Overview
What this challenge is about.
Use the public Donkeycar Tub dataset (or collect about 30 minutes of driving on the simulator). Train a CNN-policy baseline (the Donkeycar default architecture is fine) that predicts steering + throttle from camera frames. Run 3 ablations: image augmentation on/off, RGB vs. grayscale input, and a smaller backbone. Evaluate via simulator lap-time and lane-departure count. Deliver a teaching notebook + 5-page lab guide for next semester's students.
The Brief
What you'll do, and what you'll demonstrate.
Ship a reproducible end-to-end lane-following teaching reference with 3 ablations and a student-ready lab guide.
Earning criteria — what you'll demonstrate
- Train an end-to-end imitation-learning policy from camera data
- Design and run informative ablations
- Evaluate driving models in simulation with clear metrics
- Document a teaching reference that students can rerun
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
Careers
Roles this prepares you for.
Real titles. Real skill bridges. Pick the one closest to your trajectory.
AI Engineer
Packaging an end-to-end ML system as a reproducible reference is the AI-engineer skillset that scales teams and onboards new colleagues.
This challenge sharpens
- end-to-end-learning
- ablation-study
- documentation
Machine Learning Engineer
Designing informative ablations with proper hold-out evaluation is the MLE habit that distinguishes shippable from one-shot work.
This challenge sharpens
- imitation-learning
- pytorch
- ablation-study
AI Product Designer
Writing a lab guide a first-week student can follow is the UX-of-ML craft AI product designers carry into product surfaces.
This challenge sharpens
- documentation
- data-augmentation
- ablation-study