logoalt Hacker News

iandanforthtoday at 3:36 PM2 repliesview on HN

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).


Replies

duchennetoday at 4:24 PM

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.

show 4 replies
ainchtoday at 4:21 PM

Wouldn't modern SLAM or VSLAM address that problem?