Skip to content

Activité

AI light switch

Intermédiaire | MakeCode | Accéléromètre, Radio, Écran LED | Apprentissage automatique, Comprendre l'IA, Entrée / Sortie

Make an AI light switch with micro:bit CreateAI that makes a light turn on when you clap and turn off when you wave.

Guide de projet étape par étape

Étapes 1 : comprendre

How does it work?

In this project, you’ll train a machine learning (ML) model to recognise when you’re clapping and waving.

You’ll combine that model with a MakeCode program that sends a ‘lightsOn’ radio signal to another micro:bit whenever you clap, and a ‘lightsOff’ radio signal whenever you wave.

When the receiver micro:bit receives the ‘lightsOn’ signal, all its LEDs light up. When it receives the ‘lightsOff’ signal, it clears its LED display.

Qu'est-ce que l'apprentissage automatique ?

L'apprentissage automatique (Machine Learning en anglais) est une sorte d'intelligence artificielle (IA) où les ordinateurs peuvent apprendre et prendre des décisions basées sur des données.

Les modèles d'apprentissage sont formés par les humains pour les aider à prendre ces décisions, par exemple, pour reconnaître différentes ‘actions’ lorsque vous déplacez votre micro:bit de différentes manières.

Que dois-je faire ?

Les systèmes IA ont besoin d'êtres humains pour les concevoir, les construire, les tester et les utiliser. You'll collect data to train an ML model, test it, improve it, and combine it with computer code to make a smart device that uses AI. Vous utiliserez un micro:bit et le site web micro:bit CreateAI pour faire cela.

Étape 2 : programmer

Ce dont vous aurez besoin

Collecter des échantillons de données

When you open the project in micro:bit CreateAI, you’ll see we’ve given you some data samples for ‘waving’, 'clapping’ and ‘still’ actions:

You can add your own movement samples using the micro:bit's movement sensor or accelerometer.

Dans micro:bit CreateAI, cliquez sur le bouton « Se connecter » pour connecter votre collection de données micro:bit et suivez les instructions.

Photo of micro:bit with cross icon on its display, attached to someone's wrist.

Attach the micro:bit to your wrist. Click on the first action, ‘waving’, and click 'Record'. En cas d'erreur, vous pouvez supprimer les échantillons que vous ne souhaitez pas. Vous pouvez également appuyer sur le bouton B du micro:bit pour commencer l'enregistrement.

If you would like to record continuously for 10 seconds to get 10 samples, click on the three dots next to the record button and select that option.

Now record your own data samples for the ‘clapping’ and 'still' actions, making sure for 'still' that you collect samples in different positions, such as facing up and down.

Entraîner et tester le modèle

Click the ‘Train model’ button to train the model. Try clapping, waving and keeping still to see if those actions are estimated. Give your micro:bit to someone else to wear (making sure they put it on the same wrist and in the same orientation) and see if it works as well for them.

Améliorer votre modèle

La plupart des modèles peuvent être améliorés avec plus de données. If the model needs improving, click on ‘← Edit data samples’.

You can delete any data samples which you think don’t fit or add more samples.

Entraînez à nouveau le modèle et testez-le à nouveau.

Mettez le modèle et le code sur votre micro:bit

Dans micro:bit CreateAI, cliquez sur « Modifier dans MakeCode » pour voir le code du projet dans l'éditeur MakeCode.

You can modify the code or just try it out as it is. Attach the first micro:bit using a USB cable, click on the ‘Download’ button in the MakeCode screen, and follow the instructions to transfer your AI model and the code blocks to it. Afterwards, download again onto another micro:bit.

Attach a battery pack to the sender micro:bit. You can keep the receiver micro:bit plugged into the computer or attach it to battery pack. Now wear the sender micro:bit and test it out.

Comment fonctionnent les blocs de code

When the program starts, the radio group is set to 52. Radio groups are like channels, so any micro:bit using the same group will get the message. Vous pouvez utiliser n'importe quel numéro de groupe de 0 à 255. If you are using this project in a class or coding club, you might like to encourage each pair or group of students to use a different radio group from others in the class.

The 'on ML... start' blocks are triggered when the sender micro:bit’s ML model decides you have started waving, clapping or being still.

If you are clapping, the ‘on ML clapping start’ block causes a tick icon to appear on the LED display of the sender micro:bit and the radio message ‘lightsOn’ to be sent to the receiver micro:bit. If you are waving, the ‘on ML waving start block’ causes a cross icon to appear on the LED display of the sender micro:bit and the radio message ‘lightsOff’ to be sent to the receiver micro:bit.

If you are still or the sender micro:bit can’t recognise your movements, the LED display is cleared and no radio message is sent.

The ’on radio received’ blocks turn on all the LEDs on the receiver micro:bit if a message is received saying ‘lightsOn’ and clear the screen if a message is received saying ‘lightsOff’.

The ‘on radio received lightsOn / lightsOff’ blocks are from a MakeCode extension called ‘Radio broadcast’. If you want to code this project yourself, you can find the blocks by clicking on ‘Extensions’ then choosing ‘Radio broadcast’.

Évaluation

How accurate is the light switch in turning on and off in response to your movements? How could you improve it, if needed?

How useful would this device be in real life? How does it compare to a regular light switch?

Étape 3 : étendre

  • You could light up a room by putting the same code on multiple micro:bits. Keep the other micro:bits still while someone moves another to turn them all on or off.
  • Add a fourth action which causes the receiver micro:bit to show dimmed lights. Use the ‘set brightness’ block, found in the LED section under ‘More’.