Mode-Adaptive Neural Networks for Quadruped Motion Control

He Zhang, Sebastian Starke, Taku Komura, Jun Saito

Research output: Contribution to journalArticlepeer-review


Quadruped motion includes a wide variation of gaits such as walk, pace, trot and canter, and actions such as jumping, sitting, turning and idling. Applying existing data-driven character control frameworks to such data requires a significant amount of data preprocessing such as motion labeling and alignment. In this paper, we propose a novel neural network architecture called Mode-Adaptive Neural Networks for controlling quadruped characters. The system is composed of the motion prediction network and the gating network. At each frame, the motion prediction network computes the character state in the current frame given the state in the previous frame and the user-provided control signals. The gating network dynamically updates the weights of the motion prediction network by selecting and blending what we call the expert weights, each of which specializes in a particular movement. Due to the increased flexibility, the system can learn consistent expert weights across a wide range of non-periodic/periodic actions, from unstructured motion capture data, in an end-to-end fashion. In addition, the users are released from performing complex labeling of phases in different gaits. We show that this architecture is suitable for encoding the multimodality
of quadruped locomotion and synthesizing responsive motion in real-time.
Original languageEnglish
Article number145
Number of pages11
JournalACM Transactions on Graphics
Issue number4
Early online date30 Jul 2018
Publication statusPublished - 1 Aug 2018
Event45th Conference on Computer Graphics and Interactive Techniques - Vancouver, Canada
Duration: 12 Aug 201816 Aug 2018


  • quadruped animation
  • Character animation
  • Deep Learning


Dive into the research topics of 'Mode-Adaptive Neural Networks for Quadruped Motion Control'. Together they form a unique fingerprint.

Cite this