Safety is extremely important for urban flights of autonomous Unmanned Aerial Vehicles (UAVs). Risk-aware path planning is one of the most effective methods to guarantee the safety of UAVs. This type of planning can be represented as a Constrained Shortest Path (CSP) problem, which seeks to find the shortest route that meets a predefined safety constraint. Solving CSP problems is NP-hard, presenting significant computational challenges. Although traditional methods can accurately solve CSP problems, they tend to be very slow. Previously, we introduced an additional safety dimension to the traditional A* algorithm, known as ASD A*, to effectively handle Constrained Shortest Path (CSP) problems. Then, we developed a custom learning-based heuristic using transformer-based neural networks, which significantly reduced computational load and enhanced the performance of the ASD A* algorithm. In this paper, we expand our dataset to include more risk maps and tasks, improve the proposed model, and increase its performance. We also introduce a new heuristic strategy and a novel neural network, which enhance the overall effectiveness of our approach.

翻译：对于城市环境中自主无人机（UAV）的飞行而言，安全性至关重要。风险感知路径规划是保障无人机安全最有效的方法之一。此类规划可表述为约束最短路径（CSP）问题，其目标是在满足预设安全约束条件下寻找最短路径。求解CSP问题是NP难的，存在显著的计算挑战。尽管传统方法能够精确求解CSP问题，但其计算速度通常较慢。此前，我们在传统A*算法中引入了一个额外的安全维度，称为ASD A*算法，以有效处理约束最短路径（CSP）问题。随后，我们利用基于Transformer的神经网络开发了一种定制化的学习型启发式方法，显著降低了计算负荷并提升了ASD A*算法的性能。本文通过扩展数据集以纳入更多风险地图与任务、改进所提模型并提升其性能。我们还引入了一种新的启发式策略与一种新颖的神经网络架构，从而全面提升了本方法的整体效能。