Reason about Drone Mission Plans with Probabilistic Logic
Overview
What this challenge is about.
Build a small Bayesian network (around 12 nodes) capturing weather, no-fly-zone proximity, battery state, operator certification, and mission risk. Implement exact inference (variable elimination is fine for this size). Write 20 test cases with expected risk-classification outputs hand-labeled by a domain inspector. Evaluate accuracy and the network's calibration. Produce a 2-page methodology section that the consultancy can drop into its municipal-RFP response (request for proposal). Be explicit about what the network does and does not know.
The Brief
What you'll do, and what you'll demonstrate.
Build a Bayesian-network reasoner for drone-mission risk and validate it against inspector-curated test cases.
Earning criteria — what you'll demonstrate
- Model uncertain knowledge as a Bayesian network
- Implement exact inference (variable elimination) on a small network
- Validate a probabilistic system against domain ground truth
- Write methodology prose for a non-technical procurement audience
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
Implementing a working probabilistic reasoner and validating it against domain labels is the kind of grounded AI engineering municipalities and consultancies actually buy.
This challenge sharpens
- bayesian-networks
- probabilistic-inference
- python
Data Scientist
Probabilistic modeling and calibration are core data-scientist skills that transfer to any risk-classification problem.
This challenge sharpens
- probabilistic-inference
- model-validation
- knowledge-representation
AI Solutions Architect
Designing a knowledge-representation module that slots into a larger product is the solutions-architect's bridge between domain knowledge and code.
This challenge sharpens
- knowledge-representation
- bayesian-networks
- model-validation