Logistics

Post-Class Discussion

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 instructor. Rather than emailing questions to the teaching staff, we encourage you to post your questions on Piazza.
Find our class signup link at: https://piazza.com/utexas/fall2022/cs391r

Grading Policy

Student presentation (20%)
Paper summaries / abstracts and Quizzes (30%)
Course project (40%)
In-class participation (10%)

Student Presentations

An integral component of this course is to present a robot learning research topic to the class. This requires conducting a systematic literature review on the topic and guide an in-class discussion. Each student should present and moderate discussions on one paper. Presentations will be 15 min (strict!) + 5 min Q&A. To ensure the quality and clarity of the presentations, we expect the students to
  • read the assigned paper and the related work thoroughly and gain a good understanding before making the presentation slides.
    Template: [Powerpoint] or [Google Slides]
  • email the slides to the TAs and the instructor seven days (EOD) prior to the presentation date for feedback and revision.
    Deadline: 9:59pm Tue for talks next Tue and 9:59pm Thu for talks next Thu
  • email a list of open-ended questions on the topic to the TAs and the instructor seven days (EOD) prior to the presentation date
Failures to email the slides or the questions on time would incur a 20% deduction on the presentation score. Each presentation should be 20min (± 2min). The presentations will be graded in the following aspects:
  • Clarity of presentation (problem formulation, proposed method, key results);
  • Presentation of the background material (basic concepts to understand the research improvement);
  • Review of prior work and the challenges addressed by this work;
  • Analysis of the strengths and weaknesses of the research;
  • Discussion of potential research extensions and applications;
  • Response to student questions (in-class and on Canvas).
After each presentation, we will do a 5min Q&A about the presentation. Three papers will be presented in each class, and then we will have an open-ended final discussion supported by the questions sent by each presenter and moderated by the instructors and the presenters. The discussion questions will be posted on Canvas by the instructor the day before the class. The slides and video recordings of the presentations will be shared on Canvas within one week of the presentation date. The presentation will be worth 20% of the total grade.

Useful Resources

Paper Summaries / Abstracts and Quizzes

A paper summary in the form of a short abstract will be due by 9:59pm the previous night for each class with student presentations (9:59pm Mon and 9:59pm Wed). There will be three papers presented in each class, you have to write a summary/abstract for each one. Abstracts will be submitted through Gradescope.

Each abstract will be each worth 0.75% of the total grade and a minimum of 40 abstracts are required, summing up to 30% of the grade. The course includes more than 40 papers (60), so there is some room for missing some abstracts. If more than 40 abstracts are submitted, the best ones will be used for the grade. The abstracts will not be accepted late since we expect the students' independent evaluations of the papers prior to in-class presentations and discussions. Note that both the abstract and class attendance and participation are required in order to receive a non-zero grade of an abstract.

What should be contained in the abstract?
  • 1-2 sentences describing the problem
  • 1-2 sentences explaining why the state-of-the-art is not enough for this, why it fails
  • 1-2 sentences explaining the clever idea of this paper
  • 1-2 sentences explaining how the idea is implemented
  • 1 sentence about the experimental evaluation
The entire abstract should be 5-7 sentences long. Be concise.
We will run a plagiarism software on the abstracts to compare to the original abstract.

Quizzes: At the beginning of the class, we will run a quiz on each of the three papers to be presented and discussed. The quizzes will contain a variable (but short!) number of multiple choice questions, around 6 questions per paper. At least half of the questions on a paper need to be correctly answered for the abstract/summary and the participation to be counted on the grade. Questions will be very easy to answer after reading the papers. The answers will be given by the presenter of each paper after the quiz is over.

Course Project

The course project aims to help the students gain in-depth, hands-on experiences applying AI-based techniques to practical robot perception and decision making problems. It consists of four key components: a project proposal (5%), a milestone report (5%), a final report (20%), and a spotlight talk with interactive poster session (10%). For more details, please see the Project page.

Useful Resources

In-Class Participation

All students are required to participate in the discussions of the papers (5 minutes of Q&A) and in the final debate. We will use these guidelines to grade the participation. At the end of the class, we will poll the opinions of the students using PollEverywhere. This component will weight a 10% of the final grade.
We will also ask all students to provide anonymous feedback to the presenters. This will allow participants to improve their presentation skills, a critical soft-skill in industry and academia.

Useful Resources

Classroom Safety and COVID-19

To help preserve our in person learning environment, the university recommends the following.

Academic Integrity

You are encouraged to discuss assignments with classmates, but all collected data, analysis, images and graphs, and other written work must be your own. All programming assignments must be entirely your own except for teamwork on the final project. You may NOT look online for existing implementations of algorithms related to the programming assignments, even as a reference. Your code will be analyzed by automatic tools that detect plagiarism to ensure that it is original. For the final project, you have full access to the web, but all ideas, quotes, and code fragments that originate from elsewhere must be cited according to standard academic practice. Students caught cheating will automatically fail the course and will be reported to the university. If in doubt about the ethics of any particular action, look at the departmental guidelines and/or ask — ignorance of the rules will not shield you from potential consequences.

Notice about students with disabilities

The University of Texas at Austin provides upon request appropriate academic accommodations for qualified students with disabilities. For more information, contact the Division of Diversity and Community Engagement — Services for Students with Disabilities at 512-471-6529; 512-471-4641 TTY.

Notice about missed work due to religious holy days

A student who misses an examination, work assignment, or other projects due to the observance of a religious holy day will be given an opportunity to complete the work missed within a reasonable time after the absence, provided that he or she has properly notified the instructor. It is the policy of the University of Texas at Austin that the student must notify the instructor at least fourteen days prior to the classes scheduled on dates he or she will be absent to observe a religious holy day. For religious holy days that fall within the first two weeks of the semester, the notice should be given on the first day of the semester. The student will not be penalized for these excused absences, but the instructor may appropriately respond if the student fails to satisfactorily complete the missed assignment or examination within a reasonable time after the excused absence.