Announcements:
2020/12/24: SDC Test Ride and the Action lecture at ITRI.
2020/12/17: The slide decks of Prediction are available.
2020/12/09: The slide deck of Multiple Target Tracking is available.
2020/12/02: The slide deck of Lane Detection is available.
2020/11/25: The slide decks of Probabilistic Machine Perception and Final Competition are available.
2020/11/19: The slide decks of Geometric Mapping and Semantic Mapping are available.
2020/10/28: The slide deck of SLAM is available. Watch Autoware Course Lecture 14: HD Maps.
2020/10/21: The slide decks of Registration are available.
2020/10/14: The slide deck of Localization is available.
2002/10/14: The EKF and localization package used by the TAs in this course is available at https://github.com/cra-ros-pkg/robot_localization.
2020/10/08: A nice introduction to Kalman filter by Steve Bruton.
2020/10/07: The slide deck of Gaussian Filters is available. Have a look at Autoware Course Lecture 10: State Estimation for Localization.
2020/09/23: The slide deck of probabilistic state estimation is available.
2020/09/16: The free online courses on ROS 2 and Autoware provided by Apex AI are available here.
2020/09/15: Bob's 線上演講 「多車款自駕車系統建置與台灣開放場域測試驗證」.
2020/09/15: The lecture slide decks are available here.
Time & Room:
10:10 - 13:10 Thursdays at Room 635, Engineering Building 5, NCTU.
Course descriptions and objectives:
The course is designed for senior undergraduates and graduates who want to learn the key techniques of self-driving cars and/or want to become self-driving engineers/scientists.
This course will cover the cutting-age of robotics, computer vision and machine learning for enabling self-driving cars including sensors & sensing, probabilistic state estimation, localization, mapping, tracking, sematic understanding, deep learning, control & path planning, software engineering and hardware systems.
Prerequisite:
This is an advanced course describing the key technologies used in self-driving cars. The course is highly related to robotics, computer vision and machine learning. The students must have good C/C++ and Python programming skills and they should have some hands-on experiences on robotics, computer vision or machine learning before taking this course.