Observed arrival · 2026-09-21
FlyDrones: When a Fruit Fly Flies the Drone
An online 3D and 2D simulator uses a spiking neural network modeled on fruit-fly visual circuits to steer an FPV drone.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Researchers and builders exploring bio-inspired autonomy
- Worth noticing
- The simulator reports reducing default MID collisions from four to one after adding reward-modulated Hebbian learning.
Field notes
The homepage exposes the simulator’s internal chain rather than treating the result as a black box: rendered pixels become 1,024 compound-eye values, pass through structured LIF connections, and produce five named outputs. A 16-frame decoder converts spike activity into yaw and throttle. The page distinguishes completed LGMD, central-complex, and mushroom-body stages from the planned banked 3D escape maneuver, and provides a 19 KB Canvas version for lower-powered devices.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
◉HumanPersonal, local, civic, or handmade
One card from the complete issue