UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control
This addresses the problem of domain gaps and task-specific fine-tuning in physics-based character control for applications like animation and robotics, representing a novel method for a known bottleneck.
The paper tackles the challenge of generating natural and physically plausible character motion for long-horizon control with diverse guidance signals by introducing UniPhys, a diffusion-based behavior cloning framework that unifies motion planning and control into a single model, resulting in outperforming prior methods in motion naturalness, generalization, and robustness across diverse control tasks.
Generating natural and physically plausible character motion remains challenging, particularly for long-horizon control with diverse guidance signals. While prior work combines high-level diffusion-based motion planners with low-level physics controllers, these systems suffer from domain gaps that degrade motion quality and require task-specific fine-tuning. To tackle this problem, we introduce UniPhys, a diffusion-based behavior cloning framework that unifies motion planning and control into a single model. UniPhys enables flexible, expressive character motion conditioned on multi-modal inputs such as text, trajectories, and goals. To address accumulated prediction errors over long sequences, UniPhys is trained with the Diffusion Forcing paradigm, learning to denoise noisy motion histories and handle discrepancies introduced by the physics simulator. This design allows UniPhys to robustly generate physically plausible, long-horizon motions. Through guided sampling, UniPhys generalizes to a wide range of control signals, including unseen ones, without requiring task-specific fine-tuning. Experiments show that UniPhys outperforms prior methods in motion naturalness, generalization, and robustness across diverse control tasks.