Safety Control of Service Robots with LLMs and Embodied Knowledge Graphs

TL;DR

This paper introduces a novel safety framework for service robots by integrating Large Language Models with Embodied Knowledge Graphs and predefined control prompts to ensure safe and compliant robot actions in real-world tasks.

Contribution

The paper presents a new integration of LLMs with Embodied Knowledge Graphs and control prompts to improve safety and compliance in autonomous service robots.

Findings

Robots with the proposed framework showed higher safety compliance in real-world tasks.

The integration effectively aligns robot actions with safety protocols.

Experimental results demonstrate improved safety adherence over traditional methods.

Abstract

Safety limitations in service robotics across various industries have raised significant concerns about the need for robust mechanisms ensuring that robots adhere to safe practices, thereby preventing actions that might harm humans or cause property damage. Despite advances, including the integration of Knowledge Graphs (KGs) with Large Language Models (LLMs), challenges in ensuring consistent safety in autonomous robot actions persist. In this paper, we propose a novel integration of Large Language Models with Embodied Robotic Control Prompts (ERCPs) and Embodied Knowledge Graphs (EKGs) to enhance the safety framework for service robots. ERCPs are designed as predefined instructions that ensure LLMs generate safe and precise responses. These responses are subsequently validated by EKGs, which provide a comprehensive knowledge base ensuring that the actions of the robot are continuously aligned with safety protocols, thereby promoting safer operational practices in varied contexts. Our experimental setup involved diverse real-world tasks, where robots equipped with our framework demonstrated significantly higher compliance with safety standards compared to traditional methods. This integration fosters secure human-robot interactions and positions our methodology at the forefront of AI-driven safety innovations in service robotics.