Duckietown goes online to teach autonomous systems

Duckietown is a worldwide initiative to realize a new vision for education in artificial intelligence (AI) and robotics. Participants learn to program toy-sized autonomous vehicles with rubber ducks as passengers, so that they can navigate a structured environment. Today, over 90 universities in 25 countries use Duckietown for teaching and research in the field of autonomous systems.

Initiated in 2015 at the Massachusetts Institute of Technology (MIT), Duckietown has been further developed by ETH Zurich in cooperation with the University of Montreal. At ETH, Jacopo Tani and Andrea Censi, both senior scientists in Professor Emilio Frazzoli’s group at the Department of Mechanical and Process Engineering, head the Duckietown project. Their newest endeavor is to create a series of massive open online courses (MOOCs). In addition to ETH and the University of Montreal, the MOOC-series is designed in cooperation with the Toyota Technological Institute at Chicago, hosted on the online course platform edX, and powered by the computational hardware resources of NVIDIA. The series will focus on the science and technology of autonomy through the lens of self-driving cars.

“Participants will learn how to have real-world machines make their own decisions to accomplish broadly defined tasks”, says Jacopo Tani. “This topic is both intellectually fascinating and very timely given the rapid progress of robotics and AI technologies in our daily lives.” Participants will engage in a sequence of hands-on software and hardware learning experiences with particular focus on overcoming the challenges of deploying robots in the real world. “We hope they will gain useful skills and come to appreciate the challenges of this technology, while at the same time having fun!”, says Tani.