Guides for getting started
Getting started for Duckietown Instructors
Vision
The Duckietown platform contains everything you need to teach an undergraduate or graduate level class on AI and robotics; from the off-the-shelf hardware plans, open source software, to the weekly lecture materials.
The materials can be used in two ways:
- Class materials – you use the platform and associated education materials to teach a class on robot autonomy.
- As an experimental platform – where the hardware and software are used as the laboratory component of another class.
Development of the “class-in-a-box”
What the “class-in-a-box” will include:
- Slides, lecture videos (for inspiration or flipped classroom), Python notebooks.
- Lecture notes;
- Exercises;
- Robot-centered activities and demos;
- An instructor’s guide;
About the community
- If you bring Duckietown to your institution, your students will be joining a fun, global community, which includes worldwide collaboration and competition!
Current status
Already 735 students in 10 countries have used Duckietown in university classes to prepare themselves for careers in AI and robotics. (Read more statistics.)
We are now in the process of polishing the experience for students and instructors.
Below, you can find the timeline of releases.
Teddy OrtStudent at MIT
Manfred DiazStudent at Université de Montréal
Matthew WalterProfessor at TTI Chicago
Timeline of releases
September-December 2018
Maturity: The “Class-in-a-box” versions are in preparatory phase. It’s ready for the adventurous instructors!
During Fall 2018:
- The graduate class “Introduction to Autonomy” is taught at select universities (ETH Zürich, Université de Montréal, and TTI Chicago).
- The undergraduate class will be taught at NCTU.
- Students will participate in the AI-DO I competition, which will take place at NIPS 2018 in Montreal.
January 2019
Maturity: The materials are ready and semi-polished.
The official “class-in-a-box” versions of the following classes will be available:
- Introduction to Autonomy (graduate level).
- Control Systems with Duckietown (graduate level).
During Spring 2019:
- Students are encouraged to participate in the AI-DO II as part of the class. Competition will take place at ICRA 2019 in Montréal (students do not need to physically present at ICRA).
During Fall 2019:
- Students are encouraged to participate in the AI-DO III (in a conference to be confirmed).
September 2019
Maturity: Software refactoring and documentation overhaul. Materials being streamlined.
September 2020
Maturity: Ready for everybody in polished form!
Official “class-in-a-box” versions of the following classes available:
- Introduction to Autonomy (graduate level).
- Control Systems with Duckietown (graduate level).
- Introduction to Robotics (undergraduate level).
During Fall 2019:
- Students are encouraged to participate in the AI-DO III (in a conference to be confirmed).
2020 and beyond
More courses will be developed and the materials for the existing courses will continue to evolve and be refined and improved by the community.
Next steps
- Take a look at all the resources that we have available to make building your class as smooth as possible
- You can order hardware kits.
Frequently asked questions
There are no questions matching your query or you do not have permission to read them.
Research using Duckietown
Vision
We designed Duckietown also as an inexpensive research platform for studying autonomy in complex systems.
Value proposition
We provide a baseline implementation for you to be able to rapidly and easily test your algorithms on real physical hardware.
- Convenience: You can only change the part that interests you and use the rest of the baselines to have a fully functional system.
- Reproducibility: Your research has a high impact since it uses a standard platform that others can easily replicate. For maximum impact, compete in an AI Driving Olympics (AI-DO).
Tools for research
- Imitation learning template
- Reinforcement learning template
- Database of Duckiebot driving logs
- Duckiebot driving simulator
- Modularized code (ROS baseline template)
- Low cost, standardized robot + environment
Current users
Please tell us about your research with Duckietown so that we can include it in the list.
Next steps
- Check out the documentation in the Duckiebook
- Start testing or training your algorithms with our templates, logs, simulator
- Get hardware
about autonomy
Makademics are a fusion of “makers” and “academics”. These are people who want to learn and build on their own, outside of an educational institution, and also want a very deep understanding of how things are working. Makademics can learn about robotics and AI by building their own Duckietown and using all of the course materials at their own pace.
We provide a unique hands-on learning experience suitable for Makademics.
All the materials are available at minimal cost. We can help you get a kit.
Next Steps
- If you are a university student, the best case is to find an instructor at your institution who will teach the course
- Take a look at all the learning resources we have as well as our Duckiebook. Here’s the quick start and webinars.
- Get the hardware
- Need help? File a github issue or join the slack community