Duckietown is an organization which started as an MIT class in 2016 with the purpose of offering engineers around the world a new and fun way to learn about robotics and computer vision
In December 2018 the Duckietown Foundation debuted the AI Driving Olympics (AI-DO), a competition focused on AI for self-driving cars, at the premiere machine learning conference: Neural Information Processing Systems conference (NeurIPS) in Montreal.
It was the first competition to ever take place at a machine learning conference with real robots.
You can learn more about it here
The Automation Engineering Association Polimi contacted us with a great idea: to join forces to create a team composed of both Computer Science and Automation Engineers who could work with Duckietown and even join their competition (of course students from other courses are welcome as well)!
We believe it could be a great opportunity for students interested in the topic to learn new things, test their abilities by working on a real world project and, most of all, have fun!
The purpose of the competition is to teach a small robotic car to navigate on a track, which is no easy task.
But of course Polimi students aren't famous for backing down from challenges! If you have some experience with reinforcement learning or machine learning in general, apply in the form below and you might get selected to be part of the team!
The main objective of the team is an ambitious one, to take part in the Duckietown biannual competition, AI Driving Olympics (AI-DO)
The challenge is open to everyone, as you don't even need to go to the competition site to partecipate but you can just sumbit you solution from home.
Moreover, the Duckietown foundation offers many useful resources and simulation tools so even people who can't afford hardware for the robot can compete.
If you're interested, apply for a position on the team with the sumbission form below!