PDP: Physics-Based Character Animation via Diffusion Policy

TL;DR

This paper introduces PDP, a novel method combining reinforcement learning and behavior cloning to generate diverse, realistic, and physically plausible character animations capable of correcting errors and interacting with environments.

Contribution

The paper presents a new diffusion policy framework that integrates RL and BC to improve stability and diversity in physics-based character animation tasks.

Findings

PDP effectively recovers from perturbations in motion.

It achieves accurate motion tracking across diverse scenarios.

Demonstrates promising results in physics-based text-to-motion synthesis.

Abstract

Generating diverse and realistic human motion that can physically interact with an environment remains a challenging research area in character animation. Meanwhile, diffusion-based methods, as proposed by the robotics community, have demonstrated the ability to capture highly diverse and multi-modal skills. However, naively training a diffusion policy often results in unstable motions for high-frequency, under-actuated control tasks like bipedal locomotion due to rapidly accumulating compounding errors, pushing the agent away from optimal training trajectories. The key idea lies in using RL policies not just for providing optimal trajectories but for providing corrective actions in sub-optimal states, giving the policy a chance to correct for errors caused by environmental stimulus, model errors, or numerical errors in simulation. Our method, Physics-Based Character Animation via Diffusion Policy (PDP), combines reinforcement learning (RL) and behavior cloning (BC) to create a robust diffusion policy for physics-based character animation. We demonstrate PDP on perturbation recovery, universal motion tracking, and physics-based text-to-motion synthesis.