基于强化学习的改进三维A*算法在线航迹规划

任智, 张栋, 唐硕

Improved three-dimensional A* algorithm of real-time path planning based on reinforcement learning

Zhi REN, Dong ZHANG, Shuo TANG

表5 仿真场景参数表

Table 5 Simulation scene parameters table (°)

场景 起始节点 目标节点 禁飞区1 禁飞区2 禁飞区3 禁飞区4 禁飞区5 禁飞区6 1 (112.9, 38.2) (112.1, 38.8) (112.4, 38.6) (112.7, 38.4) (112.5, 38.44) (112.6, 38.25) (112.4, 38.4) (112.2, 38.5) 2 (112.9, 38.7) (112.1, 38.2) (112.4, 38.6) (112.7, 38.4) (112.5, 38.44) (112.6, 38.25) (112.4, 38.4) (112.2, 38.5) 3 (112.9, 38.5) (112.1, 38.4) (112.4, 38.6) (112.7, 38.4) (112.5, 38.44) (112.6, 38.25) (112.4, 38.4) (112.2, 38.5) 4 (112.9, 38.2) (112.1, 38.8) (112.7, 38.3) (112.4, 38.6) (112.4, 38.3) (112.2, 38.4) (112.6, 38.3) (112.6, 38.4) 5 (112.9, 38.7) (112.1, 38.2) (112.7, 38.3) (112.4, 38.6) (112.4, 38.3) (112.2, 38.4) (112.6, 38.3) (112.6, 38.4) 6 (112.9, 38.5) (112.1, 38.4) (112.7, 38.3) (112.4, 38.6) (112.4, 38.3) (112.2, 38.4) (112.6, 38.3) (112.6, 38.4)