Dynamic Evacuation Routing Using IoT Fire Sensors and

Semantic BIM Graphs

Rajkumar Rajavel1,* N. Partheeban2

1 School of Engineering and Technology, Department of AI and Data Science Engineering, CHRIST (Deemed to be University),

Kanmanike, Kumbalagodu, Mysore Road, Bangalore, Karnataka-560074, India

2 Department of Computer Science and Engineering, SRM Institute of Science and Technology, Delhi-NCR Campus, Delhi-Meerut

Road, Modinagar, India

Received: December 18, 2025 Revised: January 25, 2026 Accepted: March 03, 2026 ⋆ Corresponding author

ABSTRACT

Indoor fire evacuation requires decisions that change as smoke, heat, and occupant movement evolve. Conventional

evacuation drawings are usually prepared before an incident and cannot represent real-time loss of visibility, blocked

corridors, congested stairs, or the changing reliability of alternative exits. This paper proposes a dynamic evacuationrouting

framework that connects IoT fire-sensor streams with a semantic graph derived from a BIM model. The

building is represented as a weighted network of rooms, corridors, doors, stairs, and exits, while sensor readings are

transformed into a time-dependent hazard index that continuously modifies edge costs. The proposed model integrates

fire-safety asset recognition, semantic BIM enrichment, hazard propagation, congestion-aware edge weighting, and

dynamic shortest-path recalculation. A controlled simulation demonstrates how the route recommendation changes

during fire development and how dynamic routing reduces hazard exposure compared with a static egress plan. The

study contributes a transparent computational structure for transforming BIM from a static documentation model

into an adaptive emergency decision-support interface.

Keywords: Building information modelling Dynamic evacuation IoT fire sensors Semantic graph Dijkstra

algorithm Fire safety engineering

1. INTRODUCTION

Fire evacuation planning in buildings is commonly developed

around fixed exit routes, prescribed travel distances, and static

assumptions about the availability of corridors, doors, and

stairs. These assumptions are useful for code compliance,

yet they are limited during an actual incident because fire

conditions develop unevenly across compartments. A corridor

that is acceptable at the beginning of an event may become

unsafe after smoke migration, while an initially longer route

may become preferable if it avoids high-risk zones. The need

for adaptive routing is therefore not only a computational

problem, but also a fire-safety management problem that

requires real-time interpretation of building geometry and

sensor evidence.

Building Information Modeling (BIM) provides a structured

representation of indoor spaces, openings, vertical circulation,

and fire-safety assets. However, BIM is often used as a static

repository of drawings and object properties rather than as a

live graph for emergency reasoning. A BIM model contains

the information required to identify rooms, doors, corridors,

stairs, exits, and equipment locations, but these objects must

be transformed into a navigable semantic network before they

can support evacuation computation. Without this transformation,

BIM cannot directly answer routing questions such