• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
  • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    flybody simulates a fruit fly’s movements with open-source code, a user says

    The post credits Google DeepMind and HHMI Janelia with the project and says an AI agent learns to move the simulated body rather than relying on animation.

    ZY
    1 Source, 19d ago, first seen 19d ago

    TLDR

    A user describes flybody as a Python-based fruit fly simulation rebuilt from microscopy and running in MuJoCo, a physics engine. The post says it includes articulated legs, wings, head and abdomen, plus leg adhesion to grip surfaces. According to the user, its reinforcement-learning environments cover walking imitation, free flight and vision-guided flight, where the agent uses what the simulated fly sees. The user says the code is available on GitHub under the Apache 2.0 license.

    Combined views

    566.7K

    1 Source, first seen 19d ago

    Combined views

    566.7K

    1 Source, first seen 19d ago

    4.9K likes
    4.9K likes
    112 comments
    2.4K saves
    509 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    112 comments
    2.4K saves
    509 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    1 Source

    @Zyvex_0x🚨 Someone open sourced an entire animal. Not a model of an animal. The animal. A fruit fly, rebuilt joint by joint from microscopy, that walks, grips, flies and lands inside a physics engine running on your laptop. It's called flybody. Built by Google DeepMind and HHMI Janelia, published in Nature, and sitting on GitHub under Apache 2.0 right now. What's actually inside: A full body in MuJoCo. Legs, wings, head, abdomen, every joint articulated and physically simulated. A 59-dimensional action space in the walking task alone. That is how many things a network has to coordinate for the fly to take one step. Leg adhesion, so it actually grips surfaces instead of sliding off them 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 thing is Python. Clone it, open MuJoCo, and the fly is on your screen. And the part that got me: Nobody animated any of this. You hand the body to a reinforcement learning agent and it discovers how to move it. Same loop as a robot arm, except the robot is a bug and the reward is staying airborne. Which means people are now training it to do things no fly has done in 100 million years of evolution. 525 stars. Apache 2.0. Zero dollars.

    1 Source

    @Zyvex_0x🚨 Someone open sourced an entire animal. Not a model of an animal. The animal. A fruit fly, rebuilt joint by joint from microscopy, that walks, grips, flies and lands inside a physics engine running on your laptop. It's called flybody. Built by Google DeepMind and HHMI Janelia, published in Nature, and sitting on GitHub under Apache 2.0 right now. What's actually inside: A full body in MuJoCo. Legs, wings, head, abdomen, every joint articulated and physically simulated. A 59-dimensional action space in the walking task alone. That is how many things a network has to coordinate for the fly to take one step. Leg adhesion, so it actually grips surfaces instead of sliding off them 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 thing is Python. Clone it, open MuJoCo, and the fly is on your screen. And the part that got me: Nobody animated any of this. You hand the body to a reinforcement learning agent and it discovers how to move it. Same loop as a robot arm, except the robot is a bug and the reward is staying airborne. Which means people are now training it to do things no fly has done in 100 million years of evolution. 525 stars. Apache 2.0. Zero dollars.