SafeGuard ASF: SR Agentic Humanoid Robot System for Autonomous Industrial Safety

TL;DR

SafeGuard ASF is a humanoid robot system designed for autonomous hazard detection and safety in industrial environments, integrating perception, reasoning, and locomotion for tasks like fire detection and intruder monitoring.

Contribution

This work introduces a comprehensive humanoid robot framework combining multi-modal perception, agentic reasoning, and learned locomotion policies for industrial safety applications.

Findings

Achieved 94.2% mAP in fire and smoke detection with 127ms latency.

Demonstrated stable locomotion policy training within 80,000 iterations.

Validated autonomous patrol and hazard detection in real-world environments.

Abstract

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.