It's implied, and I'm hoping it's true, that this is a map-less navigation. Which is impressive. This kind of task is much easier if you have a pre-captured map of the environment, but if they are doing this without a map it's great. Historically you were always faced with "The Kidnapped Robot" problem where robots that didn't know where they were couldn't navigate even a little bit. Here the robot appears to be able to follow directions as long as they are interpretable from its current vision (or via dead reckoning).
Wouldn't modern SLAM or VSLAM address that problem?
I am working in Mistral robotics team. I confirm this is map-less. The only inputs are the text prompt and the front camera rgb image.