AI FutuRace

We arranged the first AI vs AI car race in Finland on June 2019. The Finnish TV show Teknavi got interested on our event and we got covered in their season premiere. We even got Mr Maximum Attack himself, Markku Alén, as a special guest! Checkout the material below. Includes English subtitles. »

Author image Futurice Tammerforce

It's also about the track

TL;DR: Building a good track might be harder than it looks. You can get your own track printed at your local vendor using our CC licenced designs that can be found from Github. While my colleague Mikko has been writing about the marvels of Donkeycar and fancy machine learning thingies, we should pay some respect also to all the different tracks we’ve built during our journey. Can you really train a car to drive if there’s no track? »

Author image Lauri Anttila

Training a Donkeycar on AWS GPU instance

Training a neural network is quite an intensive task for a computer. Modern deep learning platforms, like Tensorflow, can utilize specialized hardware for speeding up things. On a basic consumer computer, it means for example NVIDIA GPU card usually used for gaming. If there is no such hardware available and one has the option to use a money cannon, it’s possible to use a cloud-based service. There are more sophisticated options also available, but in this post I will tell you how to setup a raw Linux instance in Amazon cloud. »

Author image Mikko Pohja

Realsense T265 tracking camera

One of the key points in our project so far has been to keep it simple. At the same time we have experimented with some custom hardware, like Inertial Measurement Unit (IMU), rotary encoders and sonars. IMU is used to measure rotation and acceleration, rotary encoder to measure speed and sonar to detect obstacles in front of the car. All these are pretty old and battle-proven technologies, but still quite low level. »

Author image Mikko Pohja

Short Introduction to Data Augmentation

In a previous post about Supervised racing there was a short mention about data augmentation. That has been one of the most requested topics for us to blog about, so let’s open it up a bit more. Data augmentation is basically just a method to grow your dataset using your existing data. This can be done simply by modifying the existing dataset and including the modified data as part of training data on top of the original data. »

Author image Osmo Kajasto