Session by session
- Session 36 · Ask & understandWeek 18
Form a testable prediction question
Evidence: a question, sketch or new vocabulary
- Session 37 · Build & designWeek 19
Fit a small model on tracker observations
Evidence: a design draft, dataset or build
- Session 38 · ImplementWeek 19
Compare suggested positions with a rule baseline
Evidence: a working version, explained once
- Session 39 · Test & improveWeek 20
Use supervised bounded commands
Evidence: a test log with at least one failure
- Session 40 · Explain & reflectWeek 20
Explain why a simple rule may be sufficient
Evidence: an individual explanation
- Tracker
- Python
- recorded measurements
- optional serial link
Use the same held-out trials for baseline and model.
A laptop model sends named commands only after bench tests, with a simulator as fallback.
Completion needs the artefact, an honest test log, an individual explanation and no open safety or privacy issue.
Projects in the same block
- RoboticsG09-P05
Dual-LDR Tracker
A single-axis light-tracking model.
Sessions 21-25Builder and up - RoboticsG09-P06
Dual-Axis Solar Tracker
A dual-axis demonstration matched to the listed solar-tracker kit.
Sessions 26-30Builder and up - AIG09-P07
Dataset Quality Notebook
A reproducible data-cleaning notebook and change log.
Sessions 31-35Builder and up - IntegratedG09-P08
AI Tracker Comparison
An experiment comparing model advice with rule-based tracking.
Sessions 36-40Builder and up
For school leadersChoose a starting point.
Build from evidence.
Pick the classes and a plan. We map the timetable, kit and safety checks with you, then pilot one class first.
- Prospectus and class-wise plan
- Kit and readiness check
- Pilot one class first
- Evidence at every milestone
Let's plan your pilot.
Share a few details and we will send the right plan for your classes.