LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture
On the map: LLM agents and tool use → Agent threats, guardrails and governance
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 8 of its 24 references that are in the map. First posted on arXiv 22 Apr 2026.
Builds on
8 of 24 references.
Closest ancestors · 1
Same direction, newest first
Other references · 7
- 2019Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videoscited by 103
- 2023Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?cited by 53
- 2024Semantically Safe Robot Manipulation: From Semantic Scene Understanding to Motion Safeguardscited by 16
- 2026Grounding Generative Planners in Verifiable Logic: A Hybrid Architecture for Trustworthy Embodied AIcited by 4
- 2024IPAD: Industrial Process Anomaly Detection Datasetcited by 3
- 2025Executable Governance for AI: Translating Policies into Rules Using LLMscited by 3
- 2026Pre-Execution Safety Gate & Task Safety Contracts for LLM-Controlled Robot Systemscited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Safety Aware Task Planning via Large Language Models in Robotics
- 2025SafePlan: Leveraging Formal Logic and Chain-of-Thought Reasoning for Enhanced Safety in LLM-based Robotic Task Planning
- 2025RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
- 2025A Framework for Benchmarking and Aligning Task-Planning Safety in LLM-Based Embodied Agents
- 2024Safeguarding AI Agents: Developing and Analyzing Safety Architectures
- 2026ForesightSafety-VLA: A Unified Diagnostic Safety Benchmark for Vision-Language-Action Models
- 2026How Long Until Your Robot Ignores You? A Safety Benchmark for LLM Orchestrators in Human-Humanoid Collaboration ↗
- 2026VLPSA: Vision-Language-Poisson-Safe Actions for Full-Body Safety of Learned Policies