A hybrid spatial-temporal data model for indoor dynamic path planning in a 2D/2.5D environment

As building structures grow increasingly complex and demands for indoor navigation rise rapidly, representing dynamic indoor environments has become an urgent necessity for indoor path planning. Nevertheless, the majority of existing indoor data models still lack the capacity to depict the changing elements of indoor objects. In this paper, a hybrid data model (NRDM) that combines a node-relation graph (NRG) model and raster map is proposed to represent the temporal information of indoor objects. The spatial, attribute, and semantic information are extracted from a building information model (BIM) to define the subspaces and construct the NRDM. Meanwhile, a door-to-door (D2D) D* Lite algorithm is also proposed to plan the optimal path in a 2D/2.5D dynamic indoor environment for the humanoid robot with the semantic information derived from the BIM. The NRDM and D2D D* Lite algorithm were tested using two datasets (data from a single-story residential building (Dataset 1) and a multi-story office building (Dataset 2)) under two scenarios (door state changes (S1) and indoor fire propagation (S2)). The experimental results show that the NRDM can effectively represent dynamic information in an indoor space. The path lengths obtained by the D2D D*Lite algorithm using Dataset 1 under S1 and S2 are 49.87 m and 27.62 m respectively, and those obtained using Dataset 2 are 93.96 m and 38.73 m respectively. Although the lengths of the paths are longer than those of the two comparative algorithms D* Lite and LPA* in most cases, the paths obtained by D2D D*Lite algorithm can effectively avoid and stay away from obstacles, making the paths safer.