Monday, August 20, 2018

Duckietown: How Rubber Ducks Are Being Used to Teach Concepts in Autonomous Driving



Image credit: Jason Dorfman/MIT CSAIL

Duckietown combines robotics and rubber ducks to introduce students to concepts in autonomous driving in a scalable, modular, and inexpensive fashion. Andrea Censi from ETH Zurich has expanded the Duckietown class into a Kickstarter project after strong support from both the media and academic world. Individuals are able to purchase a Duckiebox for $150 USD and create their own Duckiebot at home.

After recognition in the 2016 International Conference on Robotics and Automation conference, rubber ducks are known in the robotics community as an amusing and cheap prop often used to indicate the size of a project. Duckietown takes this icon and uses it for learning purposes.

Andrea Censi explains the concepts taught through the Duckietown simulation: “At an undergraduate level, students using Duckietown learn the fundamentals of autonomy (perception, estimation, decision making, actuation, the relevance of environmental disturbances, modeling, etc.), robotics (system level interplay of functionalities), and computer vision (line detection).”

In contrast to traditional classroom experiences where students work on individual projects, every Duckiebot runs on the same master code that students are capable of modifying. Thus, the team must work together to ensure the common objective is achieved; this communicates the interdependency required in engineering.

Read more about Duckietown at: https://spectrum.ieee.org/automaton/robotics/artificial-intelligence/learn-to-program-self-driving-cars-and-help-duckies-commute-with-duckietown
Visit the Duckietown website at: https://www.duckietown.org/
Visit the Kickstarter to support Duckietown at: https://www.kickstarter.com/projects/163162211/duckietown-a-playful-road-to-learning-robotics-and/

No comments:
Write comments