Class announcements, discussions, assignments, and due dates will be posted on Canvas.
This is an exciting time to be a roboticist. Robots continue to get smaller, faster, and cheaper. Robots today are packed with sophisticated computing, communication, and sensing resources. It is becoming increasingly important to develop efficient decision-making algorithms that makes full use of the robot's capabilities. In this course, we will discuss the state-of-the-art algorithms that aim to do just that.
The goals of this course are for you to:
This course is a seminar-style course featuring student-led discussions of recent research papers. See more information on paper presentations here. In order to make the course self-contained, I will give introductory lectures that cover background material.
We will have assignments which will be a mix of theory questions, and programming/implementation assignments. You will also have to write reviews for papers covered in the class.
The students will also work in groups on a research-oriented course project. More information about the project is here.
Letter grades: A (93% to 100%); A- (90% to 93%); B+ (87% to 90%); B (83% - 87%); B- (80% to 83%); C+ (77% to 80%); C (73% to 77%); C- (70% to 73%); D+ (67% to 70%); D (63% to 67%); D- (60% to 63%); F (below 60%)
No required textbook. Course materials will be drawn from research papers and notes that I will post online.
A tentative schedule is given here.
Details will posted on canvas. The assignments will be a mix of theory questions, and programming/implementation problems.
Each student will present 1 paper of their choice during the semester. You may choose a paper from the list given here.
You are also encouraged to search for papers on your own, preferably from a top robotics journals (T-RO, T-ASE, RAM, IJRR, AURO) and conferences (ICRA, IROS, RSS, WAFR). You may also present papers from related research areas (e.g., Computer Vision, Machine Learning, Controls, Computational Geometry) if they are relevant for the course. If so, please discuss with me if you have specific ideas. I will announce the mechanism for paper selection in the first two weeks of classes.
Each presentation must be at most 45 minutes long, plus time for discussions during and after the presentation. The nature of presentation --- powerpoint, whiteboard, interpretive dance --- is up to you. Depending on the paper, you may have to spend a significant portion of the time covering the background material.
One day (24 hours) before your scheduled presentation, you must post on the class forum a short summary (~400 words) in your own words of the paper you will be presenting.
You will be asked to submit 3 reviews, written individually, for 5% each. One review must be for the paper you presented in class. This review is due exactly a week after you present the paper. Two other reviews can be for any other papers presented in class. These must be submitted in two steps. First review (from amongst papers presented before 19th October) is due on 28th October. Second review (from amongst papers presented after October 28th) is due on December 9. Each review must contain:
The project can be any of the following types:
You may work in groups of at most 3 students for the project. You will be required to submit a project proposal (1-2 pages) with the names of the group members, proposed project details, expected timeline, and individual responsibilities.
In addition to the above mentioned deliverables, each project team will give a presentation in the last week of the class. The size of the team will depend on the scope of the project.
I will propose specific topics and hardware details in the first few lectures. You are also highly encouraged to choose a project topic that is related to your MS/PhD thesis research. However, your project topic must be relevant to this course, and must be performed during this semester. No double counting allowed. Discuss this with me, if you choose this route.
This is a seminar-style course. An ability to read and critique research papers is required.
There are no explicit course prerequisites. Familiarity with at least one of the following topics is required (mainly to make it easier for you to select relevant papers): data structures and algorithms, machine learning, computer vision, linear/non-linear systems and controls, optimization, computational geometry, state estimation and filtering. Prior background in robotics would similarly be helpful, but not required. We will aim to keep the material self-contained. I will cover the relevant background materials in lectures.
Feel free to discuss with me if you are unsure about your background.
You are encouraged to discuss the course materials with the instructor and other students in the class. However, any work that you submit (including but not limited to homeworks, paper reviews, project reports) must be your own. Give proper citations if you use any code or data from anyone else.
The tenets of the Virginia Tech Graduate Honor Code will be strictly enforced in this course, and all assignments shall be subject to the stipulations of the Graduate Honor Code. For more information on the Graduate Honor Code, please refer to the GHS Constitution at this URL.
Any student who feels that he or she may need an accommodation because of a disability (learning disability, attention deficit disorder, psychological, physical, etc.), please make an appointment to see me during office hours. My office hours are Monday and Wednesday 5:20 PM to 6:20PM in 627 Whittemore Hall.