DASA: a direction-aware and self-adaptive A algorithm with learned heuristic for UAV path planning of smart city

Path planning is a fundamental component in the development of robotics, autonomous navigation, and intelligent systems, playing a pivotal role in the functioning of smart cities. Within the realm of smart cities, where infrastructure is becoming increasingly interconnected, efficient path planning algorithms are essential for optimizing traffic flow, reducing congestion, and ensuring the seamless movement of people and goods. Among various path planning algorithms, the A* algorithm remains one of the most widely used approaches due to its completeness and optimality under consistent heuristics. However, traditional A* suffers from several limitations when applied to complex 3D environments, including uniform neighbor expansion, fixed-resolution grids, and overly simplistic heuristic functions. These drawbacks often lead to excessive computation, suboptimal paths, and failure in cluttered or large-scale scenarios. To address these challenges, we propose a direction-aware and self-adaptive A* algorithm named DASA*, an enhanced A*-based path planning framework. First, we introduce a direction-aware neighbor selection mechanism that prioritizes node expansion along vectors aligned with the goal, significantly reducing unnecessary exploration. Second, a resolution-adaptive search strategy dynamically adjusts the planning granularity according to local obstacle density, improving both efficiency and safety in heterogeneous environments. Third, we design a learned heuristic interface that supports the integration of neural models trained on spatial and semantic environmental features, enabling more informed and goal-directed search behavior. Finally, we design a path adjustment strategy to simplify the path by removing unnecessary path points to generate smoother and more natural planning trajectories. Additionally, DASA* features a robust fallback mechanism to guarantee path discovery even when guided strategies are overly restrictive. Subsequently, Extensive experiments in simulated 3D environments demonstrate that DASA* outperforms conventional A* and its variants in terms of planning time, length of optimal path , and success rate. The proposed framework provides a practical and extensible foundation for real-world applications such as UAV navigation, mobile robotics, and autonomous inspection in complex terrains.