Meets: Fri 1.45 - 4.45 p.m. ET at  LRSM 112 B

Instructor: Dinesh Jayaraman (dineshj [at] seas.upenn.edu) 

If you are on the waitlist, attend the first class and speak with me afterwards.

Recommended Background

• Graduate-level machine learning (CIS 419/519 or equivalent)

• Undergraduate level computer vision

• Undergraduate level robotics

Most importantly, you must be able to understand and analyze conference papers in these areas. Talk to me if you are unsure if the course is a good match for your background. I would recommend scanning through a few papers on the syllabus to gauge what kind of background is expected. You don't have to be familiar with every single algorithm or tool a given paper mentions, but you should feel comfortable following the key ideas.

Topics

This is a graduate seminar course in computer vision and machine learning applied to robotic control.  Perception and control have long been studied disjointly across many disciplines: computer vision, robotics, control theory, reinforcement learning, and cognitive science. Through presentations and discussions of recent academic papers from across disciplines, interspersed with lectures, this course will aim to synthesize a common understanding of recent advances in data-driven methods for vision-based robotic control, to actively analyze the strengths and weaknesses of current approaches, and to identify interesting open questions and possible directions for future research.  See below for an outline of the topics.

The majority of the course will consist of student presentations, experiments, and paper discussions. 

Requirements and Grading Summary (Tentative, based on class size)

• Experiment presentation (Random team of 4. 3 times): 20%

• Paper presentations (Individual. 2 times during the semester.): 20%

• Class discussion participation: 10%

• Weekly paper reviews (Random team of 2. 7 weeks x 2 papers each week): 25%

• Final project (Teams of 3. Report and presentation in the last class): 25%