CS 4803-RBA - Robotics AI Techniques

Special Topics CS 4903-RBA Taught in the summer of 2024 is an undergraduate course based on the CS 7638 - Robotics AI Techniques graduate course. You will learn how to program all the major systems of a robotic car. You will be watching lectures from the former leader of Google’s and Stanford's autonomous driving teams, Sebastian Thrun before class, and receiving supplemental instruction and activities to test your knowledge in class. You will learn some of the basic techniques in artificial intelligence, including probabilistic inference, planning and search algorithms, localization, tracking, and PID control, all with a focus on robotics. Extensive programming examples and assignments in Python will apply these methods in the context of autonomous vehicles.

Learning Objectives

Upon successfully completing this course, you will be able to:

Implement filters (including Kalman and particle filters) in order to localize moving objects whose locations are subject to noise.
Implement search algorithms (including A* and Value Iteration) to plan the shortest path from one point to another subject to costs on different types of movement.
Implement PID controls to smoothly correct an autonomous robot’s course.
Implement a SLAM algorithm for a robot moving in at least two dimensions.

Instructors

Chris Wirgler
Jay Summet

Materials

Textbook: Probabilistic Robotics by Wolfram Burgard, Dieter Fox, and Sebastian Thrun.
www.probabilistic-robotics.org
PBS Nova: The Great Robot Race
Canvas is the primary website you will be using for this course ( https://gatech.instructure.com/ ). Lectures and problem sets will be accessed via Canvas in the Modules and Assignments pages, respectively.
There is also an older (Python 2) version of the course videos available for free on the Udacity website, which you can find at the direct URL: https://www.udacity.com/course/artificial-intelligencefor-robotics--cs373.
All online course communication including public questions about content and private questions about individual grades will be handled via the EdDiscussion website. You will be automatically enrolled in EdDiscussion using your GaTech Official login.

Projects

Important Dates and Deadlines

Wed, May 15th, 2024	First Day of Class
Monday, May 20th	Syllabus & Policy Guidelines Quiz Due
Wed, May 22nd	Problem Set 0 Due
Fri, May 24th	Problem Set 1 Due
Wed, May 29th	Problem Set 2 Due
Wed, June 5th	Kalman Filter Project Due
Mon, June 10th	Problem Set 3 Due
Fri, June 14th	Problem Set 4 Due
Wed, June 19th	Particle Filter Project Due
Mon, June 24th	Problem Set 5 Due
Wed June 26th	Midterm Exam (Covering the Topics of: Localization, Kalman Filters, Particle Filters)
Fri, June 28th	PID Project Due
Wed, July 10th	Search Project Due
Fri July 12th	Problem Set 6 Due
Mon, July 22nd	SLAM Project Due
Wed, July 24th	Final Exam (Comprehensive, covering all course material, but focusing on last 3 modules.)

Grading Policy

Your overall course grade will be calculated from your weighted scores on the following deliverable items:

7 problem sets and a Syllabus Quiz (20% total)
PID Project (7%)
Kalman Filter, Particle Filter, Search and SLAM Projects (12% each, 48% total)
Midterm & Final Exam (25%)
Required Attendance – Attendance will be taken daily. Missing the first 3 days are "free". Thereafter, each missed day (4 and above) will result in a 3% drop in your overall course grade. (e.g. missing 5 days = 6% drop in overall course grade). Missing less than 3 days will be taken into account if you are close to a letter grade cutoff at the end of the semester.

The minimum required percentage scores (we do NOT round up) for course letter grades are:

A: 90.00%
B: 80.00%
C: 70.00%
D: 60.00%

Students wishing to use this course for academic credit within the Georgia Tech College of Computing Threads model may find this letter describing this 4803RBA special topics course in relation to other CoC undergraduate courses useful.