
| 第 9 週 | SLAM Back-end (I) * State Estimation and SLAM Problem * Probability Theory and Bayes Filter * Kalman Filter / Extended Kalman Filter |
| 第 10 週 | SLAM Back-end (II) * Graph based Optimization * Graph Optimization for 2D SLAM (Bundle Adjustment) |
| 第 11 週 | 3D SLAM (I) * Feature Descriptor * Multi-view Geometry * Lie Group & Lie Algebra |
| 第 12 週 | 3D SLAM (II) * 3D SLAM: ORB-SLAM * Direct Method * DNN-based SLAM |
| 第 13 週 | 3D Embodied Agent |
| 第 14 週 | Paper Presentation (I) |
| 第 15 週 | Paper Presentation (II) |
| 第 16 週 | Project Presentation & Demo |
● Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, Second Edition, MIT Press, Cambridge, MA, 2018 ● Sebastian Thrun, Wolfram Burgard, and Dieter Fox , Probabilistic Robotics,2005. (Intelligent Robotics and Autonomous Agents series) ● Kevin Murphy, Machine Learning: A Probabilistic Perspective. ● Daphne Koller and Nir Friedman, Probabilistic Graphical Models: Principles and Techniques, 1st Edition, 2009. ● Ian Goodfellow, Yoshua Bengio and Aaron Courville: Deep Learning.