Georgia Tech CS X803-AMR Spring 2026 edition
Mobile robots—ground vehicles, legged robots, underwater vehicles, drones, and space robots—are increasingly prevalent across diverse domains. This course provides a comprehensive introduction to the mathematical foundations of robot mobility, emphasizing optimization, estimation, and control. Students will also gain hands-on experience with multiple types of mobile robots.
Upon successful completion, you will be able to:
For undergrads:
For everyone:
The course requires access to a computer that can run Webots. A GPU card will make things faster and easier but a workaround might be available. All programming assignments will be completed in Python.
This class will be partially flipped in the sense that I will teach theory in the beginning of class and then we will immediately put it in practice in the second half of the class. That activity is going to be team-based, where teams are created randomly for each of the five sections in the class: underwater, walking, driving, flying, multi-robot. Attendance and in-class participation is mandatory and will count for a large part of your grade, 25%.
In-class participation will serve to build a foundation for your project contributions, which will come in two parts. Individual contributions are code deliverables and count for 5% per project, totaling 25%. Each project will also have a team-based component that explores machine learning in the context of the assignment and also counts for 5% for another 25% total. There will be no code deliverable here, only literature review and a proposal.
Finally, we will have in-class quizzes that, again, will count for 5% each. There is no final or midterm.
In summary:
Besides “institute-excused” absences, any absences in the class have to be documented through the Dean of Students, if valid. To allow for the occasional happenstance we will allow one undocumented absence per section in the class - no questions asked.
To grade assignments we will be using GradeScope. You can access that from the canvas module or directly on this URL: https://www.gradescope.com/courses/1078561.
For each project, the individual code deliverables and the answers to the reflection questions will be separate assignments on GradeScope.
Assignments are due Fridays at 11.59 pm. We use a sliding scale for late submissions, with 1% late penalty per hour. So if you submit between midnight and 1 AM, you lose 1% Between 1 AM and 2 AM, lose 2% etc.
Academic dishonesty will not be tolerated. This includes cheating, lying about course matters, plagiarism, or helping others commit a violation of the Honor Code. Plagiarism includes reproducing the words of others without both the use of quotation marks and citation. Students are reminded of the obligations and expectations associated with the Georgia Tech Academic Honor Code and Student Code of Conduct, available here.
You are expected to implement the core components of each project on your own, but the extra credit opportunities often build on third party data sets or code. That’s fine. Feel free to include results built on other software, as long as you are clear in your hand-in that it is not your own work.
You should not view or edit anyone else’s code. You should not post code to Piazza, except for starter code / helper code that isn’t related to the core project.
I ask you to be present for the assignments, thoroughly understand them, and take full ownership of the artifacts you produce. While coding with AI is now a fact of life, and it’s great, thrilling even, for this class the goal is to make your brain understand the math, through implementation of some key techniques. hence, I expected every line of code to be written and typed by you.
Specifically, the use of generative AI to code up an entire assignment with minimal involvement from your part (e.g., pasting the entire assignment in to an AI, or using “Agentic” AI to take care of the whole project) defeats the point of the class. Hence, this falls under the academic dishonesty policy. The purpose of the assignment is to build intuition and skill in robotics, which cannot be outsourced. Hence, I expect you to personally embark on each TODO in the coding assignments, being fully engaged. If abuse is of this nature is detected, the penalty will be an automatic zero on the assignment, and an F in the class on a second offense.
The assignments will frequently be accompanied with reflection questions designed to help assess whether you have fully grokked the methods/algorithms/techniques the assignments are designed to help you learn. Again, I expect that you to be the author of the answers, not the prompter.
If needed, we will make classroom accommodations for students with documented disabilities. These accommodations must be arranged in advance and in accordance with the ADAPTS office.
This term we will be using Piazza for class discussion. The system is highly catered to getting you help fast and efficiently from classmates, the TA, and myself. Rather than emailing questions to the teaching staff, I encourage you to post your questions on Piazza. If you have any problems or feedback for the developers, email team@piazza.com.
Use Piazza to ask questions and seek clarifications. If you have a very specific question (related to your grade etc.) or a question that involves your personal information, you can make a private post on Piazza.
The TA office hours will be announced very soon, along with the location, in a pinned post on Piazza.
The materials from this class might rely on slides prepared by other instructors. Each slide set and assignment contains acknowledgements. Feel free to use these slides for academic or research purposes, but please maintain all acknowledgements.