Overview
What this challenge is about.
Use CARLA (open-source AV simulator) and encode 10 representative safety scenarios across 3 categories (cut-in, pedestrian emergence, signalized-intersection right-of-way). Write pass-fail criteria in code (e.g., minimum time-to-collision, no comfort-threshold violations). Hook the harness to a stand-in planner (CARLA's built-in autopilot is fine), produce a HTML dashboard summarizing pass-fail counts per category over the last 7 runs, and write a 3-page handover doc.
The Brief
What you'll do, and what you'll demonstrate.
Ship a CARLA scenario test harness that auto-scores 10 safety scenarios and produces a Monday-morning regression dashboard.
Earning criteria — what you'll demonstrate
- Build reproducible scenario tests in an AV simulator
- Define measurable safety criteria (time-to-collision, comfort)
- Wire a regression dashboard to recurring test runs
- Hand a test asset off to a team that will own it long-term
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 Safety Researcher
Reproducible scenario testing with measurable safety criteria is the day-one safety researcher's work at any AV company.
This challenge sharpens
- scenario-testing
- safety-evaluation
- simulation
MLOps Engineer
Recurring test harnesses + regression dashboards are MLOps-style infrastructure for safety-critical ML systems.
This challenge sharpens
- ml-pipelines
- dashboarding
- python
AI Engineer
Wiring a simulator, criteria, and dashboard into a single deliverable handover is the AI-engineer-as-toolsmith role AV companies hire for.
This challenge sharpens
- simulation
- scenario-testing
- dashboarding