Toward Hardware-Agnostic Quadrupedal World Models via Morphology Conditioning

TL;DR

This paper introduces a morphology-conditioned quadrupedal world model that generalizes across different robot embodiments, enabling zero-shot locomotion control without retraining for each new morphology.

Contribution

It proposes a novel framework that explicitly conditions the dynamics model on robot morphology, allowing zero-shot generalization across different quadrupedal robots.

Findings

The model can generalize to new morphologies within the same family without retraining.

Explicit morphology conditioning improves zero-shot adaptation compared to implicit methods.

The approach enables safe and efficient locomotion control across varied robot embodiments.

Abstract

World models promise a paradigm shift in robotics, where an agent learns the underlying physics of its environment once to enable efficient planning and behavior learning. However, current world models are often hardware-locked specialists: a model trained on a Boston Dynamics Spot robot fails catastrophically on a Unitree Go1 due to the mismatch in kinematic and dynamic properties, as the model overfits to specific embodiment constraints rather than capturing the universal locomotion dynamics. Consequently, a slight change in actuator dynamics or limb length necessitates training a new model from scratch. In this work, we take a step towards a framework for training a generalizable Quadrupedal World Model (QWM) that disentangles environmental dynamics from robot morphology. We address the limitations of implicit system identification, where treating static physical properties (like mass or limb length) as latent variables to be inferred from motion history creates an adaptation lag that can compromise zero-shot safety and efficiency. Instead, we explicitly condition the generative dynamics on the robot's engineering specifications. By integrating a physical morphology encoder and a reward normalizer, we enable the model to serve as a neural simulator capable of generalizing across morphologies. This capability unlocks zero-shot control across a range of embodiments. We introduce, for the first time, a world model that enables zero-shot generalization to new morphologies for locomotion. While we carefully study the limitations of our method, QWM operates as a distribution-bounded interpolator within the quadrupedal morphology family rather than a universal physics engine, this work represents a significant step toward morphology-conditioned world models for legged locomotion.