SafeGuard ASF：基于SR代理的人形机器人自主工业安全系统
SafeGuard ASF: SR Agentic Humanoid Robot System for Autonomous Industrial Safety
AI总结：
本文提出SafeGuard ASF系统，利用人形机器人结合多模态感知与ReAct代理推理框架，实现工业环境中的火灾烟雾、管道异常温度及禁区入侵检测，通过训练多种运动策略实现自主巡逻与避障。
摘要：
无人『暗工厂』的兴起要求具备多类型危险检测与响应能力的自主安全系统。本文提出SafeGuard ASF（Agentic Security Fleet）框架，部署人形机器人进行工业环境中的自主危险检测。系统整合多模态感知（RGB-D成像）、基于ReAct的代理推理框架及学习的运动策略。针对火灾烟雾检测、管道异常温度监控及禁区入侵检测三大关键场景，感知管道实现94.2%的mAP和127ms延迟。通过Unitree RL Lab使用PPO训练多种运动策略，如舞蹈动作追踪与速度控制，在80,000次训练迭代内稳定收敛。系统在仿真与现实环境中验证，展示自主巡逻、视觉人检测与避障能力。提出的ToolOrchestra行动框架通过感知、推理与行动工具实现结构化决策。
英文摘要：
The rise of unmanned ``dark factories'' operating without human presence demands autonomous safety systems capable of detecting and responding to multiple hazard types. We present SafeGuard ASF (Agentic Security Fleet), a comprehensive framework deploying humanoid robots for autonomous hazard detection in industrial environments. Our system integrates multi-modal perception (RGB-D imaging), a ReAct-based agentic reasoning framework, and learned locomotion policies on the Unitree G1 humanoid platform. We address three critical hazard scenarios: fire and smoke detection, abnormal temperature monitoring in pipelines, and intruder detection in restricted zones. Our perception pipeline achieves 94.2% mAP for fire or smoke detection with 127ms latency. We train multiple locomotion policies, including dance motion tracking and velocity control, using Unitree RL Lab with PPO, demonstrating stable convergence within 80,000 training iterations. We validate our system in both simulation and real-world environments, demonstrating autonomous patrol, human detection with visual perception, and obstacle avoidance capabilities. The proposed ToolOrchestra action framework enables structured decision-making through perception, reasoning, and actuation tools.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
