Montreal Robotics Summer School (2022)

School Photo Getting excited This years champions

Robotics is a rapidly growing field with interest from around the world. This summer school offers tutorials and lectures on state-of-the-art machine learning methods for training the next generation of learning robots. This summer school is an extension supported by the many robotics groups around Montreal.

The tutorials and interaction with real robot hardware will take place at Mila, the Quebec AI Institute, the largest academic organization for deep learning researchers worldwide. Attendees will have the opportunity to learn about current deep reinforcement learning methods, how to apply them to real hardware, sim2real transfer techniques, and experience with legged robotics.

Challenge: On the summer school’s last day, teams will use their new skills to compete in designing the most robust navigation controller on a quadruped robot to navigate an obstacle course. The obstacle course will feature many changes in terrain and difficult to traverse obstacles for the robot. Teams will be given multiple rounds to see how far their robot can make it across the terrain. The team with the best final performance wins!

Who: This summer school tailors to graduate students with a strong programming background and experience with algorithms.

What Students Learn

The goal of the summer school is to give more students skills on how to control and program navigating robots. The content assumes a strong knowledge of python programming, with some Linux and hardware skills.

  1. We will start with an introduction to robotics.
  2. Introduction to Robotics software stack (control and ROS, etc)
  3. Presentation on the robotics simulation and how to control the robot
  4. State estimation
  5. Introduction to deep learning and computer vision for state estimation
  6. Presentation on the hardware and how to control the robot using Python
  7. SLAM
  8. Planning and planning with learned models
  9. Introduction to reinforcement learning and sim2real transfer


  • Google
  • L’Institute Courtios
  • Mila


  • Aneri Muni: DeepRL and Sim2Real prep
  • Annie-Shan Morin: Logistics and Promotion
  • Elham Daneshmand: DeepRL and Sim2Real prep
  • Florian Golemo: Sim2Real Demo and DeepRL support
  • Ken Ming Lee: DeepRL and Sim2Real prep
  • Miguel Saavedra: Computer Vision and ROS support
  • Sacha Morin: Computer Vision and ROS support
  • Steven Parkison: Computer Vision and ROS support
  • Simon Chamorro: Social organization
  • Special thanks to Mila for giving us space and Mila IT/IDT for setting up the computers used for training deepRL policies in IsaacsGym.