ECE / CS 598 SG1: Robot Learning (Spring 2025)

Instructor: Saurabh Gupta (saurabhg)
TA: Arjun Gupta (arjung2)
Lecture Times: Tuesday / Thursday 12:30pm - 1:50pm
Lecture Location: ECEB 3020

Office Hours | Campuswire (announcements and discussion, joining link and code: 8698) | Gradescope (programming assignments, entry code: TBD)

To the extent possible, you should use Campuswire for asking questions. If you have a logistics question specific to yourself, you can email the course staff at rl-sp25-staff@lists.illinois.edu.

Course Description

This course will introduce students to recent developments in the area of robot learning, i.e. the use of learning to program robots. The course will start with an overview of basic concepts from relevant subfields: computer vision, machine learning, robotics, control theory, and reinforcement learning. This will be followed by a discussion of advanced concepts and case studies through a discussion of latest research papers. The course will conclude with a discussion on the central research questions in the field. Programming assignments will offer hands-on experience in applying robot learning concepts, while the course project will provide a flavor of conducting research in this new emerging area.

Prerequisites

This is an advanced gradate course aimed at graduate students conducting research in relevant research areas. The course will be structured around research papers published within the last few years in computer vision, robotics, machine learning, and robot learning. Students should be familiar with reading and critiquing research papers, and should have a basic understanding of concepts in artificial intelligence and machine learning. Students must have taken at least one of the following (or equivalent) courses: ECE 448 / CS 440 (Introduction to Artificial Intelligence), ECE 544NA (Pattern Recognition), ECE 549 / CS 543 (Computer Vision). If you are not sure whether you meet the prerequisites, talk to the instructor after the first class or in office hours.

Recommended Textbooks

Grading Scheme

Tentative and subject to change.

  1. Programming assignments: 30%. 3 MPs, to be done individually. Assignments need to be submitted to gradescope. Gradescope entry code is TBD. Dates are tentative.

    1. Assignment 1. Released Feb 6 2025, due Feb 27, 2025 at 11:59 PM.

    2. Assignment 2. Released Feb 20 2025, due Mar 13, 2025 at 11:59 PM.

    3. Assignment 3. Released Mar 13 2024, due Apr 3, 2025 at 11:59 PM.

  2. Project: 30%. Students will engage in projects in groups of 1-3. Projects should involve investigation of relevant research questions in computer vision, robotics, machine learning and robot learning. Projects could be done in simulation, or on real robot platforms that you may have access to. See here for more details.

  3. Paper Presentation and Debate: 25%. Part II and III of this class will involve students presenting recent research papers and participating in debates on central research questions in the field. For the paper presentations we will be adopting a Role Playing Style. Different students will be presenting different aspects of the paper and each student will present multiple times during the semester. More details will be provided in the coming weeks.

  4. Answer to Paper Question: 10%. For Part II of the class, we will be reading recent papers. You are required to read the paper before coming to class. To incentivize this, you will need to answer a question related to the paper before the class. More details will be provided in the coming weeks.

  5. Participation: 5% Participation in discussion in class and on Campuswire.

Frequently Asked Questions

  1. Enrollment works on a first come first serve basis for this class, and I am unable to make exceptions.

  2. This class exclusively caters to graduate students who are actively engaged in research in relevant areas. This class is not suitable for students enrolled in professional programs.

  3. Exceptional undergraduates who are conducting research on related topics are welcome to join. Please fill out this form asap and I will email you back if I believe you have the right preparation to sign an override form that will let you try to enroll if seats open up.

  4. If you enroll late, it is your responsibility to catch up with the material. We will not be extending the various assignment deadlines for late enrollment reasons.

  5. We will not be accommodating requests to officially audit the class.

  6. UIUC has a vibrant community of researchers working on robotics and other related areas in AI (link1 and link2) like computer vision, and natural language processing. Feel free to check out what all these researchers are up to.

Acknowledgement

We thank the many researchers who have made their slides and course materials available.