A Spring course in the Massachusetts Institute of Technology's (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL) aimed to create a fleet of 50 rubber duckie-adorned self-driving taxis that can navigate the roads of a model city with a single on-board camera and no pre-programmed maps.
The model city, called Duckietown, is designed to help roboticists incorporate their open source teaching materials and $100 "Duckiebot" design into other schools' programs. "We hope this will make it easier for computer scientists to continue to work together to bring autonomous vehicles into the real world," says CSAIL researcher Liam Paull.
The researchers also have used the platform to prototype algorithms for CSAIL's recently announced $25-million collaboration with Toyota on autonomous cars.
The class focuses on developing perception, object detection, and tracking for autonomous vehicles. Students developed algorithms to read traffic signs and notice pedestrian-ducks, and learned to integrate different disciplines such as control theory, machine learning, and computer vision into their systems.
Duckietown is a collaborative effort involving more than a dozen people from CSAIL and MIT's Laboratory for Information and Decision Systems, as well as researchers from the departments of mechanical engineering, aeronautics and astronautics, and electrical engineering and computer science.
From MIT News
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found