Deployment of Large Language Models to Control Mobile Robots at the Edge

TL;DR

This paper evaluates the use of large language models like GPT-4-Turbo and LLaMA 2 for intuitive human-robot interaction on mobile robots at the edge, comparing their performance and feasibility without relying on cloud services.

Contribution

It demonstrates the practical deployment of LLMs on edge devices for mobile robotics and compares the effectiveness of cloud-based versus offline-capable models.

Findings

GPT-4-Turbo outperforms LLaMA 2 in command accuracy and reliability.

LLaMA 2 shows limitations in consistency for command execution.

Edge deployment of LLMs is feasible but presents challenges in model performance.

Abstract

This paper investigates the possibility of intuitive human-robot interaction through the application of Natural Language Processing (NLP) and Large Language Models (LLMs) in mobile robotics. This work aims to explore the feasibility of using these technologies for edge-based deployment, where traditional cloud dependencies are eliminated. The study specifically contrasts the performance of GPT-4-Turbo, which requires cloud connectivity, with an offline-capable, quantized version of LLaMA 2 (LLaMA 2-7B.Q5 K M). These results show that GPT-4-Turbo delivers superior performance in interpreting and executing complex commands accurately, whereas LLaMA 2 exhibits significant limitations in consistency and reliability of command execution. Communication between the control computer and the mobile robot is established via a Raspberry Pi Pico W, which wirelessly receives commands from the computer without internet dependency and transmits them through a wired connection to the robot's Arduino controller. This study highlights the potential and challenges of implementing LLMs and NLP at the edge, providing groundwork for future research into fully autonomous and network-independent robotic systems. For video demonstrations and source code, please refer to: https://tinyurl.com/MobileRobotGPT4LLaMA2024.