RoboMorph: Evolving Robot Morphology using Large Language Models

TL;DR

RoboMorph leverages large language models and evolutionary algorithms to automate the generation and optimization of modular robot designs, resulting in diverse, terrain-specific morphologies that outperform traditional methods.

Contribution

This work introduces a novel framework combining LLMs with evolutionary algorithms for automated robot morphology design, demonstrating improved efficiency and diversity.

Findings

RoboMorph discovers diverse terrain-specific robot morphologies.

It outperforms traditional graph-search methods in design quality.

The approach reduces computational time in robot design exploration.

Abstract

We introduce RoboMorph, an automated approach for generating and optimizing modular robot designs using large language models (LLMs) and evolutionary algorithms. Each robot design is represented by a structured grammar, and we use LLMs to efficiently explore this design space. Traditionally, such exploration is time-consuming and computationally intensive. Using a best-shot prompting strategy combined with reinforcement learning (RL)-based control evaluation, RoboMorph iteratively refines robot designs within an evolutionary feedback loop. Across four terrain types, RoboMorph discovers diverse, terrain-specialized morphologies, including wheeled quadrupeds and hexapods, that match or outperform designs produced by Robogrammar's graph-search method. These results demonstrate that LLMs, when coupled with evolutionary selection, can serve as effective generative operators for automated robot design. Our project page and code are available at https://robomorph.github.io.