DeepMind open-sources flybody: a full fruit fly simulated joint-by-joint in MuJoCo, published in Nature
ZeroStateReflex · x · 2026-09-11
Google DeepMind and HHMI Janelia have open-sourced flybody (Apache 2.0 on GitHub), published in Nature: not a model of an animal, but a fruit fly rebuilt joint-by-joint from microscopy data.
Key details:
- Full-body MuJoCo simulation: legs, wings, head, and abdomen all articulated, runnable on a laptop
- 59-dimensional action space: just the walking task requires coordinating 59 degrees of freedom per step
- Leg adhesion: the fly grips surfaces instead of sliding like a game asset
- Ready-made RL environments: walking imitation, free flight, and vision-guided flight where the policy flies on what the fly sees
The whole project is Python-based—clone it, open MuJoCo, and start experimenting. A valuable resource for neuroscience and embodied AI research.
More from Embodied
- OpenTac tactile sensing project to be showcased at CoRL — _krishna_murthy · 2026-10-28
- Hybrid LLM agent scores 83.2%, beats nine VLA policies on new SO-101 robot arm benchmark — Truman Hickok · 2026-10-28
- cixliv: robot fighting may be the first realized market where bots beat average humans — cixliv · 2026-10-28
- Can the Hiwonder MentorPi T1 run fully offline as a robot pet? Pi 5 questioned — oulu2006 · 2026-10-28
- Testing Mint Modeler to Build the Menlo Research Robot — freelerobot · 2026-10-28
- Khosla-backed startup builds a 'mind-reading' cap with 100,000 tiny chips to write AI prompts — Distinct-Question-16 · 2026-10-28