Quadrupedal World Model: A Single Morphology-Conditioned Dynamics Model for Generalization Across Heterogeneous Quadrupeds
Researchers from the ETH Robotic Systems Lab present a world model for quadruped robots that allows zero-shot policy transfer across different robot morphologies without fine-tuning, retraining, or warm-up. The model conditions policies on dynamics rather than directly training policies, enabling generalization across heterogeneous quadrupeds.
The paper introduces a world model for quadruped robots that enables zero-shot policy transfer across different morphologies without fine-tuning, suggesting a shift from policy-based to dynamics-conditioned learning.
Source: ETH Robotic Systems Lab — X · Read original article ↗
Article text · Original source · English
In our latest work at @corl_conf, we introduce Quadrupedal World Model: a single morphology-conditioned dynamics model, where policies are trained entirely in imagination.
We found generalization emerges by conditioning the dynamics, not the policy.
What if one world model could control many different robots? 🤖🌍 That's QWM. In this 2 minutes video we show keypoints about QWM: learning across heterogeneous quadrupeds, and transferring zero-shot to unseen morphologies. No fine-tuning. No warm-up. No retraining. Let's talk it further at CoRL 🥳View the quoted post on X
Source：Robotic Systems Lab · x.com