A local fruit-fly simulation combining a physical NeuroMechFly body in MuJoCo, MaleCNS connectome data, and explicit behavioral controllers.
The main hybrid mode supports walking, odor-guided food search, contact-based feeding through an articulated proboscis, grooming, sleep pressure, and waking. A separate two-fly arena adds shared food, body collisions, pushing, foreleg fencing, and retreat. These behaviors combine simulated physiology with engineered decisions and motor programs. This is an experimental model, not a physiologically validated digital fly.


People seeing what they can do with the data from Google’s research paper. They just finished mapping out the entire brain and central nervous system of the male fruit fly. https://research.google/blog/a-connectomics-milestone-mapping-the-complete-male-fruit-fly-brain/
This is Google’s summary about why they’re doing this research:
Wait, does this simulate fly behavior by simulating a fly brain?
Edit: it looks it simulates pieces of a fly brain
But at certain points it looks like the neural network hands off to human-programmed stuff
Fly-brain-shaped neural net with some explicitly programmed behaviors. The actual biochemistry of the brain is not modeled.