Posts | Comments

Planet Arduino

Archive for the ‘machine learning’ Category

If you’re interested in embedded machine learning (TinyML) on the Arduino Nano 33 BLE Sense, you’ll have found a ton of on-board sensors — digital microphone, accelerometer, gyro, magnetometer, light, proximity, temperature, humidity and color — but realized that for vision you need to attach an external camera.

In this article, we will show you how to get image data from a low-cost VGA camera module. We’ll be using the Arduino_OVD767x library to make the software side of things simpler.

Hardware setup

To get started, you will need:

You can of course get a board without headers and solder instead, if that’s your preference.

The one downside to this setup is that (in module form) there are a lot of jumpers to connect. It’s not hard but you need to take care to connect the right cables at either end. You can use tape to secure the wires once things are done, lest one comes loose.

You need to connect the wires as follows:

Software setup

First, install the Arduino IDE or register for Arduino Create tools. Once you install and open your environment, the camera library is available in the library manager.

  • Install the Arduino IDE or register for Arduino Create
  • Tools > Manage Libraries and search for the OV767 library
  • Press the Install button

Now, we will use the example sketch to test the cables are connected correctly:

  • Examples > Arduino_OV767X > CameraCaptureRawBytes
  • Uncomment line 48 to display a test pattern –  Camera.testPattern();
  • Compiler and upload to your board

Your Arduino is now outputting raw image binary over serial. You cannot view the image using the Arduino Serial Monitor; instead, we’ve included a special application to view the image output from the camera using Processing.

Processing is a simple programming environment that was created by graduate students at MIT Media Lab to make it easier to develop visually oriented applications with an emphasis on animation and providing users with instant feedback through interaction.

To run the Arduino_OV767X camera viewer:

  • Install Processing 
  • Open Examples > Arduino_OV767X > extras > CameraVisualizerRawBytes
  • Copy the CameraVisualizerRawBytes code 
  • Paste the code into the empty sketch in Processing 
  • Edit line 35-37 to match the machine and serial port your Arduino is connected to
  • Hit the play button in Processing and you should see a test pattern (image update takes a couple of seconds):

If all goes well, you should see the striped test pattern above! To see a live image from the camera in the Processing viewer: 

  • If you now comment out line 48 of the Arduino sketch
  • Compile and upload to the board
  • Once the sketch is uploaded hit the play button in Processing again
  • After a few seconds you should now have a live image:

Considerations for TinyML

The full VGA (640×480 resolution) output from our little camera is way too big for current TinyML applications. uTensor runs handwriting detection with MNIST that uses 28×28 images. The person detection example in the TensorFlow Lite for Microcontrollers example uses 96×96 which is more than enough. Even state-of-the-art ‘Big ML’ applications often only use 320×320 images (see the TinyML book). Also consider an 8-bit grayscale VGA image occupies 300KB uncompressed and the Nano 33 BLE Sense has 256KB of RAM. We have to do something to reduce the image size! 

Camera format options

The OV7670 module supports lower resolutions through configuration options. The options modify the image data before it reaches the Arduino. The configurations currently available via the library today are:

  • VGA – 640 x 480
  • CIF – 352 x 240
  • QVGA – 320 x 240
  • QCIF – 176 x 144

This is a good start as it reduces the amount of time it takes to send an image from the camera to the Arduino. It reduces the size of the image data array required in your Arduino sketch as well. You select the resolution by changing the value in Camera.begin. Don’t forget to change the size of your array too.

Camera.begin(QVGA, RGB565, 1)

The camera library also offers different color formats: YUV422, RGB444 and RGB565. These define how the color values are encoded and all occupy 2 bytes per pixel in our image data. We’re using the RGB565 format which has 5 bits for red, 6 bits for green, and 5 bits for blue:

Converting the 2-byte RGB565 pixel to individual red, green, and blue values in your sketch can be accomplished as follows:

    // Convert from RGB565 to 24-bit RGB

    uint16_t pixel = (high << 8) | low;

    int red   = ((pixel >> 11) & 0x1f) << 3;
    int green = ((pixel >> 5) & 0x3f) << 2;
    int blue  = ((pixel >> 0) & 0x1f) << 3;

Resizing the image on the Arduino

Once we get our image data onto the Arduino, we can then reduce the size of the image further. Just removing pixels will give us a jagged (aliased) image. To do this more smoothly, we need a downsampling algorithm that can interpolate pixel values and use them to create a smaller image.

The techniques used to resample images is an interesting topic in itself. We found the simple downsampling example from Eloquent Arduino works with fine the Arduino_OV767X camera library output (see animated GIF above).

Applications like the TensorFlow Lite Micro Person Detection example that use CNN based models on Arduino for machine vision may not need any further preprocessing of the image — other than averaging the RGB values in order to remove color for 8-bit grayscale data per pixel.

However, if you do want to perform normalization, iterating across pixels using the Arduino max and min functions is a convenient way to obtain the upper and lower bounds of input pixel values. You can then use map to scale the output pixel values to a 0-255 range.

byte pixelOut = map(input[y][x][c], lower, upper, 0, 255); 

Conclusion

This was an introduction to how to connect an OV7670 camera module to the Arduino Nano 33 BLE Sense and some considerations for obtaining data from the camera for TinyML applications. There’s a lot more to explore on the topic of machine vision on Arduino — this is just a start!

Cycling can be fun, not to mention great exercise, but is also dangerous at times. In order to facilitate safety and harmony between road users on his hour-plus bike commute in Marseille, France, Maltek created his own LED backpack signaling setup.

The device uses a hand mounted Arduino Nano 33 BLE Sense to record movement via its onboard IMU and runs a TinyML gesture recognition model to translate this into actual road signals. Left and right rotations of the wrist are passed along to the backpack unit over BLE, which shows the corresponding turn signal on its LED panel.

Other gestures include a back twist for stop, forward twist to say “merci,” and it displays a default green forward scrolling arrow as the default state.

More details on the project can be found in Maltek’s write-up here.

Machine learning (ML) algorithms come in all shapes and sizes, each with their own trade-offs. We continue our exploration of TinyML on Arduino with a look at the Arduino KNN library.

In addition to powerful deep learning frameworks like TensorFlow for Arduino, there are also classical ML approaches suitable for smaller data sets on embedded devices that are useful and easy to understand — one of the simplest is KNN.

One advantage of KNN is once the Arduino has some example data it is instantly ready to classify! We’ve released a new Arduino library so you can include KNN in your sketches quickly and easily, with no off-device training or additional tools required. 

In this article, we’ll take a look at KNN using the color classifier example. We’ve shown the same application with deep learning before — KNN is a faster and lighter weight approach by comparison, but won’t scale as well to larger more complex datasets. 

Color classification example sketch

In this tutorial, we’ll run through how to classify objects by color using the Arduino_KNN library on the Arduino Nano 33 BLE Sense.

To set up, you will need the following:

  • Arduino Nano 33 BLE Sense board
  • Micro USB cable
  • Open the Arduino IDE or Arduino Create
  • Install the Arduino_KNN library 
  • Select ColorClassifier from File > Examples > Arduino_KNN 
  • Compile this sketch and upload to your Arduino board

The Arduino_KNN library

The example sketch makes use of the Arduino_KNN library.  The library provides a simple interface to make use of KNN in your own sketches:

#include <Arduino_KNN.h>

// Create a new KNNClassifier
KNNClassifier myKNN(INPUTS);

In our example INPUTS=3 – for the red, green and blue values from the color sensor.

Sampling object colors

When you open the Serial Monitor you should see the following message:

Arduino KNN color classifier
Show me an example Apple

The Arduino board is ready to sample an object color. If you don’t have an Apple, Pear and Orange to hand you might want to edit the sketch to put different labels in. Keep in mind that the color sensor works best in a well lit room on matte, non-shiny objects and each class needs to have distinct colors! (The color sensor isn’t ideal to distinguish between an orange and a tangerine — but it could detect how ripe an orange is. If you want to classify objects by shape you can always use a camera.)

When you put the Arduino board close to the object it samples the color and adds it to the KNN examples along with a number labelling the class the object belongs to (i.e. numbers 0,1 or 2 representing Apple, Orange or Pear). ML techniques where you provide labelled example data are also called supervised learning.

The code in the sketch to add the example data to the KNN function is as follows:

readColor(color);

// Add example color to the KNN model
myKNN.addExample(color, currentClass);

The red, green and blue levels of the color sample are also output over serial:

The sketch takes 30 color samples for each object class. You can show it one object and it will sample the color 30 times — you don’t need 30 apples for this tutorial! (Although a broader dataset would make the model more generalized.)

Classification

With the example samples acquired the sketch will now ask to guess your object! The example reads the color sensor using the same function as it uses when it acquired training data — only this time it calls the classify function which will guess an object class when you show it a color:

 readColor(color);

 // Classify the object
 classification = myKNN.classify(color, K);

You can try showing it an object and see how it does:

Let me guess your object
0.44,0.28,0.28
You showed me an Apple

Note: It will not be 100% accurate especially if the surface of the object varies or the lighting conditions change. You can experiment with different numbers of examples, values for k and different objects and environments to see how this affects results.

How does KNN work?

Although the  Arduino_KNN library does the math for you it’s useful to understand how ML algorithms work when choosing one for your application. In a nutshell, the KNN algorithm classifies objects by comparing how close they are to previously seen examples. Here’s an example chart with average daily temperature and humidity data points. Each example is labelled with a season:

To classify a new object (the “?” on the chart) the KNN classifier looks for the most similar previous example(s) it has seen.  As there are two inputs in our example the algorithm does this by calculating the distance between the new object and each of the previous examples. You can see the closest example above is labelled “Winter”.

The k in KNN is just the number of closest examples the algorithm considers. With k=3 it counts the three closest examples. In the chart above the algorithm would give two votes for Spring and one for Winter — so the result would change to Spring. 

One disadvantage of KNN is the larger the amount of training example data there is, the longer the KNN algorithm needs to spend checking each time it classifies an object. This makes KNN less feasible for large datasets and is a major difference between KNN and a deep learning based approach. 

Classifying objects by color

In our color classifier example there are three inputs from the color sensor. The example colors from each object can be thought of as points in three dimensional space positioned on red, green and blue axes. As usual the KNN algorithm guesses objects by checking how close the inputs are to previously seen examples, but because there are three inputs this time it has to calculate the distances in three dimensional space. The more dimensions the data has the more work it is to compute the classification result.

Further thoughts

This is just a quick taste of what’s possible with KNN. You’ll find an example for board orientation in the library examples, as well as a simple example for you to build on. You can use any sensor on the BLE Sense board as an input, and even combine KNN with other ML techniques.

Of course there are other machine learning resources available for Arduino include TensorFlow Lite tutorials as well as support from professional tools such as Edge Impulse and Qeexo. We’ll be inviting more experts to explore machine learning on Arduino more in the coming weeks.

This post is written by Jan Jongboom and Dominic Pajak.

Running machine learning (ML) on microcontrollers is one of the most exciting developments of the past years, allowing small battery-powered devices to detect complex motions, recognize sounds, or find anomalies in sensor data. To make building and deploying these models accessible to every embedded developer we’re launching first-class support for the Arduino Nano 33 BLE Sense and other 32-bit Arduino boards in Edge Impulse.

The trend to run ML on microcontrollers is called Embedded ML or Tiny ML. It means devices can make smart decisions without needing to send data to the cloud – great from an efficiency and privacy perspective. Even powerful deep learning models (based on artificial neural networks) are now reaching microcontrollers. This past year great strides were made in making deep learning models smaller, faster and runnable on embedded hardware through projects like TensorFlow Lite Micro, uTensor and Arm’s CMSIS-NN; but building a quality dataset, extracting the right features, training and deploying these models is still complicated.

Using Edge Impulse you can now quickly collect real-world sensor data, train ML models on this data in the cloud, and then deploy the model back to your Arduino device. From there you can integrate the model into your Arduino sketches with a single function call. Your sensors are then a whole lot smarter, being able to make sense of complex events in the real world. The built-in examples allow you to collect data from the accelerometer and the microphone, but it’s easy to integrate other sensors with a few lines of code. 

Excited? This is how you build your first deep learning model with the Arduino Nano 33 BLE Sense (there’s also a video tutorial here: setting up the Arduino Nano 33 BLE Sense with Edge Impulse):

  • Download the Arduino Nano 33 BLE Sense firmware — this is a special firmware package (source code) that contains all code to quickly gather data from its sensors. Launch the flash script for your platform to flash the firmware.
  • Launch the Edge Impulse daemon to connect your board to Edge Impulse. Open a terminal or command prompt and run:
$ npm install edge-impulse-cli -g
$ edge-impulse-daemon
  • Your device now shows in the Edge Impulse studio on the Devices tab, ready for you to collect some data and build a model.
  • Once you’re done you can deploy your model back to the Arduino Nano 33 BLE Sense. Either as a binary which includes your full ML model, or as an Arduino library which you can integrate in any sketch.
Deploy to Arduino from Edge Impulse
Deploying to Arduino from Edge Impulse
  • Your machine learning model is now running on the Arduino board. Open the serial monitor and run `AT+RUNIMPULSE` to start classifying real world data!
Keyword spotting on the Arduino Nano 33 BLE Sense
Keyword spotting on the Arduino Nano 33 BLE Sense

Integrates with your favorite Arduino platform

We’ve launched with the Arduino Nano 33 BLE Sense, but you can also integrate Edge Impulse with your favourite Arduino platform. You can easily collect data from any sensor and development board using the Data forwarder. This is a small application that reads data over serial and sends it to Edge Impulse. All you need is a few lines of code in your sketch (here’s an example).

After you’ve built a model you can easily export your model as an Arduino library. This library will run on any Arm-based Arduino platform including the Arduino MKR family or Arduino Nano 33 IoT, providing it has enough RAM to run your model. You can now include your ML model in any Arduino sketch with just a few lines of code. After you’ve added the library to the Arduino IDE you can find an example on integrating the model under Files > Examples > Your project – Edge Impulse > static_buffer.

To run your models as fast and energy-efficiently as possible we automatically leverage the hardware capabilities of your Arduino board – for example the signal processing extensions available on the Arm Cortex-M4 based Arduino Nano BLE Sense or more powerful Arm Cortex-M7 based Arduino Portenta H7. We also leverage the optimized neural network kernels that Arm provides in CMSIS-NN.

A path to production

This release is the first step in a really exciting collaboration. We believe that many embedded applications can benefit from ML today, whether it’s for predictive maintenance (‘this machine is starting to behave abnormally’), to help with worker safety (‘fall detected’), or in health care (‘detected early signs of a potential infection’). Using Edge Impulse with the Arduino MKR family you can already quickly deploy simple ML based applications combined with LoRa, NB-IoT cellular, or WiFi connectivity. Over the next months we’ll also add integrations for the Arduino Portenta H7 on Edge Impulse, making higher performance industrial applications possible.

On a related note: if you have ideas on how TinyML can help to slow down or detect the COVID-19 virus, then join the UNDP COVID-19 Detect and Protect Challenge. For inspiration, see Kartik Thakore’s blog post on cough detection with the Arduino Nano 33 BLE Sense and Edge Impulse.

We can’t wait to see what you’ll build!

Jan Jongboom is the CTO and co-founder of Edge Impulse. He built his first IoT projects using the Arduino Starter Kit.

Dominic Pajak is VP Business Development at Arduino.

First the robots took our jobs, then they came for our video games. This dystopian future is brought to you by [Little French Kev] who designed this adorable 3D-printed robot arm to interface with an Xbox One controller joystick. He shows it off in the video after the break, controlling a ball-balancing physics demonstration written in Unity.

Hats off to him on the quality of the design. There are two parts that nestle the knob of the thumbstick from either side. He mates those pieces with each other using screws, firmly hugging the stick. Bearings are used at the joints for smooth action of the two servo motors that control the arm. The base of the robotic appendage is zip-tied to the controller itself.

The build targets experimentation with machine learning. Since the computer can control the arm via an Arduino, and the computer has access to metrics of what’s happening in the virtual environment, it’s a perfect for training a neural network. Are you thinking what we’re thinking? This is the beginning of hardware speed-running your favorite video games like [SethBling] did for Super Mario World half a decade ago. It will be more impressive since this would be done by automating the mechanical bit of the controller rather than operating purely in the software realm. You’ll just need to do your own hack to implement button control.

By Dominic Pajak and Sandeep Mistry

Arduino is on a mission to make machine learning easy enough for anyone to use. The other week we announced the availability of TensorFlow Lite Micro in the Arduino Library Manager. With this, some cool ready-made ML examples such as speech recognition, simple machine vision and even an end-to-end gesture recognition training tutorial. For a comprehensive background we recommend you take a look at that article

In this article we are going to walk through an even simpler end-to-end tutorial using the TensorFlow Lite Micro library and the Arduino Nano 33 BLE 33 Sense’s colorimeter and proximity sensor to classify objects. To do this, we will be running a small neural network on the board itself. 

Arduino BLE 33 Nano Sense running TensorFlow Lite Micro

The philosophy of TinyML is doing more on the device with less resources – in smaller form-factors, less energy and lower cost silicon. Running inferencing on the same board as the sensors has benefits in terms of privacy and battery life and means its can be done independent of a network connection. 

The fact that we have the proximity sensor on the board means we get an instant depth reading of an object in front of the board – instead of using a camera and having to determine if an object is of interest through machine vision. 

In this tutorial when the object is close enough we sample the color – the onboard RGB sensor can be viewed as a 1 pixel color camera. While this method has limitations it provides us a quick way of classifying objects only using a small amount of resources. Note that you could indeed run a complete CNN-based vision model on-device. As this particular Arduino board includes an onboard colorimeter, we thought it’d be fun and instructive to demonstrate in this way to start with.

We’ll show a simple but complete end-to-end TinyML application can be achieved quickly and without a deep background in ML or embedded. What we cover here is data capture, training, and classifier deployment. This is intended to be a demo, but there is scope to improve and build on this should you decide to connect an external camera down the road. We want you to get an idea of what is possible and a starting point with tools available.

What you’ll need

About the Arduino board

The Arduino Nano 33 BLE Sense board we’re using here has an Arm Cortex-M4 microcontroller running mbedOS and a ton of onboard sensors – digital microphone, accelerometer, gyroscope, temperature, humidity, pressure, light, color and proximity. 

While tiny by cloud or mobile standards the microcontroller is powerful enough to run TensorFlow Lite Micro models and classify sensor data from the onboard sensors.

Setting up the Arduino Create Web Editor

In this tutorial we’ll be using the Arduino Create Web Editor – a cloud-based tool for programming Arduino boards. To use it you have to sign up for a free account, and install a plugin to allow the browser to communicate with your Arduino board over USB cable.

You can get set up quickly by following the getting started instructions which will guide you through the following:

  • Download and install the plugin
  • Sign in or sign up for a free account

(NOTE: If you prefer, you can also use the Arduino IDE desktop application. The setup for which is described in the previous tutorial.)

Capturing training data

We now we will capture data to use to train our model in TensorFlow. First, choose a few different colored objects. We’ll use fruit, but you can use whatever you prefer. 

Setting up the Arduino for data capture

Next we’ll use Arduino Create to program the Arduino board with an application object_color_capture.ino that samples color data from objects you place near it. The board sends the color data as a CSV log to your desktop machine over the USB cable.

To load the object_color_capture.ino application onto your Arduino board:

  • Connect your board to your laptop or PC with a USB cable
    • The Arduino board takes a male micro USB
  • Open object_color_capture.ino in Arduino Create by clicking this link

Your browser will open the Arduino Create web application (see GIF above).

  • Press OPEN IN WEB EDITOR
    • For existing users this button will be labeled ADD TO MY SKETCHBOOK
  • Press Upload & Save
    • This will take a minute
    • You will see the yellow light on the board flash as it is programmed
  • Open the serial Monitor
    • This opens the Monitor panel on the left-hand side of the web application
    • You will now see color data in CSV format here when objects are near the top of the board

Capturing data in CSV files for each object

For each object we want to classify we will capture some color data. By doing a quick capture with only one example per class we will not train a generalized model, but we can still get a quick proof of concept working with the objects you have to hand! 

Say, for example, we are sampling an apple:

  • Reset the board using the small white button on top.
    • Keep your finger away from the sensor, unless you want to sample it!
    • The Monitor in Arduino Create will say ‘Serial Port Unavailable’ for a minute
  • You should then see Red,Green,Blue appear at the top of the serial monitor
  • Put the front of the board to the apple. 
    • The board will only sample when it detects an object is close to the sensor and is sufficiently illuminated (turn the lights on or be near a window)
  • Move the board around the surface of the object to capture color variations
  • You will see the RGB color values appear in the serial monitor as comma separated data. 
  • Capture at a few seconds of samples from the object
  • Copy and paste this log data from the Monitor to a text editor
    • Tip: untick AUTOSCROLL check box at the bottom to stop the text moving
  • Save your file as apple.csv
  • Reset the board using the small white button on top.

Do this a few more times, capturing other objects (e.g. banana.csv, orange.csv). 

NOTE: The first line of each of the .csv files should read:

Red,Green,Blue

If you don’t see it at the top, you can just copy and paste in the line above. 

Training the model

We will now use colab to train an ML model using the data you just captured in the previous section.

  • First open the FruitToEmoji Jupyter Notebook in colab
  • Follow the instructions in the colab
    • You will be uploading your *.csv files 
    • Parsing and preparing the data
    • Training a model using Keras
    • Outputting TensorFlowLite Micro model
    • Downloading this to run the classifier on the Arduino 

With that done you will have downloaded model.h to run on your Arduino board to classify objects!

The colab will guide you to drop your .csv files into the file window, the result shown above
Normalized color samples captured by the Arduino board are graphed in colab

Program TensorFlow Lite Micro model to the Arduino board

Finally, we will take the model we trained in the previous stage and compile and upload to our Arduino board using Arduino Create. 

Your browser will open the Arduino Create web application:

  • Press the OPEN IN WEB EDITOR button
  • Import the  model.h you downloaded from colab using Import File to Sketch: 
Import the model.h you downloaded from colab
The model.h tab should now look like this
  • Compile and upload the application to your Arduino board 
    • This will take a minute
    • When it’s done you’ll see this message in the Monitor:
  • Put your Arduino’s RGB sensor near the objects you trained it with
  • You will see the classification output in the Monitor:
Classifier output in the Arduino Create Monitor

You can also edit the object_color_classifier.ino sketch to output emojis instead (we’ve left the unicode in the comments in code!), which you will be able to view in Mac OS X or Linux terminal by closing the web browser tab with Arduino Create in, resetting your board, and typing cat /cu/usb.modem[n]. 

Output from Arduino serial to Linux terminal using ANSI highlighting and unicode emojis

Learning more

The resources around TinyML are still emerging but there’s a great opportunity to get a head start and meet experts coming up 2-3 December 2019 in Mountain View, California at the Arm IoT Dev Summit. This includes workshops from Sandeep Mistry, Arduino technical lead for on-device ML and from Google’s Pete Warden and Daniel Situnayake who literally wrote the book on TinyML. You’ll be able to hang out with these experts and more at the TinyML community sessions there too. We hope to see you there!

Conclusion

We’ve seen a quick end-to-end demo of machine learning running on Arduino. The same framework can be used to sample different sensors and train more complex models. For our object by color classification we could do more, by sampling more examples in more conditions to help the model generalize. In future work, we may also explore how to run an on-device CNN. In the meantime, we hope this will be a fun and exciting project for you. Have fun!

This post was originally published by Sandeep Mistry and Dominic Pajak on the TensorFlow blog.

Arduino is on a mission to make machine learning simple enough for anyone to use. We’ve been working with the TensorFlow Lite team over the past few months and are excited to show you what we’ve been up to together: bringing TensorFlow Lite Micro to the Arduino Nano 33 BLE Sense. In this article, we’ll show you how to install and run several new TensorFlow Lite Micro examples that are now available in the Arduino Library Manager.

The first tutorial below shows you how to install a neural network on your Arduino board to recognize simple voice commands.

Example 1: Running the pre-trained micro_speech inference example.

Next, we’ll introduce a more in-depth tutorial you can use to train your own custom gesture recognition model for Arduino using TensorFlow in Colab. This material is based on a practical workshop held by Sandeep Mistry and Dan Coleman, an updated version of which is now online

If you have previous experience with Arduino, you may be able to get these tutorials working within a couple of hours. If you’re entirely new to microcontrollers, it may take a bit longer. 

Example 2: Training your own gesture classification model.

We’re excited to share some of the first examples and tutorials, and to see what you will build from here. Let’s get started!

Note: The following projects are based on TensorFlow Lite for Microcontrollers which is currently experimental within the TensorFlow repo. This is still a new and emerging field!

Microcontrollers and TinyML

Microcontrollers, such as those used on Arduino boards, are low-cost, single chip, self-contained computer systems. They’re the invisible computers embedded inside billions of everyday gadgets like wearables, drones, 3D printers, toys, rice cookers, smart plugs, e-scooters, washing machines. The trend to connect these devices is part of what is referred to as the Internet of Things.

Arduino is an open-source platform and community focused on making microcontroller application development accessible to everyone. The board we’re using here has an Arm Cortex-M4 microcontroller running at 64 MHz with 1MB Flash memory and 256 KB of RAM. This is tiny in comparison to Cloud, PC, or mobile but reasonable by microcontroller standards.

Arduino Nano 33 BLE Sense board is smaller than a stick of gum.

There are practical reasons you might want to squeeze ML on microcontrollers, including: 

  • Function – wanting a smart device to act quickly and locally (independent of the Internet).
  • Cost – accomplishing this with simple, lower cost hardware.
  • Privacy – not wanting to share all sensor data externally.
  • Efficiency – smaller device form-factor, energy-harvesting or longer battery life.

There’s a final goal which we’re building towards that is very important:

  • Machine learning can make microcontrollers accessible to developers who don’t have a background in embedded development 

On the machine learning side, there are techniques you can use to fit neural network models into memory constrained devices like microcontrollers. One of the key steps is the quantization of the weights from floating point to 8-bit integers. This also has the effect of making inference quicker to calculate and more applicable to lower clock-rate devices. 

TinyML is an emerging field and there is still work to do – but what’s exciting is there’s a vast unexplored application space out there. Billions of microcontrollers combined with all sorts of sensors in all sorts of places which can lead to some seriously creative and valuable TinyML applications in the future.

What you need to get started

The Arduino Nano 33 BLE Sense has a variety of onboard sensors meaning potential for some cool TinyML applications:

  • Voice – digital microphone
  • Motion – 9-axis IMU (accelerometer, gyroscope, magnetometer)
  • Environmental – temperature, humidity and pressure
  • Light – brightness, color and object proximity

Unlike classic Arduino Uno, the board combines a microcontroller with onboard sensors which means you can address many use cases without additional hardware or wiring. The board is also small enough to be used in end applications like wearables. As the name suggests it has Bluetooth LE connectivity so you can send data (or inference results) to a laptop, mobile app or other BLE boards and peripherals.

Tip: Sensors on a USB stick – Connecting the BLE Sense board over USB is an easy way to capture data and add multiple sensors to single board computers without the need for additional wiring or hardware – a nice addition to a Raspberry Pi, for example.

TensorFlow Lite for Microcontrollers examples

The inference examples for TensorFlow Lite for Microcontrollers are now packaged and available through the Arduino Library manager making it possible to include and run them on Arduino in a few clicks. In this section we’ll show you how to run them. The examples are:

  • micro_speech – speech recognition using the onboard microphone
  • magic_wand – gesture recognition using the onboard IMU
  • person_detection – person detection using an external ArduCam camera

For more background on the examples you can take a look at the source in the TensorFlow repository. The models in these examples were previously trained. The tutorials below show you how to deploy and run them on an Arduino. In the next section, we’ll discuss training.

How to run the examples using Arduino Create web editor

Once you connect your Arduino Nano 33 BLE Sense to your desktop machine with a USB cable you will be able to compile and run the following TensorFlow examples on the board by using the Arduino Create web editor:

Compiling an example from the Arduino_TensorFlowLite library.

Focus on the speech recognition example: micro_speech

One of the first steps with an Arduino board is getting the LED to flash. Here, we’ll do it with a twist by using TensorFlow Lite Micro to recognise voice keywords. It has a simple vocabulary of “yes” and “no”. Remember this model is running locally on a microcontroller with only 256KB of RAM, so don’t expect commercial ‘voice assistant’ level accuracy – it has no Internet connection and on the order of 2000x less local RAM available.

Note the board can be battery powered as well. As the Arduino can be connected to motors, actuators and more this offers the potential for voice-controlled projects.

Running the micro_speech example.

How to run the examples using the Arduino IDE

Alternatively you can use try the same inference examples using Arduino IDE application.

First, follow the instructions in the next section Setting up the Arduino IDE.

In the Arduino IDE, you will see the examples available via the File > Examples > Arduino_TensorFlowLite menu in the ArduinoIDE.

Select an example and the sketch will open. To compile, upload and run the examples on the board, and click the arrow icon:

For advanced users who prefer a command line, there is also the arduino-cli.

Training a TensorFlow Lite Micro model for Arduino

[optimize output image]
Gesture classification on Arduino BLE 33 Nano Sense, output as emojis.

Next we will use ML to enable the Arduino board to recognise gestures. We’ll capture motion data from the Arduino Nano 33 BLE Sense board, import it into TensorFlow to train a model, and deploy the resulting classifier onto the board.

The idea for this tutorial was based on Charlie Gerard’s awesome Play Street Fighter with body movements using Arduino and Tensorflow.js. In Charlie’s example, the board is streaming all sensor data from the Arduino to another machine which performs the gesture classification in Tensorflow.js. We take this further and “TinyML-ifiy” it by performing gesture classification on the Arduino board itself. This is made easier in our case as the Arduino Nano 33 BLE Sense board we’re using has a more powerful Arm Cortex-M4 processor, and an on-board IMU.

We’ve adapted the tutorial below, so no additional hardware is needed – the sampling starts on detecting movement of the board. The original version of the tutorial adds a breadboard and a hardware button to press to trigger sampling. If you want to get into a little hardware, you can follow that version instead.

Setting up the Arduino IDE

Following the steps below sets up the Arduino IDE application used to both upload inference models to your board and download training data from it in the next section. There are a few more steps involved than using Arduino Create web editor because we will need to download and install the specific board and libraries in the Arduino IDE.

  • In the Arduino IDE menu select Tools > Board > Boards Manager…
    • Search for “Nano BLE” and press install on the board 
    • It will take several minutes to install
    • When it’s done close the Boards Manager window
This image has an empty alt attribute; its file name is k88wXiRDpbadmTW1EreSetBJwHgMN3IP4skuTRywedIgp2aAWvzg3mqyDPZ2_fafH7tFXK-GtFwPEcnMAM0fqfa8XeYCc7orh6LXg4pD2_fKu1JQqw8LALMHfv6lFIBA3a_9pYeg
  • Now go to the Library Manager Tools > Manage Libraries…
    • Search for and install the Arduino_TensorFlowLite library

Next search for and install the Arduino_LSM9DS1 library:

  • Finally, plug the micro USB cable into the board and your computer
  • Choose the board Tools > Board > Arduino Nano 33 BLE
  • Choose the port Tools > Port > COM5 (Arduino Nano 33 BLE) 
    • Note that the actual port name may be different on your computer

There are more detailed Getting Started and Troubleshooting guides on the Arduino site if you need help.

Streaming sensor data from the Arduino board

First, we need to capture some training data. You can capture sensor data logs from the Arduino board over the same USB cable you use to program the board with your laptop or PC.

Arduino boards run small applications (also called sketches) which are compiled from .ino format Arduino source code, and programmed onto the board using the Arduino IDE or Arduino Create. 

We’ll be using a pre-made sketch IMU_Capture.ino which does the following:

  • Monitor the board’s accelerometer and gyroscope 
  • Trigger a sample window on detecting significant linear acceleration of the board 
  • Sample for one second at 119Hz, outputting CSV format data over USB 
  • Loop back and monitor for the next gesture

The sensors we choose to read from the board, the sample rate, the trigger threshold, and whether we stream data output as CSV, JSON, binary or some other format are all customizable in the sketch running on the Arduino. There is also scope to perform signal preprocessing and filtering on the device before the data is output to the log – this we can cover in another blog. For now, you can just upload the sketch and get sampling.

To program the board with this sketch in the Arduino IDE:

  • Download IMU_Capture.ino and open it in the Arduino IDE
  • Compile and upload it to the board with Sketch > Upload

Visualizing live sensor data log from the Arduino board

With that done we can now visualize the data coming off the board. We’re not capturing data yet this is just to give you a feel for how the sensor data capture is triggered and how long a sample window is. This will help when it comes to collecting training samples.

  • In the Arduino IDE, open the Serial Plotter Tools > Serial Plotter
    • If you get an error that the board is not available, reselect the port:
    • Tools > Port > portname (Arduino Nano 33 BLE) 
  • Pick up the board and practice your punch and flex gestures
    • You’ll see it only sample for a one second window, then wait for the next gesture
  • You should see a live graph of the sensor data capture (see GIF below)
Arduino IDE Serial Plotter will show a live graph of CSV data output from your board.

When you’re done be sure to close the Serial Plotter window – this is important as the next step won’t work otherwise.

Capturing gesture training data 

To capture data as a CSV log to upload to TensorFlow, you can use Arduino IDE > Tools > Serial Monitor to view the data and export it to your desktop machine:

  • Reset the board by pressing the small white button on the top
  • Pick up the board in one hand (picking it up later will trigger sampling)
  • In the Arduino IDE, open the Serial Monitor Tools > Serial Monitor
    • If you get an error that the board is not available, reselect the port:
    • Tools > Port > portname (Arduino Nano 33 BLE) 
  • Make a punch gesture with the board in your hand (Be careful whilst doing this!)
    • Make the outward punch quickly enough to trigger the capture
    • Return to a neutral position slowly so as not to trigger the capture again 
  • Repeat the gesture capture step 10 or more times to gather more data
  • Copy and paste the data from the Serial Console to new text file called punch.csv 
  • Clear the console window output and repeat all the steps above, this time with a flex gesture in a file called flex.csv 
    • Make the inward flex fast enough to trigger capture returning slowly each time

Note the first line of your two csv files should contain the fields aX,aY,aZ,gX,gY,gZ.

Linux tip: If you prefer you can redirect the sensor log output from the Arduino straight to a .csv file on the command line. With the Serial Plotter / Serial Monitor windows closed use:

 $ cat /dev/cu.usbmodem[nnnnn] > sensorlog.csv

Training in TensorFlow

We’re going to use Google Colab to train our machine learning model using the data we collected from the Arduino board in the previous section. Colab provides a Jupyter notebook that allows us to run our TensorFlow training in a web browser.

Arduino gesture recognition training colab.

The colab will step you through the following:

  • Set up Python environment
  • Upload the punch.csv and flex.csv data 
  • Parse and prepare the data
  • Build and train the model
  • Convert the trained model to TensorFlow Lite
  • Encode the model in an Arduino header file

The final step of the colab is generates the model.h file to download and include in our Arduino IDE gesture classifier project in the next section:

Let’s open the notebook in Colab and run through the steps in the cells – arduino_tinyml_workshop.ipynb

Classifying IMU Data

Next we will use model.h file we just trained and downloaded from Colab in the previous section in our Arduino IDE project:

  • Open IMU_Classifier.ino in the Arduino IDE.
  • Create a new tab in the IDE. When asked name it model.h
  • Open the model.h tab and paste in the version you downloaded from Colab
  • Upload the sketch: Sketch > Upload
  • Open the Serial Monitor: Tools > Serial Monitor
  • Perform some gestures
  • The confidence of each gesture will be printed to the Serial Monitor (0 = low confidence, 1 =  high confidence)

Congratulations you’ve just trained your first ML application for Arduino!

For added fun the Emoji_Button.ino example shows how to create a USB keyboard that prints an emoji character in Linux and macOS. Try combining the Emoji_Button.ino example with the IMU_Classifier.ino sketch to create a gesture controlled emoji keyboard ?.

Conclusion

It’s an exciting time with a lot to learn and explore in TinyML. We hope this blog has given you some idea of the potential and a starting point to start applying it in your own projects. Be sure to let us know what you build and share it with the Arduino community.

For a comprehensive background on TinyML and the example applications in this article, we recommend Pete Warden and Daniel Situnayake’s new O’Reilly book “TinyML: Machine Learning with TensorFlow on Arduino and Ultra-Low Power Microcontrollers.”

Even though machine learning AKA ‘deep learning’ / ‘artificial intelligence’ has been around for several decades now, it’s only recently that computing power has become fast enough to do anything useful with the science.

However, to fully understand how a neural network (NN) works, [Dimitris Tassopoulos] has stripped the concept down to pretty much the simplest example possible – a 3 input, 1 output network – and run inference on a number of MCUs, including the humble Arduino Uno. Miraculously, the Uno processed the network in an impressively fast prediction time of 114.4 μsec!

Whilst we did not test the code on an MCU, we just happened to have Jupyter Notebook installed so ran the same code on a Raspberry Pi directly from [Dimitris’s] bitbucket repo.

He explains in the project pages that now that the hype about AI has died down a bit that it’s the right time for engineers to get into the nitty-gritty of the theory and start using some of the ‘tools’ such as Keras, which have now matured into something fairly useful.

In part 2 of the project, we get to see the guts of a more complicated NN with 3-inputs, a hidden layer with 32 nodes and 1-output, which runs on an Uno at a much slower speed of 5600 μsec.

This exploration of ML in the embedded world is NOT ‘high level’ research stuff that tends to be inaccessible and hard to understand. We have covered Machine Learning On Tiny Platforms Like Raspberry Pi And Arduino before, but not with such an easy and thoroughly practical example.

Machine learning is starting to come online in all kinds of arenas lately, and the trend is likely to continue for the forseeable future. What was once only available for operators of supercomputers has found use among anyone with a reasonably powerful desktop computer. The downsizing isn’t stopping there, though, as Microsoft is pushing development of machine learning for embedded systems now.

The Embedded Learning Library (ELL) is a set of tools for allowing Arduinos, Raspberry Pis, and the like to take advantage of machine learning algorithms despite their small size and reduced capability. Microsoft intended this library to be useful for anyone, and has examples available for things like computer vision, audio keyword recognition, and a small handful of other implementations. The library should be expandable to any application where machine learning would be beneficial for a small embedded system, though, so it’s not limited to these example applications.

There is one small speed bump to running a machine learning algorithm on your Raspberry Pi, though. The high processor load tends to cause small SoCs to overheat. But adding a heatsink and fan is something we’ve certainly seen before. Don’t let your lack of a supercomputer keep you from exploring machine learning if you see a benefit to it, and if you need more power than just one Raspberry Pi you can always build a cluster to get your task done just a little bit faster, too.

Thanks to [Baldpower] for the tip!

When was the last time you poured water onto your radio to turn it on?

Designed collaboratively by [Tore Knudsen], [Simone Okholm Hansen] and [Victor Permild], Pour Reception seeks to challenge what constitutes an interface, and how elements of play can create a new experience for a relatively everyday object.

Lacking buttons or knobs of any kind, Pour Reception appears an inert acrylic box with two glasses resting on top. A detachable instruction card cues the need for water, and pouring some into the glasses wakes the radio.

Inside, two aluminium plates —  acting as capacitive touch sensors — are connected to an Arduino using the Tact library from NANDSudio. Wekinator — a machine learning tool — enabled [Knudsen] to program various actions to control the radio. Pouring water between the glasses changes stations, rotating and tweaking the glass’ positions adjusts audio quality, and placing a finger in the glass mutes it temporarily.

It’s a great concept for a more engaging piece of tech, if perhaps a little unnerving to be pouring water around household electronics. Best take preventative measures before applying this idea elsewhere.



  • Newsletter

    Sign up for the PlanetArduino Newsletter, which delivers the most popular articles via e-mail to your inbox every week. Just fill in the information below and submit.

  • Like Us on Facebook