{"id":1308,"date":"2020-08-12T10:35:57","date_gmt":"2020-08-12T08:35:57","guid":{"rendered":"https:\/\/wpethzprd.ethz.ch\/letblog\/?p=1308"},"modified":"2021-02-10T14:04:20","modified_gmt":"2021-02-10T13:04:20","slug":"learning-autonomy-with-self-driving-cars-duckietown-goes-mooc","status":"publish","type":"post","link":"https:\/\/blogs.ethz.ch\/letblog\/2020\/08\/12\/learning-autonomy-with-self-driving-cars-duckietown-goes-mooc\/","title":{"rendered":"Learning Autonomy with Self-Driving Cars: Duckietown goes MOOC."},"content":{"rendered":"\n
\"\"
Figure  1 Tani (left) and Censi (right) in the Duckietown Lab
(Picture: ETH, Alessandro della Bella) <\/figcaption><\/figure>\n\n\n\n

Jacopo Tani and Andrea Censi are senior assistants in the research group headed by Emilio Frazzoli (D-MAVT), an internationally renowned specialist in autonomous systems. Together with Prof. Liam Paull of the University of Montreal, they lead the Duckietown<\/a> project, which was conceived at the Massachusetts Institute of Technology (MIT) in 2015. The goal was to build a platform that was small-scale and cute yet still preserved the real scientific challenges inherent in a full-scale real autonomous robot platform.  Duckietown is now a worldwide initiative to realize a new vision for AI\/robotics education. It teaches participants to programme autonomous vehicles to navigate a structured environment using rubber ducks as the passengers of the vehicles, and has now been used by over 80 universities in 23 countries worldwide. Their next endeavor is to create a series of massive open online courses (MOOCs) focused on the science and technology of autonomy through the lens of self-driving cars. In this multi-institution project, ETH will take leadership and develop the first course of the MOOC-series.<\/p>\n\n\n\n

What\nwill the MOOC be about and what do you seek to achieve for participants?<\/strong><\/p>\n\n\n\n

The Duckietown MOOC series will be about\nautonomy, or how to make machines take their own decisions to accomplish\nbroadly defined tasks. This topic is both intellectually fascinating and very\ntimely given the rapid progress of robotics and AI technologies in our daily\nlives. Autonomy will be studied through self-driving cars, an application with\ndisruptive social potential.<\/p>\n\n\n\n

Participants will engage in a sequence of\nsoftware and hardware hands-on learning experiences whose particular focus is\non overcoming the challenges of deploying robots in the real world. Our hope is\nthat participants will gain useful skills and come to appreciate and understand\nthe challenges of this technology, while at the same time having lots of fun! <\/p>\n\n\n\n

What\nmotivated you personally to make a MOOC?<\/strong><\/p>\n\n\n\n

The Duckietown project was developed to make\nthe science and technology of autonomy accessible to the broadest possible\naudience, not only to those learners lucky enough to have access to premiere\neducational institutions where these topics are addressed. Building a\nDuckietown MOOC experience was a logical step towards achieving the mission of\nthe project. We are grateful for ETH-Innovedum supporting our efforts and\nextremely excited to bring our vision for learning autonomy to the world.    <\/p>\n\n\n\n

What\nare the unique didactic challenges?<\/strong><\/p>\n\n\n\n

Teaching autonomy requires a fundamentally\ndifferent approach compared to many computer science and engineering\ndisciplines. There is extensive and diverse preliminary knowledge needed to\nreally comprehend autonomy from the “pure” mathematics and physics to\n“modern” machine learning based approaches. Moreover, robots are real\nworld machines, and theory and practice do not always play well together. To\nsee the theory work in the real world it is necessary to translate the\nknowledge in software architectures, and deploy them on hardware platforms.\nFinally, there is a proliferation of hardware platforms and software tools out\nthere, each with its own peculiarities, strengths and shortcomings. It is not\nalways clear what tools are worth investing time in mastering, and how this\ncompetence will translate to different platforms.    <\/p>\n\n\n\n

 How will you overcome these challenges?<\/strong><\/p>\n\n\n\n

To address these barriers of entry to learning\nautonomy, the MOOC \u201eSelf-Driving Cars with Duckietown\u201c will have several\ndistinguishing features, namely: <\/p>\n\n\n\n