Robotic Fire Risk Detection based on Dynamic Knowledge Graph Reasoning: An LLM-Driven Approach with Graph Chain-of-Thought

2025-08-25

AI Summary

To address critical challenges in fire scenarios—including incomplete robotic perception, insufficient situational awareness, and delayed response—this paper proposes Insights-on-Graph, a novel framework integrating large language model (LLM)-driven fire safety knowledge graph construction, multimodal real-time sensing (vision + environmental), and dynamic graph-based reasoning for interpretable risk identification and task-driven autonomous decision-making. Its key innovation lies in embedding schema-based chain-of-thought reasoning into knowledge graph inference, enabling joint optimization of pre-incident risk forecasting and in-fire rescue path planning. Evaluated in both simulated and real-world fire environments, the framework demonstrates significant improvements in risk detection accuracy and emergency response timeliness. It exhibits strong adaptability across diverse fire scenarios and high engineering feasibility for practical deployment.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness
• Reasoning under Uncertainty: Graphical Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Fire is a highly destructive disaster, but effective prevention can significantly reduce its likelihood of occurrence. When it happens, deploying emergency robots in fire-risk scenarios can help minimize the danger to human responders. However, current research on pre-disaster warnings and disaster-time rescue still faces significant challenges due to incomplete perception, inadequate fire situational awareness, and delayed response. To enhance intelligent perception and response planning for robots in fire scenarios, we first construct a knowledge graph (KG) by leveraging large language models (LLMs) to integrate fire domain knowledge derived from fire prevention guidelines and fire rescue task information from robotic emergency response documents. We then propose a new framework called Insights-on-Graph (IOG), which integrates the structured fire information of KG and Large Multimodal Models (LMMs). The framework generates perception-driven risk graphs from real-time scene imagery to enable early fire risk detection and provide interpretable emergency responses for task module and robot component configuration based on the evolving risk situation. Extensive simulations and real-world experiments show that IOG has good applicability and practical application value in fire risk detection and rescue decision-making.

Problem

• Enhancing robotic fire risk detection and emergency response planning
• Addressing incomplete perception and delayed response in fire scenarios
• Integrating knowledge graphs with multimodal models for early detection

Innovation

• LLM-constructed knowledge graph for fire domain
• Insights-on-Graph framework integrating KG and LMM
• Real-time risk detection with interpretable emergency responses