Mode-Adaptive Neural Networks for Quadruped Motion Control

Have a look at an amazing study on real-time quadruped motion synthesis which will be presented at this year’s SIGGRAPH.

Have a look at an amazing study on real-time quadruped motion synthesis which will be presented at this year’s SIGGRAPH. The paper proposes a novel method called Mode-Adaptive Neural Networks. The thing is that this model could be really useful for games, films, and other projects that require top-notch animation. Let’s study the details. 

We present a novel method for real-time quadruped motion synthesis called Mode-Adaptive Neural Networks. Our system is trained in an end-to-end fashion on unstructured motion capture data, without requiring labels for the phase or locomotion gaits. The system can be used for creating natural animations in games and films, and is the first of such systematic approaches whose quality could be of practical use. It is implemented in the Unity 3D engine and TensorFlow, and published under the ACM Transactions on Graphics / SIGGRAPH 2018.

You can find the full paper here. You can also check out the project on GitHub

Published 16 May 2018
Arti Sergeev
Business Head