A Spatiotemporal Knowledge Graph-Based Approach for Low-Altitude Aircraft Path Planning

Abstract. With the rapid development of low-altitude economy in China, path planning for low-altitude aircraft faces challenges such as strong environmental dynamics, complex constraints, and difficult real-time decision-making. To achieve efficient and universal path planning capabilities, this paper proposes a three-layer Spatiotemporal knowledge graph(3L-STKG) architecture comprising a conceptual layer, an instance layer, and a spatiotemporal layer. Guided by ontological spatiotemporal knowledge, this architecture enables efficient route planning in complex scenarios and addresses the challenges of path planning in low-altitude environments. The proposed method pre-matches the maneuverability constraints from the conceptual layer with the grid traversal attributes of the spatiotemporal layer through a cross-layer semantic association mechanism, dynamically constructing an accessible correlation network. On this basis, the path planning problem is transformed into a minimum weighted connected subgraph search problem in the ontology-constrained spatiotemporal network, and an improved A* algorithm is used to solve for the global optimal path. The experimental results show that the planning time in specific scenarios is reduced by 88.54% compared with traditional methods, while supporting rapid adaptation to multiple aircraft types. The research results provide a theoretical framework for intelligent decision-making of low-altitude aircraft in complex environments and have broad application prospects in fields such as emergency rescue and urban logistics.