Week 8 · Learn: A baseline is a reference contract

Session 1 of 4 · Characterize your robot · Phase 2

Plan about 15 minutes for explanation, 30 minutes for practical work and 10–15 minutes for documentation. A longer build may continue into the next session: stop safely, commit the current state and record the next check. Desktop simulations count as software evidence; label them clearly and record physical validation separately.

Engineering challenge

What does your robot do reliably, and what must the next controller improve? This session focuses on a baseline is a reference contract.

Before you start

The previous week’s recorded baseline and Week 7, Improve. For later sessions this week, retain the preceding session’s files and predictions.

Equipment: Desktop Python, editor, paper and ruler; for physical work, the configured 3pi+ 2040, clear floor mat and hardware checklist. Week 3 additionally uses the separate low-voltage LED circuit described in its procedure.

For any motion, verify the stop button, short time limit and clear floor area first. Keep the wheels raised for a new device program until its commands and stop behaviour are checked. A hazard or uncertain input is a reason to stop and document, not to force the trial to finish.

Theory and mathematics

A baseline is a reference contract

A baseline specifies both software and test conditions. The same code on a different surface is not an identical trial. Record wheels, load, battery set, floor material, starting guide and calibration version. Requirements express what a result must do, such as stop within 5 cm of a target in a clear lane. Choose them before viewing results. A baseline enables later control experiments to answer whether complexity helped rather than merely whether a new program worked once.

Worked example — illustrative values

Fictional distance errors −0.03, 0.00 and +0.03 m average to 0 m, but mean absolute error is (0.03 + 0 + 0.03)/3 = 0.02 m. Zero signed bias does not mean accurate individual stops.

Write the calculation in your notebook before running code. State which values you measured, which you assumed and which the program calculates. A correct numerical calculation cannot rescue an incorrect physical assumption.

Run and explain the model

The following is desktop Python, not a ready-to-run motor program. Download this week’s example, save it in your student repository and run python3 code/w08.py from the repository root. The same small model is reused across the week so you can learn it, build with it, test it and revise it.

# Desktop Python teaching example. Numerical inputs are illustrative.
errors_m = [-0.03, 0.0, 0.03]  # fictional
print("bias_m", sum(errors_m) / len(errors_m))
print("mean_absolute_error_m", sum(abs(e) for e in errors_m) / len(errors_m))

Predict the example’s output by hand. Mark the inputs, units and assumptions; explain where this model could fail. If an exception appears, read its final line, identify the input or assumption that caused it and make the smallest explained correction. Do not delete validation merely to obtain output.

Understanding the model and its limits

The three signed residuals cancel to zero bias, but their absolute values do not cancel. The example has mean absolute error 0.02 m, so a zero mean signed error does not mean perfect prediction. Report both with the individual residuals. A comparison of surfaces should use the same starting protocol, command and measurement method; a battery change at the same time makes a causal surface claim ambiguous. When revising a model, fit on development data and keep another batch for validation. Preserve the original parameter set so your report can reproduce the baseline.

Practical instructions

1. Freeze your forward and turning source files and calibration values.
2. Write two baseline requirements with numeric tolerances and permitted floor conditions.
3. Create a test matrix for straight travel and turning on the current surface.
4. Identify which measurements are independent of the model being assessed.

Experiment

Use a fictional signed-error list to contrast bias with absolute error; then choose which metric matches each baseline requirement.

Before testing, record your prediction, changed factor, measured response, fixed conditions and stopping rule. Save every attempted run, including failures, with a condition and source version. If hardware is unavailable, use an explicitly labelled synthetic/replay dataset and list the physical question it cannot answer. Do not invent completed trials.

Deliverable

A frozen configuration and two measurable requirements with independent references.

Save notebook/w08-s1.md, the relevant code revision, raw CSV or test-case records, and one labelled diagram/plot/table. Link the files relatively from your notebook. Use the entry template and report guide.

Completion criteria

• Explain a baseline is a reference contract in your own words using this session’s example and its units/assumptions.
• Produce the specific evidence above: A frozen configuration and two measurable requirements with independent references.
• Keep predictions and raw outcomes, distinguish observations from interpretation, and explain one limitation or unresolved failure.
• Review the Git diff, commit the session’s intended files and state the next experiment or safe continuation point.

A documented failed prediction can meet the learning criteria. A missing physical trial must remain marked untested; software success alone does not validate the robot.

Reading and video

• Focused reading: Robotics Lab: scientific testing guide. Study task: Explain why tuning and held-out validation use different trials.
• Video/lecture option: CS50 Python: loops. Study task: Pause on a loop and predict its output before continuing. Watch a relevant 5–10 minute excerpt or use the linked notes if video is inaccessible. This is supporting conceptual material; hardware in a demonstration may differ from yours.
• Practical reference: Engineering handbook and hardware setup. Manufacturer/API references and video metadata were checked on 2026-10-09; recheck the actual firmware before transferring code.

Reflection and next step

Which assumption most affected your result? Point to one observation that supports your explanation and one alternative explanation the evidence has not ruled out. Write a specific next test with a changed factor and measurable outcome, then proceed through the week’s Learn → Build → Experiment → Improve cycle.