Instructor
David Meger
david.meger@X
Office: McConnell 112N
Office Hours: Wednesdays after class
Dave's office MC112N
X = mcgill.ca
-------------------------------------
Teaching Assistant
Travis Manderson
travis dot manderson at mail dot mcgill dot ca
Office hours by appointment through email

News

Overview

COMP 765 is a research seminar on Intelligent Robotics: the intersection of rocket science and the latest machine learning on-board systems that can sense the world and act upon it. The class will begin with lectures on definitional problems and algorithms in robotics. We will then transition to mixed student-lead and instructor-lead discussions of recent developments in research and in practice. The emphasis is on algorithms, probabilistic reasoning, learning to improve behaviors using data, and decision making under uncertainty, as opposed to electromechanical systems design. We will broadly cover the following areas:

Seminar Format

The class will be a mix between lecture-style teaching and student-lead discussion. In each unit, I will lead things off by presenting standard material given in textbooks, covering the theory and analysis with basic examples. We will then transition to the state-of-the-art in the area, with the end of the unit featuring presentations of important recent papers following the PROPONENT, OPPONENT, REPRODUCER format to be described in class.

The [READING LIST], along with the schedule and assigned presenters is located here. This link is edittable. Please feel free to offer your peers trades, the spreadsheet can be edited using this link.

Assignments

Schedule

Date Topics Slides References
Jan 7 Introduction
Motivation and course sylabus
(pdf) (pptx) PR Chapter 1.
Jan 9 Spatial Representations
Kinematics and Dynamics
(pdf) (pptx) PR Chapter 5.
Jan 14 and 16 Intro to Estimation
Sensing uncertainty, Bayesian filters, Kalman basics
(pdf) (pptx) PR Chapter 3
Jan 21 EKF and Particle Filters
Importance sampling, analysis, efficient resampling methods
(pdf) (pptx) PR Chapter 4
Jan 23 Modern Localization and Mapping
Rao-Blackwellized Particle Filtering, large-scale sparse graph optimizers, mapping an entire city.
(pdf) (pptx) PR Section 3
Jan 28 Example Seminar Presentation
Dave and Travis as Proponent and Opponent present ORBSLAM.
(pdf) (pptx) ORBSLAM Paper
Jan 30 Gaussian Processes For Robot Learning
Bayesian regression, random processes, GP formulation, inference and parameter learning.
(pdf) (pptx) Slides from Uni Freiburg course
GP text first 3 chapters
Feb 4 Estimation Papers Day
Student-lead seminars for 3 papers
Send me your slides when ready so I can post them. As listed in the reading list
Feb 6 and Feb 11 Robotic Control Intro
Control theory, ODE background, PID, MDPs, dynamic programming
(pdf) (pptx) PLAN text, selected ideas from Chapter 15
Feb 13 Trajectory Optimization
LQR, DDP, policy search
(pdf) (pptx) (recording) Underactuated robotics text, Chapter 9 - LQR
Feb 18 Control Papers Day
Student-lead seminars for 3 papers
Send me your slides when ready so I can post them. As listed in the reading list
Feb 20 Multi-task and Robust Control
Contextual and transfer learning overview, domain randomization, policy adjustment.
(pdf) (pptx) Behavior Adaptation
Feb 25 Learning to learn
Meta learning, generalized policies and value functions.
(pdf) (pptx) Dropout as a Bayesian Approximation
Feb 27 Transfer Learning Papers Day
Student-lead seminars for 3 papers
Send me your slides when ready so I can post them. As listed in the reading list
March 4 and 6 McGill Reading Week
No class. Take a rest!
March 11 Human Robot Interaction Intro
HRI overview, imitation learning, behavior cloning, DAGGER.
(pdf) (pptx) An Invitation to Imitation
March 13 Inverse Reinforcement Learning
MaxEnt IRL, Interactive Reward Learning, outperforming the demonstrator.
March 18 HRI Papers Day
Student-lead seminars for 4 papers
Send me your slides when ready so I can post them. As listed in the reading list
March 20 Planning Introduction
Planning flavors: geometric, symbolic, discrete, continuous. Dynamic programming and graph solutions.
(pptx)(pdf) PLAN text first 3 chapters
March 25 Sampling-based planning
Efficient solutions to high-dimensional planning. PRM and RRTs. Probabilistic completeness.
PLAN text RRT material
March 27 Planning under uncertainty
POMDPs, black-box optimization, Bayesian neural networks.
April 1 Planning Papers Day
Student-lead seminars for 3 papers
Send me your slides when ready so I can post them. As listed in the reading list
April 3 Multi-robot systems
Collaborative manipulation, swarm robotics, decision making under communication and coordination constraints.
April 8 Multi-robot Papers Day
Student-lead seminars for 3 papers
Send me your slides when ready so I can post them. As listed in the reading list
April 10 Project presentation day
Will be in an extended class or poster session. More details as the date approaches.
Send me your slides when ready so I can post them.

Marking scheme

Recommended, but optional, textbooks

Related courses

Diversity and Inclusion

Robotics is one of the most technologies in our world today and this knowledge should be shared equally by all agents. , and indeed one of the most important skill-sets that people will use to influence the world in our lifetimes. Our goal is to make this content equally accessible to students of all backgrounds and we work to pro-actively acknowledge and address any bias that may occur during the term. Equal treatment of students from every gender, race and orientation is a top priority. We openly welcome suggestions on how to improve inclusion, by contacting the TAs or instructor either with your name or anonymously.