Buried deep within the halls of MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) lies a small suburb called Duckietown, a mock-up municipality used to test and develop driverless technology. Populated entirely by rubber ducks riding on autonomous robo-taxis, Duckietown is the culmination of a graduate-level class that could prove invaluable to automakers in the future.
“We believe a tool like this will help create a common platform and language for researchers to build on,” said CSAIL postdoctoral associate Liam Paull, who co-leads the Duckietown course. “We hope this will make it easier for computer scientists to continue to work together to bring autonomous vehicles into the real world.”
To bring us closer to the driverless future, 50 “Duckiebots” wander the colorful foam streets of Duckietown, using a single onboard camera to track road markings, monitor their fellow Duckiebots, and even read street signs. It’s not quite the real thing — there are no worn lane markings or inclement weather to deal with — but according to Andrea Censi, an MIT researcher who also leads the class, that isn’t really the goal.
“We thought about key problems like integration and co-design,” said Censi. “How do we make sure that systems developed separately will work together? How do we design systems that maximize performance while sharing resources? It’s a delicate balancing act in weighing the relative importance of different infrastructure elements.”
If you’re looking to build a Duckiebot, Doggiebot, or G.I. Joe action-figurebot for yourself, there is good news — the robo-taxi platform and the attached teaching materials are free and open-source. That means someday soon, you could have your very own autonomous community in your basement, albeit a small one. To stay up to date on all the happenings in Duckietown, check out the team’s Facebook page.
