Planet Arduino

Based on the Renesas RA4M1 microcontroller, the new Arduino UNO R4 boasts 16x the RAM, 8x the flash, and a much faster CPU compared to the previous UNO R3. This means that unlike its predecessor, the R4 is capable of running machine learning at the edge to perform inferencing of incoming data. With this fact in mind, Roni Bandini wanted to leverage his UNO R4 Minima by training a model to predict the likelihood of a FIFA team winning their match.

Bandini began his project by first downloading a dataset containing historical FIFA matches, including the country, team, opposing team, ranking, and neutral location. Next, the data was added to Edge impulse as a time-series dataset which feeds into a Keras classifier ML block and produces “win” and “lose/draw” values. Once trained, the model achieved an accuracy of 69% with a loss value of 0.58.

Inputting the desired country and rank to make a prediction is done by making selections on a DFRobot LCD shield, and these values are then used to populate the input tensor for the model before it gets invoked and returns its classification results. Bandini’s device demonstrates how much more powerful the Arduino UNO R4 is over the R3, and additional information on the project can be found here in his post.

The post Predicting soccer matches with ML on the UNO R4 Minima appeared first on Arduino Blog.

If you are an American, you’d probably think of [Silas Hansen’s] project as “air soccer” but most people will prefer air football. Either way, it is like air hockey but more of a football field feel. The project looks great — if you saw this on the shelves of the local toy store, you wouldn’t think anything of it. You can see a video of the game in action, below.

Unsurprisingly, the brains of the game are an Arduino. The case looks good thanks to laser cutting and 3D printing. A Roland printer produced the stickers that really dress the case up, but you could find another artistic way to do the decoration.

You could probably pull this off without all the fancy fabrication gear, but hand drilling all those air holes would be a pain. The air is from a 3,000 RPM brushless fan and a pair of line trackers are repurposed to sense when the puck — er, ball — reach the goals. A touch display handles the scorekeeping.

Overall, a great-looking project and one of those things that doesn’t use anything too high-tech, but still looks great and seems to work well.

We’ve seen hockey tables before, of course. If you are too antisocial to have an opponent, you can always build one.

It’s FIFA World Cup time and we have a project for makers who prefer to be active instead of only watching the others play. The exciting penalty shoot-out we’ve always enjoyed in video games was implemented by Germán Carrillo as an electro-mechanical game where you save goals using a control device and kick the ball with your fingers:

It is an interactive game situated between electronics and the real world making you part of the game. The more players the better (we have played 8 people!). The video below shows the construction phase of the project and several sample penalty kicks. The project involves a variety of electronic components such as the Arduino Uno, servos, LEDs, push buttons, a potentiometer, a switch, a piezo buzzer, a gearmotor, and the ATtiny85, among others (great for a first Arduino project, isn’t it?).