Guides for getting started
Duckietown is at the intersection of education, training, and research and is intended for instructors, researchers, and makademics. Do you already know where you stand? Skip these guides and start learning!
I am an instructor
Vision
These materials can be used in several 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.
- As a flipped classroom – where the students watch the Duckietown “Self-Driving Cars” massive open online course (MOOC) materials from home, and you use the class time to work through the proposed activities and exercises.
The “class-in-a-box”
Setting up a state-of-the-art robot autonomy class is hard and time-consuming. The Duckietown class-in-a-box is designed to be a one-click solution to modern robot autonomy education.
The class-in-a-box will include:
- Slides and lecture videos (for inspiration or flipped classroom);
- Python notebooks with lecture notes and tutorial activities;
- Exercises with automatic online grading;
- Robot-centered activities and demos;
- Development environment (Duckietown Shell) and simulator;
- Classroom kits with Duckiebots and Duckietowns;
- An instructor’s guide;
- Access to separate Slack communities for instructors and students with class dedicated channels;
- Access to the Duckietown Stack Overflow;
About the community
If you bring Duckietown to your institution, your students will be joining a fun, global community, which includes opportunities for worldwide collaboration and competition, e.g., the AI Driving Olympics, featured yearly in scientific venues like ICRA and NeurIPS!
Instructor next steps
- Join the Duckietown Slack so you can communicate with the community efficiently;
- Check the available classroom resources;
- Get a classroom kit, containing all the hardware you need to get started.
I am a researcher
Vision
We designed Duckietown to be a modular, inexpensive research platform for studying autonomy in complex systems.
Think of it as an “experimental simulator” which exposes the nuisances fo the real world while preserving control over the environments.
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).
Example 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 robots and smart city environment
- An international embodied AI competition (AI-DO)
- A community to bounce ideas off
- A simulation-based system for robotic agent benchmarking
- A physical system for reproducible agent benchmarking (Autolab)
- Here is a partial list of published papers using Duckietown.
Researcher next steps
- Join the Duckietown Slack
- Check out the documentation in the Duckiebook
- Get the hardware
and start testing or training your algorithms with our templates, logs, simulator
Want to build a Duckietown Autolab at your institution? Reach out to us on Slack or by email.
Learn autonomy with Duckietown
Want to learn autonomy.. in autonomy? You might be a Makademic!
Makademics are a fusion of “makers” and “academics”.
You are a Makademic if you want to learn and build on your own, outside of an educational institution, and also want a 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.
Duckietown is learning autonomy: we provide a unique hands-on learning experience, and an international community to bounce off ideas with.
Makademic next steps
- Join the Duckietown Slack to, e.g., find an instructor at your institution who will teach the course
- Join the massive open online course “Self-Driving Cars with Duckietown”
- Get the hardware
You can also :
- take a look at all the learning resources we have as well as our Duckiebook
- Join the AI Driving Olympics and challenge your understanding with the community!
Need help? Join the Slack community and ask away!
Teddy OrtPh. D. Student, Massachusetts Institute of Technology (MIT)
Manfred DiazPh. D. Student, University of Montreal
Matthew WalterProfessor, Toyota Technological Institute at Chicago (TTIC)