Towards Semantic Voxel-Based Reasoning for Robotic Fleet Management in Construction

Abstract: Current robotic fleet management in construction primarily relies on 2D maps and geometry-based planners, with limited integration of process context and machine capabilities. This restricts scalability and adaptability in complex, dynamic sites. This paper proposes a semantic voxelisation framework that combines 3D voxel models with knowledge of construction processes, resources, and capabilities using IOC, BOT, and CaSkMan ontologies. The knowledge for capability-aware planning and task scheduling is queried using SPARQL and translated into domains and constraints for the planning framework. The contribution is a unified semantic-to-robotic pipeline enabling context-aware planning and scheduling for holistic fleet management.