Human-like Character Animation System Uses AI to Navigate Terrains

Researchers from University of Edinburgh and Method Studios developed a real-time character control mechanism using deep learning that can help virtual characters walk, run and jump a little more naturally. 

“Data-driven motion synthesis using neural networks is attracting researchers in both the computer animation and machine learning communities thanks to its high scalability and runtime efficiency,” mentioned the researchers in their paper.

Using CUDA, NVIDIA GeForce GPUs and cuDNN with the Theano deep learning framework, their “Phase-Functioned Neural Network” is a time-series approach that can predict the pose of the character given the user inputs and the previous state of the character. The system is trained on data that includes the character moving over different terrains which then helps the character automatically adapt to the geometry of the environment during runtime.

The innovative work by Daniel Holden (now a researcher at Ubisoft Montreal), Taku Komura (University of Edinburgh) and Jun Saito (Method Studios) can possibly change the future of video game development.

Read more >

2 thoughts on “Human-like Character Animation System Uses AI to Navigate Terrains

  1. Filip Jakub Dębosz on May 23, 2017 at 9:08 am said:

    Płotka nie miała podobnego? hehe

  2. Yan Bellavance on August 8, 2017 at 9:18 pm said:

    oh nice! will nvidia emergy from virtual to reality? amazing…

    we invented computers to the image of our brain
    we are now discovering our brain from the image of a computer.

    The cloud…it’s heaven….your subconsiousness and memorie could be stored and backup somewhere in the cloud.. you might even be in the cloud right now(quantum entanglement from the big bang making teleportation

    We learned how to make computers by understanding our brain.
    our computer technology went so far that we discovered more aspects of the nature of the brain and increased our definition of understanding of already known brain theories and principals

    Good jobb