AI Driving Olympics

Important Dates for AI-DO at ICRA

Local evaluations and training in simulator: February 15th
Get started right away and evaluate your algorithms locally

Submissions open: April 1st
Submit your algorithms to our challenges server and see how you place in the standings. 

Challenge evaluation criteria finalized: April 15th
Now that we’ve calibrated the rules and evaluation criteria to match the quality of the submissions you can fine tune your approach

Real Robot Evaluations: May 1st
For those who do not have access to their own Duckiebot and Duckietown, we hope to provide opportunities for testing of algorithms through online submission and remote running on Duckietown “robotariums” in Zurich, Chicago, or Montreal.
*Note: The success of this process is dependant on the number or competitors and availability of robotarium volunteers. We thank you for your understanding.

Final testing opportunity in our demo Duckietown at ICRA: May 20, 21, 22
Test your submission on a Duckiebot ahead of the live competition

Live competition at ICRA: May 22 afternoon
Come one come all to watch the final runs of the top ranking competitors

Get Started

The not-so-quick start

Train in the simulator
Section 1.4 of https://docs.duckietown.org/DT18/AIDO/out/ros_baseline.html

Prepare for submissions




Do I need to attend ICRA to compete in the competition?

No! If you are not present at the conference we will run your submission on your behalf.

How do I get help?

File a github issue or ask a question to the community

How do I get a Duckiebot?

Send us an email and we’ll help you out!

About the AI-DO

The Duckietown Foundation is excited to host the The AI Driving Olympics (AI-DO), a competition focused around AI for self-driving cars.

The first edition of the AI-DO took place in December 2018, at NeurIPS, the premiere machine learning conference, in Montréal. This is the first competition that will take place at a machine learning conference with real robots.

The second edition of AI-DO will take place in May 2019 in conjunction with the International Conference on Robotics and Automation (ICRA) 2019.

The main purpose of the competition is to probe the frontier of the state of the art in machine learning in the interactive and embodied setting. 

Recent progress in Deep Learning, Machine Learning, and Reinforcement Learning has produced incredible results. This competition is designed to evaluate the real ability for these learning-based systems to control physical mobile robots. 

Competitors will have access to simulatorslogs, and a training track that will be available for testing during the conference ahead of the live competition. The entries that score best running on real Duckietowns will be compete during the live event.

Quotes from the experts

“The AI Driving Olympics is a great way to push the limits of deep learning on physically embodied systems.”

Yoshua Bengio, University of Montreal

“The AI Driving Olympics offer a glimpse of the challenges of creating self-driving cars. A playful but rigorous competition on a smaller and safer testbed is the best way to develop the creativity needed to make progress in this field.”

Emilio Frazzoli, ETH Zurich / nuTonomy

“It is great to see Duckietown host the AI Driving Olympics at ICRA and NIPS. What a fun way to demonstrate the real challenges in building and deploying self driving cars!”

John Leonard, MIT

“Starting from MIT CSAIL, Duckietown has grown into a global initiative that is inspiring students around the world to learn about self-driving cars, as well as the science and engineering of autonomy.“

Daniela Rus, MIT

Thank you to our generous sponsors!

Close Menu