Overview
What this challenge is about.
You receive 4 hours of recorded sidewalk traversals with annotated pedestrian tracks, occupancy grids, and a map of the pilot neighborhood. Implement a sampling-based planner (RRT* or its informed variant) with a cost function that encodes the social constraints. Compare against a vanilla A* baseline on three metrics: success rate, mean clearance from pedestrians, and time-to-goal. Report on 30 held-out scenarios. Deliver the planner, a benchmark report, and a 5-slide briefing for the operations lead.
The Brief
What you'll do, and what you'll demonstrate.
Design and benchmark a sampling-based planner that lifts safety clearance without sinking time-to-goal on a real sidewalk dataset.
Earning criteria — what you'll demonstrate
- Implement a sampling-based motion planner with a structured cost
- Design a cost function that encodes social/safety constraints
- Evaluate plans on real-world metrics (clearance, success, time)
- Communicate planner trade-offs to a non-engineering stakeholder
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
Wiring planning algorithms into a real robot stack with measurable safety metrics is everyday AI-engineer work at last-mile robotics companies.
This challenge sharpens
- motion-planning
- python
- evaluation
Machine Learning Engineer
Cost-function design with held-out evaluation is the same discipline MLEs apply to loss functions and policy tuning.
This challenge sharpens
- cost-function-design
- evaluation
- python
Applied AI Scientist
Briefing a non-engineer stakeholder on planner trade-offs is the soft-skill side of applied-AI work in operations-heavy robotics.
This challenge sharpens
- motion-planning
- evaluation
- cost-function-design