About this course

Robotics and AI are all around us and promise to revolutionize our daily lives. Autonomous vehicles have a huge potential to impact society in the near future, for example, by making owning private vehicles unnecessary!
Have you ever wondered how autonomous cars actually work?
With this course, you will start from a box of parts and finish with a scaled self-driving car that drives autonomously in your living room. In the process, you will use state-of-the-art approaches, the latest software tools, and real hardware in an engaging hands-on learning experience.
Self-driving cars with Duckietown is a practical introduction to vehicle autonomy. It explores real-world solutions to the theoretical challenges of autonomy, including their translation into algorithms and their deployment in simulation as well as on hardware.
Using modern software architectures built with Python, Robot Operating System (ROS), and Docker, you will appreciate the complementary strengths of classical architectures and modern machine learning-based approaches. The scope of this introductory course is to go from zero to having a self-driving car safely driving in a Duckietown.
This course is presented by Professors and Scientists who are passionate about robotics and accessible education. It uses the Duckietown robotic ecosystem, an open-source platform created at the MIT Computer Science and Artificial Intelligence Laboratory and now used by over 150 universities worldwide.
We support a track for learners to deploy their solutions in a simulation environment, and an additional option for learners that want to engage in the challenging but rewarding, tangible, hands-on learning experience of making the theory come to life in the real world. The hardware track is streamlined through an all-inclusive low-cost Jetson Nano-powered Duckiebot kit, inclusive of city track, available here.
This course is made possible thanks to the support of the Swiss Federal Institute of Technology in Zurich (ETH Zurich), in collaboration with the University of Montreal (Prof. Liam Paull), the Duckietown Foundation, and the Toyota Technological Institute at Chicago (Prof. Matthew Walter).
Course created with support from

At a Glance:
Institution: ETHx
Subject: Computer Science
Level: Introductory
Prerequisites:
Basic Linux, Python, Git:
we are going to use a terminal interface, so basic knowledge of Bash is required (cd, ls, mkdir, …)
We are going to write “autonomy” code in Python
We are going to pull, fork, push, branch repositories, etc.
Elements of linear algebra, probability, and calculus:
We are going to use matrices to represent coordinate systems
We are going to use notions of probability (marginalization, Bayes theorem) to derive perception algorithms for the Duckiebot
We are going to write down equations of motion, which involve ODEs (recognizing the acronym is a good start!)
Computer with native Ubuntu installation
We are going to use Ubuntu 22.04 with a native (e.g., dual boot) installation*
Minimum requirements: Quad-core at 1.8Ghz, 4GB RAM, 60GB hard drive, GPU compatible with OpenGL 2.1+
Recommended setup: Quad-core at 2.1Ghz, 8GB RAM, 120GB hard drive, GPU compatible with OpenGL 2.1+
A broadband internet connection: we are going to up and download gigabytes of data (exercises, activities, agent submissions)
Language: English
Video Transcript: English
Associated skills:Python (Programming Language), Autonomous Vehicles, Algorithms, Robot Operating Systems, Docker (Software), Machine Learning, Artificial Intelligence, Automation, Computer Science, Robotics