Towards Embodiment Scaling Laws
in Robot Locomotion

Affiliations

CoRL 2025

One Model, Two Worlds, Many Embodiments

TLDR: We uncover embodiment scaling laws: training on diverse robot embodiments enables broad generalization to unseen ones, demonstrated in a locomotion study across ~1,000 robots.

Overview

This work investigates embodiment scaling laws in robotics, hypothesizing that training a single control policy on a larger number of diverse robot embodiments improves its ability to generalize to unseen ones.

Generating ~1000 Robots

To study the effects of embodiment scaling, we procedurally generate GENBOT-1K dataset consisting if approximately 1,000 varied robot embodiments, including humanoids, quadrupeds, and hexapods, with different geometry, topology, and kinematics.

Variations:

Topology

Geometry

Kinematics

Humanoid

Quadruped

Hexapod

Cross-Embodiment Learning

We train policies using a single model architecture capable of handling diverse observation and action spaces on different random subsets of embodiments to uncover embodiment scaling laws.

Embodiment Scaling Laws

Training generalist locomotion policies on subsets of GENBOT-1K shows that generalization to unseen robots improves steadily as the number of training embodiments increases.

Scaling curve
Key Observations
  • More training embodiments → better generalization to unseen embodiments (C1–C4)
  • Harder embodiments require more embodiments to saturate generalization (C1 vs C2–C3)
  • Cross-morphology training improves generalization (C4 vs C5–C7)
  • Embodiment scaling >> pure data scaling for embodiment generalization (C4 vs C8)

Qualitative Results in Sim

A single policy controls diverse morphologies in simulation, both seen and novel.

Sim-to-Real and Cross-Embodiment Transfer

Our best learned policy demonstrates both sim-to-real and cross-embodiment transferability. All results shown below are using one single policy trained in simulation.

Unitree Go2 with Varying Joint Limits

100% (all knees)

60% (right rear knee)

20% (right rear knee)

60% (front left knee)

40% (front left knee)

20% (front left knee)

Unitree Go2 in Varying Environments

Gravel

Grass

Grass

Pavement

Pavement

Cobblestone

Unitree H1 in Varying Directions

 

Forward

 

 

Backward

 

 

Sideward

 

Unitree H1 under External Perturbations

 

Pushes

 

Citation

@article{ai2025towards,
  title={Towards Embodiment Scaling Laws in Robot Locomotion},
  author={Ai, Bo and Dai, Liu and Bohlinger, Nico and Li, Dichen and Mu, Tongzhou and Wu, Zhanxin and Fay, K and Christensen, Henrik I and Peters, Jan and Su, Hao},
  journal={Conference on Robot Learning (CoRL)},
  url={https://arxiv.org/abs/2505.05753},
  year={2025}
}

This website was inspired by Kevin Zakka's and Brent Yi's and builds on Nico Bohlinger's and Bo Ai's.