機器導航與探索

臺北科技大學 114-2 學期課程，課號 360393。

課程大綱

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。

課程進度

Week 1: Introduction to Robotic Navigation and Exploration Week 2: Kinematic Model and Path Tracking Control * Control System Basics * PID Control * Basic Kinematic Model * Differential Drive Vehicle * Pure Pursuit Control * Kinematic Bicycle Model Week 3: Motion Planning * Motion Planning Introduction * Path Planning * Curve Interpolation * Trajectory Planning * Path Planning Week 4: Reinforcement Learning (I) * MDP * Value Function * Bellman Equation * Reinforcement Learning Week 5: Reinforcement Learning (II) * Q-Learning / Sarsa / DQN * Policy Gradient / Actor-Critic Week 6: Project Environment Building Week 7: 清明節補假 Week 8: SLAM Back-end (I) * State Estimation and SLAM Problem * Probability Theory and Bayes Filter * Kalman Filter / Extended Kalman Filter Week 9: SLAM Back-end (II) * Graph based Optimization * Graph Optimization for 2D SLAM (Bundle Adjustment) Week 10: 3D SLAM (I) * Feature Descriptor * Multi-view Geometry * Lie Group & Lie Algebra Week 11: 3D SLAM (II) * 3D SLAM: ORB-SLAM * Direct Method * DNN-based SLAM Week 12: 3D Embodied Agent (I) * 2D → 3D → Interactive Embodied Intelligence Evolution * Overview of Major Ecosystems * Real-world Use Cases Week 13: 3D Embodied Agent (II) * Vision-Language Models for Embodied Agents * Preference-based RL + VLM Rewards * 3D Content Generation for Embodied Agents * LLM-Driven Decision Making & Task Planning Week 14: Paper Presentation (I) Week 15: Paper Presentation (II) Week 16: Project Presentation & Demo

評量方式

● 4次作業: 60% (15% for each HW) ● 論文閱讀報告(10%) ● 期末專題(含實作、書面報告、口頭報告): 30%

教材

【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】 使用外文原文書：是 參考書目 ● 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) ● Xiang Gao , Tao Zhang: Introduction to Visual SLAM - From Theory to Practice, 2021. ● Gang Peng , Tin Lun LAM , Chunxu Hu , Yu Yao , Jintao Liu , Fan Yang: Introduction to Intelligent Robot System Design - Application Development with ROS, 2023.