🤖 AI Summary
To address insufficient safety and regulatory compliance of service robots in human-robot cohabitation scenarios, this paper proposes a closed-loop safety verification framework integrating large language models (LLMs), embodied knowledge graphs (EKGs), and embodied robot control prompts (ERCPs). The method innovatively employs ERCPs to guide LLMs in generating safety-compliant motion commands, while leveraging EKGs for real-time physical feasibility validation—thereby enabling cross-modal safety alignment across language understanding, knowledge reasoning, and embodied execution. A multi-stage safety verification mechanism is established within the framework. Evaluated on real-world service tasks, it reduces unsafe operation rates by 72% and significantly improves safety compliance. The framework delivers a verifiable, interpretable safety assurance solution for personnel and asset protection in human-robot collaborative environments.
📝 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.