C$\cdot$ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters

Abstract

We present C$\cdot$ASE, an efficient and effective framework that learns conditional Adversarial Skill Embeddings for physics-based characters. Our physically simulated character can learn a diverse repertoire of skills while providing controllability in the form of direct manipulation of the skills to be performed. C$\cdot$ASE divides the heterogeneous skill motions into distinct subsets containing homogeneous samples for training a low-level conditional model to learn conditional behavior distribution. The skill-conditioned imitation learning naturally offers explicit control over the character's skills after training. The training course incorporates the focal skill sampling, skeletal residual forces, and element-wise feature masking to balance diverse skills of varying complexities, mitigate dynamics mismatch to master agile motions and capture more general behavior characteristics, respectively. Once trained, the conditional model can produce highly diverse and realistic skills, outperforming state-of-the-art models, and can be repurposed in various downstream tasks. In particular, the explicit skill control handle allows a high-level policy or user to direct the character with desired skill specifications, which we demonstrate is advantageous for interactive character animation.

SIGGRAPH Asia 2023

References in corpus (10)

• Learning Transferable Visual Models From Natural Language Supervision
• NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
• Robust Motion In-betweening
• ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
• Human Motion Diffusion Model
• ControlVAE: Model-Based Learning of Generative Controllers for Physics-Based Characters
• CALM: Conditional Adversarial Latent Models for Directable Virtual Characters
• MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies
• PADL: Language-Directed Physics-Based Character Control
• UniCon: Universal Neural Controller For Physics-based Character Motion