Simon Fraser University
Engaging the World

Course Outlines

Spring 2026 - CMPT 419 D500

Special Topics in Artificial Intelligence (3)

Class Number: 5474

Delivery Method: In Person

Overview

  • Course Times + Location:

    Jan 5 – Apr 10, 2026: Tue, 4:30–5:20 p.m.
    Burnaby

    Jan 5 – Apr 10, 2026: Thu, 3:30–5:20 p.m.
    Burnaby

Description

CALENDAR DESCRIPTION:

Current topics in artificial intelligence depending on faculty and student interest.

COURSE DETAILS:

Course Overview: Recent breakthroughs in software and hardware are paving the way for robots to operate safely and intelligently alongside humans in unstructured environments (e.g., kitchens, offices, or construction sites). This seminar course provides an overview of state-of-the-art methods in robot learning and decision-making that enable fundamental capabilities required for the next generation of robots beyond the traditional scope. The theme for the upcoming semester emphasizes semantically driven approaches that enable robots to perceive their environment, reason about context, and act in ways that reflect common-sense understanding. Sample topics include, but are not limited to, 3D environment perception and mapping, language-conditioned learning and reasoning, imitation learning or learning from demonstrations, and foundations of safe robot decision-making.

Course Structure: The course will begin with an introductory lecture and tutorials that provide the necessary background on the core topics. The remaining sessions will be organized in a reading-group format, where each group presents one selected paper per lecture, followed by open-ended discussions on key techniques and pressing challenges. In addition to in-person sessions, a series of videos will be made available to provide practical guidance on essential research skills, including conducting a literature review, formulating a research problem, and communicating scientific ideas effectively in both oral and written form.

Expectations: You will work in pairs on a selected research paper, either from a provided list or a chosen alternative that aligns with the course theme. Each group is expected to:

  • Understand the assigned paper and relevant background literature
  • Critically analyze its limitations and assumptions
  • Propose a research idea suitable for a six-month project (preliminary results are encouraged but not required)

The final grade is based on the following three components:

  • Class participation during the semester (10%): A 15-minute presentation summarizing the selected paper to facilitate discussion, and preparation of questions and discussion points for sessions in which you are not presenting
  • Final report (45%): A six-page written report summarizing the selected paper and proposing a research idea addressing one identified limitation of the work
  • Final presentation (45%): A 20-minute oral presentation of your proposed research idea, followed by Q&A

COURSE-LEVEL EDUCATIONAL GOALS:

There are two overarching goals of the course: (i) to provide an in-depth review of selected state-of-the-art topics, and (ii) to offer opportunities for students to engage in group discussions and develop skills that are valuable for both academic and professional careers. The first goal is achieved through structured discussions of seminal papers from the past three years, while the latter is supported through a combination of in-class activities, video modules, and participation in the group project.

Grading

  • Class participation 10%
  • Final report 45%
  • Final presentation 45%

REQUIREMENTS:

There are no specific prerequisites for the course. Prior knowledge or experience in robotics, machine learning, control theory, and computer vision would be a plus.

Materials

REQUIRED READING NOTES:

Your personalized Course Material list, including digital and physical textbooks, are available through the SFU Bookstore website by simply entering your Computing ID at: shop.sfu.ca/course-materials/my-personalized-course-materials.

Department Undergraduate Notes:

The following are default policies in the School of Computing Science. Please check your course syllabus whether the instructor has chosen a different policy for your class, otherwise the following policies apply.
 
  • Students must attain an overall passing grade on the weighted average of exams in the course in order to get a C- or higher.
  • All student requests for accommodations for their religious practices must be made in writing by the end of the first week of classes, or no later than one week after a student adds a course. After considering a request, an instructor may provide a concession or may decline to do so. Students requiring accommodations as a result of a disability can contact the Centre for Accessible Learning (caladmin@sfu.ca).

Registrar Notes:

ACADEMIC INTEGRITY: YOUR WORK, YOUR SUCCESS

At SFU, you are expected to act honestly and responsibly in all your academic work. Cheating, plagiarism, or any other form of academic dishonesty harms your own learning, undermines the efforts of your classmates who pursue their studies honestly, and goes against the core values of the university.

To learn more about the academic disciplinary process and relevant academic supports, visit: 


RELIGIOUS ACCOMMODATION

Students with a faith background who may need accommodations during the term are encouraged to assess their needs as soon as possible and review the Multifaith religious accommodations website. The page outlines ways they begin working toward an accommodation and ensure solutions can be reached in a timely fashion.