The Tensorflow blog posts a demo built for (and had planned to be shown at) Google I/O this year with TensorFlow Lite.

Pixelopolis is an interactive installation that showcases self-driving miniature cars powered by TensorFlow Lite. Each car is outfitted with its own Pixel phone, which used its camera to detect and understand signals from the world around it. In order to sense lanes, avoid collisions and read traffic signs, the phone uses machine learning running on the Pixel Neural Core, which contains a version of an Edge TPU.

An edge computing implementation is a good option to make projects like this possible. Processing video and detecting objects are much more difficult using Cloud-based methods – due to latency. If you can, doing it on-device is much faster.

Users can interact with Pixelopolis via a “station” (an app running on a phone), where they can select the destination the car will drive to. The car will navigate to the destination, and during the journey, the app shows real-time streaming video from the Car — this allows the user to see what the car sees and detects. As you may notice from the gifs below, Pixelopolis has multilingual support built-in as well.

See the Tensorflow blog post for additional details.