LLMs and Humanoid Robot Diversity: The Pose Generation Challenge

Overview

This repository contains the prompts and resources for the paper "LLMs and Humanoid Robot Diversity: The Pose Generation Challenge". The study evaluates the ability of Large Language Models (LLMs) to generate 3D robot poses across different humanoid robot platforms.

Abstract

Humanoid robots are increasingly being integrated into diverse scenarios, such as healthcare facilities, social settings, and workplaces. As the need for intuitive control by non-expert users grows, many studies have explored the use of Artificial Intelligence to enable communication and control. However, these approaches are often tailored to specific robots due to the absence of standardized conventions and notation. This study addresses the challenges posed by these inconsistencies and investigates their impact on the ability of Large Language Models (LLMs) to generate accurate 3D robot poses, even when detailed robot specifications are provided as input.

Repository Structure

├── prompts/          # Prompting strategies and templates
├── urdfs/       # Robot URDF files for all tested platofm
├── robot_poses/     # Predicted poses alongside GT poses
├── analysis/  #Files to analyse results

Citation

If you find this code and paper useful for your research, please kindly cite our paper.

Catalini, R., Biagi, F., Salici, G., Borghi, G., Vezzani, R., & Biagiotti, L. (2025). LLMs and humanoid robot diversity: The pose generation challenge. To appear in Proceedings of the International Conference on Social Robotics.