LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911614032150528 |
|---|---|
| author | Huang, Xu Zhang, Ruofan Cheng, Lu Song, Yuefeng Huang, Xu Zhang, Huayu Yin, Sheng Liang, Anyang Qian, Chen Zhou, Yin Yuan, Xiaoyun Cheng, Yuan |
| author_facet | Huang, Xu Zhang, Ruofan Cheng, Lu Song, Yuefeng Huang, Xu Zhang, Huayu Yin, Sheng Liang, Anyang Qian, Chen Zhou, Yin Yuan, Xiaoyun Cheng, Yuan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20193 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture Huang, Xu Zhang, Ruofan Cheng, Lu Song, Yuefeng Huang, Xu Zhang, Huayu Yin, Sheng Liang, Anyang Qian, Chen Zhou, Yin Yuan, Xiaoyun Cheng, Yuan Robotics 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. |
| title | LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture |
| topic | Robotics |
| url | https://arxiv.org/abs/2604.20193 |