Not sure why "photorealistic" is such a big selling point here. If we can make robots navigate in DOOM they will probably be able to navigate in Habitat and vice versa.
Low on technical detail. What can this do that Gazebo cannot?
More confusion. Looking closer at the actual code, there are <20k lines of C++ code. For comparison, the Bullet physics engine clocks in at over 700k lines. What does Habitat actually do?
From what I understand, this is not a physics engine (at least in its current form). This is a bare metal 3D environment rendering engine particularly optimized for speed; speed being especially important for training deep reinforcement learning agents for instance.
Physics would be a layer above this; I imagine Bullet can be integrated within Habitat, but will come with significant hit on speed. These choices depend quite a bit on the task being studied.
Not quite. Real-world environments (which Habitat is aiming to be a close-enough proxy for along the computer vision axis) are far more visually complex than what Doom allows for.
https://github.com/facebookresearch/habitat-sim
https://github.com/facebookresearch/habitat-api