UniLegs: Universal Multi-Legged Robot Control through Morphology-Agnostic Policy Distillation

TL;DR

This paper presents a two-stage policy distillation framework using Transformers to create a universal controller for various legged robot morphologies, achieving high performance and generalization to unseen designs.

Contribution

It introduces a morphology-agnostic policy distillation method with Transformer architecture, enabling a single controller to handle diverse legged robot morphologies.

Findings

Transformer-based policy achieves 94.47% of specialized teacher performance on training morphologies.

The approach maintains 72.64% performance on unseen robot designs.

Transformer architecture outperforms MLP baselines in modeling joint relationships.

Abstract

Developing controllers that generalize across diverse robot morphologies remains a significant challenge in legged locomotion. Traditional approaches either create specialized controllers for each morphology or compromise performance for generality. This paper introduces a two-stage teacher-student framework that bridges this gap through policy distillation. First, we train specialized teacher policies optimized for individual morphologies, capturing the unique optimal control strategies for each robot design. Then, we distill this specialized expertise into a single Transformer-based student policy capable of controlling robots with varying leg configurations. Our experiments across five distinct legged morphologies demonstrate that our approach preserves morphology-specific optimal behaviors, with the Transformer architecture achieving 94.47% of teacher performance on training morphologies and 72.64% on unseen robot designs. Comparative analysis reveals that Transformer-based architectures consistently outperform MLP baselines by leveraging attention mechanisms to effectively model joint relationships across different kinematic structures. We validate our approach through successful deployment on a physical quadruped robot, demonstrating the practical viability of our morphology-agnostic control framework. This work presents a scalable solution for developing universal legged robot controllers that maintain near-optimal performance while generalizing across diverse morphologies.