Re:StreetLearn: Learning to navigate in cities without a map
by cs702 on Thursday June 28, 2018 @08:29AM
(#17416293)
The agent learns to navigate entire cities by exploring them on the ground (it sees only Google Street View photos), without any map or location data.
The human analogy would be to ask you to learn to navigate a new city (whose language you don't understand) without ever using a map or location data, simply by driving around and looking out of the car. You will drive around and, as you see different street scenes, you will gradually build a "mental model of the city" that allows you to navigate it.
That's essentially what the agent does.
Once trained, when the agent is asked to go to a particular location, it knows how to get there, despite never having seen a map of the city.
The human analogy would be to ask you to learn to navigate a new city (whose language you don't understand) without ever using a map or location data, simply by driving around and looking out of the car. You will drive around and, as you see different street scenes, you will gradually build a "mental model of the city" that allows you to navigate it.
That's essentially what the agent does.
Once trained, when the agent is asked to go to a particular location, it knows how to get there, despite never having seen a map of the city.
Impressive.