Semantics-based connectivity graph for indoor pathfinding powered by IFC-Graph

Abstract

Pathfinding is important for many indoor location-based applications such as facility management and indoor navigation. Conventional approaches for constructing indoor networks for pathfinding are mostly based on geometry processing, which can be computing-intensive and time-consuming, especially for buildings with complex irregular shapes. In addition, the generated geometric networks often lack semantics. This paper proposes a new semantics-based approach for constructing navigable indoor networks. This approach uses the rich semantic information from Industry Foundation Classes (IFC) in the form of IFC-Graph (i.e., a graph-based representation of building information developed in a prior study) so as to meet the needs of indoor pathfinding. Real-world building models are used to validate the proposed approach. The results show that 1) the semantics-based approach has advantages in object-to-object pathfinding such as space-to-space, space-to-exit, and space-to-facility, 2) the use of graph technology makes it flexible to add semantic information to the network to better support pathfinding applications. The semantics-based approach can fit into digital twin technology and integrate with augmented reality.