PMP: Learning to Physically Interact with Environments using Part-wise Motion Priors

TL;DR

This paper introduces a method to animate characters by combining multiple part-wise motion priors, enabling diverse and physically realistic interactions without requiring exhaustive reference data for every possible interaction scenario.

Contribution

The proposed PMP framework allows assembling multiple part skills to generate a wide variety of motions, overcoming limitations of existing methods that rely on limited reference samples.

Findings

Enables diverse motion synthesis by combining part-wise priors.

Allows training agents with multiple interaction skills.

Achieves physical interaction skills without object trajectory data.

Abstract

We present a method to animate a character incorporating multiple part-wise motion priors (PMP). While previous works allow creating realistic articulated motions from reference data, the range of motion is largely limited by the available samples. Especially for the interaction-rich scenarios, it is impractical to attempt acquiring every possible interacting motion, as the combination of physical parameters increases exponentially. The proposed PMP allows us to assemble multiple part skills to animate a character, creating a diverse set of motions with different combinations of existing data. In our pipeline, we can train an agent with a wide range of part-wise priors. Therefore, each body part can obtain a kinematic insight of the style from the motion captures, or at the same time extract dynamics-related information from the additional part-specific simulation. For example, we can first train a general interaction skill, e.g. grasping, only for the dexterous part, and then combine the expert trajectories from the pre-trained agent with the kinematic priors of other limbs. Eventually, our whole-body agent learns a novel physical interaction skill even with the absence of the object trajectories in the reference motion sequence.