DeepMind open-sources a fruit fly that learned to fly, 59-dim action space on a laptop
anthara_ai · x · 2026-09-17
flybody, a project by Google DeepMind and HHMI Janelia published in Nature, is now open source (Apache 2.0): a fruit fly body rebuilt joint by joint from real microscopy, simulated in MuJoCo so it walks, grips, flies and lands — runnable on a laptop.
Key details:
- Legs, wings, head and abdomen are fully physically simulated, with leg adhesion so the fly grips surfaces.
- Walking alone has a 59-dimensional action space — that many controls a network must coordinate per step.
- Ready-made RL environments for walking imitation, free flight, and vision-guided flight from the fly's actual visual input.
- Python stack: clone it, open MuJoCo, and the fly appears on screen.
More from Embodied
- Wearing Whoop and Apple Watch on a single dual-slot band — tinyfool · 2026-11-02
- REA: async brain-cerebellum runtime for robots where policies never wait on the LLM — Pengfei Zhou · 2026-11-02
- Robot Combat Sports Coming to Japan with a Permanent Arena in Tokyo — cixliv · 2026-11-02
- REK robot fighting in the cage: humanoid bot in boxing gloves draws a crowd — broodsugar · 2026-11-02
- iPhone Duo: a folding iPhone mod impresses, but its hinge raises crackgate concerns — rudrank · 2026-11-02
- InflatableBots: University of Calgary's inflatable robots bring dynamic haptics to large-scale VR — lukas_m_ziegler · 2026-11-02