LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture

2026-04-22

AI Summary

This work addresses the fundamental tension between the inherent uncertainty of artificial intelligence perception and the deterministic behavior mandated by industrial safety standards. To reconcile this conflict, the authors propose a low-latency perception-computation-control architecture compliant with ISO 13849 Category 3 / Performance Level d requirements. The architecture uniquely integrates a large language model–guided safety agent with a symmetric dual-channel redundant design, enabling automatic translation of natural language safety specifications into executable predicates. Fault-tolerant closed-loop control is achieved on cost-effective hardware through heterogeneous edge computing. Experimental validation on a dual RK3588 platform demonstrates the system’s effectiveness in representative human-robot interaction scenarios, offering a practical edge-deployment solution for safety-critical embodied AI systems.

Technology Category

• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Ensuring functional safety in human-robot interaction is challenging because AI perception is inherently probabilistic, whereas industrial standards require deterministic behavior. We present an LLM-guided safety agent for edge robotics, built on an ISO-compliant low-latency perception-compute-control architecture. Our method translates natural-language safety regulations into executable predicates and deploys them through a redundant heterogeneous edge runtime. For fault-tolerant closed-loop execution under edge constraints, we adopt a symmetric dual-modular redundancy design with parallel independent execution for low-latency perception, computation, and control. We prototype the system on a dual-RK3588 platform and evaluate it in representative human-robot interaction scenarios. The results demonstrate a practical edge implementation path toward ISO 13849 Category 3 and PL d using cost-effective hardware, supporting practical deployment of safety-critical embodied AI.

Problem

• functional safety
• human-robot interaction
• probabilistic perception
• deterministic behavior
• edge robotics

Innovation

• LLM-guided safety
• ISO-compliant architecture
• edge robotics
• dual-modular redundancy
• executable safety predicates