Safety Aware Task Planning via Large Language Models in Robotics

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Khan, Azal Ahmad, Andrev, Michael, Murtaza, Muhammad Ali, Aguilera, Sergio, Zhang, Rui, Ding, Jie, Hutchinson, Seth, Anwar, Ali
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913747347439616
author Khan, Azal Ahmad
Andrev, Michael
Murtaza, Muhammad Ali
Aguilera, Sergio
Zhang, Rui
Ding, Jie
Hutchinson, Seth
Anwar, Ali
author_facet Khan, Azal Ahmad
Andrev, Michael
Murtaza, Muhammad Ali
Aguilera, Sergio
Zhang, Rui
Ding, Jie
Hutchinson, Seth
Anwar, Ali
contents The integration of large language models (LLMs) into robotic task planning has unlocked better reasoning capabilities for complex, long-horizon workflows. However, ensuring safety in LLM-driven plans remains a critical challenge, as these models often prioritize task completion over risk mitigation. This paper introduces SAFER (Safety-Aware Framework for Execution in Robotics), a multi-LLM framework designed to embed safety awareness into robotic task planning. SAFER employs a Safety Agent that operates alongside the primary task planner, providing safety feedback. Additionally, we introduce LLM-as-a-Judge, a novel metric leveraging LLMs as evaluators to quantify safety violations within generated task plans. Our framework integrates safety feedback at multiple stages of execution, enabling real-time risk assessment, proactive error correction, and transparent safety evaluation. We also integrate a control framework using Control Barrier Functions (CBFs) to ensure safety guarantees within SAFER's task planning. We evaluated SAFER against state-of-the-art LLM planners on complex long-horizon tasks involving heterogeneous robotic agents, demonstrating its effectiveness in reducing safety violations while maintaining task efficiency. We also verify the task planner and safety planner through actual hardware experiments involving multiple robots and a human.
format Preprint
id arxiv_https___arxiv_org_abs_2503_15707
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Safety Aware Task Planning via Large Language Models in Robotics
Khan, Azal Ahmad
Andrev, Michael
Murtaza, Muhammad Ali
Aguilera, Sergio
Zhang, Rui
Ding, Jie
Hutchinson, Seth
Anwar, Ali
Robotics
Artificial Intelligence
The integration of large language models (LLMs) into robotic task planning has unlocked better reasoning capabilities for complex, long-horizon workflows. However, ensuring safety in LLM-driven plans remains a critical challenge, as these models often prioritize task completion over risk mitigation. This paper introduces SAFER (Safety-Aware Framework for Execution in Robotics), a multi-LLM framework designed to embed safety awareness into robotic task planning. SAFER employs a Safety Agent that operates alongside the primary task planner, providing safety feedback. Additionally, we introduce LLM-as-a-Judge, a novel metric leveraging LLMs as evaluators to quantify safety violations within generated task plans. Our framework integrates safety feedback at multiple stages of execution, enabling real-time risk assessment, proactive error correction, and transparent safety evaluation. We also integrate a control framework using Control Barrier Functions (CBFs) to ensure safety guarantees within SAFER's task planning. We evaluated SAFER against state-of-the-art LLM planners on complex long-horizon tasks involving heterogeneous robotic agents, demonstrating its effectiveness in reducing safety violations while maintaining task efficiency. We also verify the task planner and safety planner through actual hardware experiments involving multiple robots and a human.
title Safety Aware Task Planning via Large Language Models in Robotics
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2503.15707