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
- Open-source Openclaw gives humanoids spatial-temporal understanding, works on Unitree G1 — hackgoofer · 2026-09-17
- BCI and computer architecture expert Bhattacharjee joins Princeton CS from Yale — LakeBrenden · 2026-09-17
- Japan's Ugo unveils Nova, a wheeled dual-arm robot with 10kg payload for factories — CyberRobooo · 2026-09-17
- VLBiMan++ learns pouring, tool use and folding from a single human demo, no retraining — stepjamUK · 2026-09-17
- Baidu's Apollo Go begins fully driverless testing on Hong Kong roads — Baidu_Inc · 2026-09-17
- MIT's FloatForm robot boats self-assemble into bridges on water, published in Nature — lukas_m_ziegler · 2026-09-17