Fall, 2019

Simon Fraser University

Instructor: Mo Chen

Breadth Area III

Lecture times and location:

• Academic Quadrangle 5016
• Mondays 10:30 - 12:20
• Wednesdays 10:30 - 11:20

Instructor

• Mo Chen
  SFU Burnaby, TASC 1 8225
  mochen@cs.sfu.ca
  Office hours: Mondays 14:00 - 15:30

Teaching Assistant

• Shubam Sachdeva
  shubams@sfu.ca
  Office hours: ASB 9808 Thursdays 11:30 - 12:30

Instructor's Objectives

This course introduces fundamental concepts in robotics and related fields, including analytical methods for decision making, and machine learning in the context of robotics. Topics include modeling and simulation of robotic systems, optimization, optimal control, robotic safety, reinforcement learning, and robotic perception. Applications of the material include unmanned aerial vehicles and self-driving cars.

Course Schedule

• 04/09/2019: Introduction
• 09/09/2019: Linear Systems
• 11/09/2019: Nonlinear Systems
• 16/09/2019: Lyapunov Stability and Numerical Solutions to ODEs I
• 18/09/2019: Numerical Solutions to ODEs II
• 23/09/2019: Convex Optimization I and Convex Optimization II
• 25/09/2019: Non Convex Optimization SQP
• 30/09/2019: Non Convex Optimization MILP and Differential Flatness
• 02/10/2019: Single shooting
• 07/10/2019: Collocation and Dynamic Programming
• 09/10/2019: Continuous Time LQR
• 16/10/2019: Reachability Analysis I
• 21/10/2019: Reachability Analysis II and Sampling based Motion Planning
• 23/10/2019: Regression I
• 28/10/2019: Neural Networks MDP
• 30/10/2019: Imitation Learning
• 04/11/2019: Intro Reinforcement Learning and Reinforcement Learning I
• 06/11/2019: Reinforcement Learning II
• 13/11/2019: RL in TensorFlow, and Jupyter notebook
• 18/11/2019: Guest Lectures
• 20/11/2019: Sensor Overview
• 25/11/2019: Localization 1 and Localization 2
• 27/11/2019: SLAM
• 02/12/2019: Poster Presentations

This page contains all the code used in class

Grading Criteria and Submissions

There are 3 assignments and a final project in the course. Solutions to the assignment must be submitted on CourSys.

• Homework: 40%
• Project: 60%

Assignments

• Assignment 1: Due Sept. 30. Solution
• Assignment 2: Due Oct. 31. Solution 2
• Assignment 3: Due Dec. 02. Solution 3

Project

Project options

• Thoroughly understand and critically evaluate 3 to 5 papers in an area covered in this course.
• Reproduce the results of 1 to 2 papers in an area covered in this course, and suggest or make improvements
• Mini Research project related to an area covered in this course.
• Other: please consult with the instructor

Project timeline

• Consultation throughout the term
• Proposal (1-2 paragraphs) Due Oct. 7
• Poster session on Dec. 2 | Template
• Project report (6 pages maximum) due Dec. 2 | Template

Project topics

• Modelling and simulation
• Optimization
• Optimal control
• Robotic safety
• Reinforcement learning
• Robotic perception

Recommended textbooks

• R. Siegwart, I. R. Nourbakhsh, and D. Scaramuzza, Introduction to Autonomous Mobile Robots. The MIT Press, 2011, 9780262015356.
• S. S. Sastry, Nonlinear Systems: Analysis, Stability, and Control. Springer-Verlag, 1999, 9780387985138
• S. M. LaValle, Planning Algorithms. Cambridge University Press, 2006, 9780521862059.
• S. Boyd and L. Vandenberghe, Convex Optimization. Cambridge University Press, 2008, 9780521833783.
• D. P. Bertsekas, Dynamic Programming and Optimal Control. Athena Scientific, 2017, 1886529434.
• R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 1998, 9780262257053.

Academic Honesty Statement

Academic honesty plays a key role in our efforts to maintain a high standard of academic excellence and integrity. Students are advised that ALL acts of intellectual dishonesty will be handled in accordance with the SFU Academic Honesty and Student Conduct Policies ( http://www.sfu.ca/policies/gazette/student.html ).