To address the issues that parameter adjustment in the traditional A* algorithm for path planning relies on experience and it is difficult to balance planning efficiency and quality, an improved A* algorithm incorporating a radial basis function (RBF) neural network was proposed. This algorithm utilized the RBF neural network to adaptively adjust the weight coefficient α of the A* algorithm based on environmental features, enabling autonomous parameter optimization. Meanwhile, the traditional eight-neighborhood search mechanism was optimized into a four-neighborhood expansion and combined with a path smoothing strategy, enhancing search efficiency while improving path executability. Simulation results demonstrate that the improved algorithm reduces the path length by 26.0% compared to the traditional four-neighborhood method and decreases the planning time by 91.1% compared to the eight-neighborhood method. Furthermore, real-world flight experiments conducted on the robot operating system (ROS) platform validate the method’s stable navigation and effective obstacle avoidance capabilities in complex obstacle environments.
实验上位机采用ROS自带的可视化工具RVIZ进行实时监控与交互,该平台可同步显示机器人运动轨迹、USB摄像头图像、蓝紫色区域膨胀代价地图及AMCL(adaptive Monte Carlo localization)绿色区域粒子云等信息。此外,通过界面顶部的“2D Nav Goal”选项,可直接使用鼠标设定导航目标点,操作便捷高效。
4.2 实验技术路线
树莓派4B作为机载计算核心,通过硬件串口与Pixhawk 2.4.8飞控建立MAVROS通信链路,实时获取惯性测量单元(inertial measurement unit, IMU)原始数据。同时,树莓派运行专用的摄像头处理节点和激光雷达处理节点,分别采集视觉图像与二维激光点云数据,技术路线如图11所示。
WangQinhe, YinYongxin, DaiLi, et al. UAV path planning based on Voronoi diagram and ant colony algorithm[J]. Navigation, Positioning and Timing, 2021, 8(2): 66-73.
[7]
LiuQ, ZhangY, LiM, et al. Multi-UAV path planning based on fusion of sparrow search algorithm and improved bioinspired neural network[J]. IEEE Access, 2021, 9: 124670-124681.
[8]
KimJ, LeeS, LeeS, et al. Neural-network-based path replanning for gliding vehicles considering terminal velocity[J]. IEEE Access, 2021, 9: 78701-78714.
ChenQijie, JinYuqiang, WangTaoyu. Research on UAV swarm obstacle avoidance algorithm based on improved artificial potential field algorithm[J]. Navigation, Positioning and Timing, 2020, 7(6):109-113.
[11]
MashayekhiR, IdrisM Y I, AnisiM H, et al. Informed RRT*-connect: an asymptotically optimal single-query path planning method[J]. IEEE Access, 2020, 8: 19842-19852.
[12]
AlarabiS, LuoC, SantoraM. A PRM approach to path planning with obstacle avoidance of an autonomous robot[C]// 8th International Conference on Automation, Robotics and Applications(ICARA). Prague: IEEE, 2022: 76-80.
[13]
ZhangJ, LiuZ, WangY, et al. Research on effective path planning algorithm based on improved A* algorithm[J]. Journal of Physics: Conference Series, 2022, 2188(1): 012014.
YuXiang, JiangChen, DuanSirui, et al. Path planning with improved A* algorithm and artificial potential field method[J]. Journal of System Simulation, 2024, 36(3): 782-794.
ZhongZhifeng, YiMingxing, ChenZhijun, et al. A shopping guide path planning method based on improved A* algorithm[J]. Computer Engineering and Applications, 2019, 55(5): 129-134.
[18]
WangH, QiX, LouS, et al. An efficient and robust improved A* algorithm for path planning[J]. Symmetry, 2021, 13(11): 2213.
JiangBo, HuXiaohan, ZhengYuan, et al. Local high-density UAV collision avoidance decision-making based on reinforcement learning[J]. Science Technology and Engineering, 2025, 25(30): 13167-13178.
[23]
KamruzzamanM, BhusalN, BenidrisM. A convolutional neural network-based approach to composite power system reliability evaluation[J]. International Journal of Electrical Power & Energy Systems, 2022, 135: 107468.
CaiJianyin, WangZhigang, GuoYufei, et al. Hybrid force/position control of a quadcopter grinding and polishing robot based on RBF neural network[J]. Journal of Wuhan University of Science and Technology, 2023, 46(6): 465-471.
[26]
李长锋. 基于动态环境的四旋翼无人机自主飞行技术研究[D]. 广州: 华南理工大学, 2021.
[27]
LiChangfeng. Research on autonomous flight technology of quadrotor UAVs based on dynamic environments[D]. Guangzhou: South China University of Technology, 2021.
WuYuwen, NiuZhiyue, HanQianqian. Rapid UAVpath planning based on heuristic search algorithm[J]. Science Technology and Engineering, 2020, 20(20): 8394-8399.
[30]
HeidP. A link between the steepest descent method and fixed-point iterations[J]. Optimization Letters, 2023, 17(1): 27-44.
[31]
KurzerK. Path planning in unstructured environments: a real-time hybrid A* implementation for fast and deterministic path generation for the KTH research concept vehicle[D]. Stockholm: KTH Royal Institute of Technology, 2016.