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。

This course module is divided into three main parts, namely real-time tracking and map construction (SLAM), machine learning-based scene understanding (Scene Understanding), and exploration navigation action control (Action Control). The real-time tracking and map construction part includes theoretical foundations such as probability models and camera models, as well as the RGB-based 3DSLAM method based on deep learning. The scene understanding part includes the basic concepts of machine learning, and then brings to the deep learning technology and the current object detection and semantic segmentation technology. The action control part includes path planning and navigation algorithms, and brings in the concept of reinforcement learning to guide the path of travel.

● 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.

● 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.