Character Controllers Using Motion VAEs

TL;DR

This paper introduces Motion VAEs, a data-driven generative model for human movement that uses autoregressive variational autoencoders to create an action space for planning and control, enabling goal-directed motion generation.

Contribution

The paper presents a novel application of autoregressive Motion VAEs combined with reinforcement learning for human movement control in animation.

Findings

Effective generation of goal-directed human movements

Evaluation of system design choices and limitations

Demonstrated applicability across multiple tasks

Abstract

A fundamental problem in computer animation is that of realizing purposeful and realistic human movement given a sufficiently-rich set of motion capture clips. We learn data-driven generative models of human movement using autoregressive conditional variational autoencoders, or Motion VAEs. The latent variables of the learned autoencoder define the action space for the movement and thereby govern its evolution over time. Planning or control algorithms can then use this action space to generate desired motions. In particular, we use deep reinforcement learning to learn controllers that achieve goal-directed movements. We demonstrate the effectiveness of the approach on multiple tasks. We further evaluate system-design choices and describe the current limitations of Motion VAEs.