According to Facebook, the downside to using maps is that it can become outdated. For example, shifting furniture around would essentially result in the older map being obsolete. However, according to Facebook, they have created a new distributed reinforcement learning (RL) algorithm called DD-PPO, which they believe solves that problem.
Facebook believes that with this new algorithm, it will be capable of creating robots that can navigate an area without the need for maps, where it is also said to be capable of reaching its destination 99.9% of the time and with only a 3% deviation from the ideal path. This means that in theory, you could place a robot in a room or an area without a map and it should be able to find its way to its destination.
However, as Facebook notes, there is still a lot of work left to be done. “We look forward to exploring new solutions to RGB-only point-goal navigation, which is important because compass and GPS data can be noisy or simply unavailable in indoor spaces. We will also apply DD-PPO-trained models to different tasks.”