Creator, Instructor, Co-Founder of Udacity
Course Developer and Instructor
In Artificial Intelligence for Robotics, learn from Sebastian Thrun, the leader of Google and Stanford's autonomous driving team, how to program all the major systems of a robotic car. This class will teach students basic methods in Artificial Intelligence, including: probabilistic inference, planning and search, localization, tracking and control, all with a focus on robotics. Extensive programming examples and assignments will apply these methods in the context of building self-driving cars.
At the end of the course, students will leverage what they have learned by solving the problem of a runaway robot that they must chase and hunt down! Students will also be expected to complete six problem sets, and deliver a final project that applies one of the methods learned in this class on a dataset of their choosing.
Students should know Python or have enough experience with other languages to pick up what they need on their own. Check out Udacity's Introductory CS class (in Python) if you'd like some review. Students should also have strong knowledge of probability and linear algebra (see Prof. Thrun's free Udacity course on statistics).
For prospective students who are unsure if their computer science experience provides sufficient background for this course, the questions below will help gauge preparedness. If you answer "no" to any of the following questions, it may be beneficial to refresh your knowledge of this material prior to taking CS 8803:
- Do you have programming experience, preferably in Python?
- Do you have a strong understanding of linear algebra (undergraduate-level)?
- Do you have a strong understanding of probability (undergraduate-level)?
- Have you taken any courses (either from your undergraduate studies or MOOCs) in machine learning, computer vision or robotics?
- 6 Problem Sets: Problem Sets are graded on a completion basis; meaning, you will receive full credit if you complete them on time, and zero credit if you do not. There is no partial credit given for Problem Sets.
- Project 1: Runaway Robot, Parts 1-4
- Project 2: Final Project
- Extra Credit - Extra credit may be awarded for completing Part 5 of the Runaway Robot Project, completing Hardware Challenges, participating in Peer Feedback, and for exceptional helpfulness on the class Piazza forum.
- Grades for the projects will be posted to your student account on T-Square. Assignment Submission and Late Policy -
- With the exception of the Final Project, all assignments will be submitted through the Udacity site.
- You will submit your Final Project through T-Square.
- No late work accepted. The specific course schedule will be announced by the instructor and/or TA at the beginning of the term.
Required Course Readings
Website readings with an optional textbook supplement listed below:
- Optional enhancement text - Probabilistic Robotics. Sebastian Thrun, Wolfram Burgard & Dieter Fox. MIT Press. 2005.
Minimum Technical Requirements
- Browser and connection speed: An up-to-date version of Chrome or Firefox is strongly recommended. We also support Internet Explorer 9 and the desktop versions of Internet Explorer 10 and above (not the metro versions). 2+ Mbps recommended; at minimum 0.768 Mbps download speed
- Operating system: -PC: Windows XP or higher with latest updates installed -Mac: OS X 10.6 or higher with latest updates installed -Linux: Any recent distribution that has the supported browsers installed
Background Materials on Statistics -
- Prof. Thrun teaches a free introductory course on Udacity called Statistics 101.
- If you prefer written material, Think Bayes is available online. It has some great examples and the text is approachable.
Professor Thrun will hold Office Hours through Google Hangouts on Air about once every two weeks. Students may submit questions either during the session or in advance.
All Georgia Tech students are expected to uphold the Georgia Tech Academic Honor Code.