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

TL;DR

This paper introduces an LLM-guided safety system for edge robotics that translates natural language safety rules into executable code, ensuring ISO-compliant safety in human-robot interactions with low latency and fault tolerance.

Contribution

It presents a novel approach combining LLMs, ISO standards, and dual-modular redundancy for safe, real-time edge robotics applications, demonstrated on a dual-RK3588 platform.

Findings

Successfully translated safety regulations into executable predicates.

Achieved ISO 13849 Category 3 and PL d compliance on cost-effective hardware.

Demonstrated low-latency, fault-tolerant safety in human-robot interaction scenarios.

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.