Welcome to the webpage for Self-driving Vehicles: Models and Algorithms for Autonomy (TTIC 31240), which is informally known as “Duckietown”. This is the first time that the course is being offered at TTIC, following the extremely successful first edition at MIT in 2016.

Read below about what makes this a special class.

For TTIC and UChicago Students: The number of spots available is extremely limited due to resource constraints (e.g., each student gets a robot). Consequently, registration is subject to instructor approval.

Please read this page thoroughly and sign up only if you think the class is right for you. It might help to take a look at the materials for the first edition of the class, available at duckietown.mit.edu.

If you’d like to register for the course, you must first complete this questionnaire, which helps us fine-tune the class to your background.

Positions available

For TTIC and UChicago Students: We have openings for the following positions:

For TTIC and UChicago postdoctoral researchers and senior Ph.D. students: In the inaugural class at MIT, one of the collateral uses of Duckietown was to provide an opportunity for postdocs to develop their teaching and mentoring skills. We will reproduce the same idea this quarter.

We are looking for:

Dates and times

Lecture times:

daytimeroom
Monday 9am-11am TBD
Wednesday9am-11am TBD

Instructor

Learning assistants:

  • Andrea Daniele
  • Zhongtian (Falcon) Dai
  • TBD

We are looking for more learning assistants. Please contact Matthew Walter if you are interested.

Guest lecturers:

  • TBD
  • TBD

We are looking for postdocs to give guest lectures on their specialties. Please contact Matthew Walter if you are interested.

Syllabus

See the course syllabus for additional details on the class.

Grading

The grade is based on:

  • the realization of a project (percentage TBD);
  • a project report (percentage TBD); and
  • a project presentation (percentage TBD). The projects will be group-based, but the contribution of each student will be assessed individually.

Prerequisites

  • Familiarity with the GNU/Linux development environment.
  • Access to a laptop with Ubuntu 16.04 installed.

The most relevant course at TTIC is:

  • Planning, Learning, and Estimation for Robotics and Artificial Intelligence (aka Robot Learning and Estimation). If you cannot get into Self-driving Vehicles: Models and Algorithms for Autonomy, the Robot Learning and Estimation class will give you a solid introduction to robotics. Because the content and format are different than this course, it would be most beneficial to take Robot Learning and Estimation first, but the two can be taken in either order.

What makes this a special class?

Class philosophy

The best engineers are the ones who have solid theoretical foundations, as well as practical experience.

In autonomous robotics, it is important to also get the “feeling” of what actually makes a robot work. The way to do this, is not to study every component in isolation, but rather to integrate the components as part of a complex system.

For more information about the class philosophy, please refer to this paper:

Jacopo Tani, Liam Paull, Maria Zuber, Daniela Rus, Jonathan How, John Leonard, and Andrea Censi. Duckietown: an innovative way to teach autonomy. In EduRobotics 2016. Athens, Greece, December 2016. pdf

A personal experience

Each student gets their own personal Duckiebot and can bring it home.

Collaboration/competition with twin institutions

This class is offered at the same time at two others institutions:

  • The University of Montreal, Canada, lead by Prof. Liam Paull.
  • ETH Zürich, lead by Dr. Andrea Censi.

The three institutions will develop the autonomous fleets together, and there will be a (very friendly) competition at the end.

Support

We are grateful to TTIC, whose support made this class possible.