Simulation of unmanned survey path planning in debris flow gully based on GRE-Bat algorithm  

作　　者：LIU Dunlong FENG Duanguo SANG Xuejia ZHANG Shaojie YANG Hongjuan 

机构地区：[1]College of Software Engineering,Chengdu University of Information Technology,Chengdu 610225,China [2]State Key Laboratory of Mountain Hazards and Engineering Resilience,Institute of Mountain Hazards and Environment,Chinese Academy of Sciences,Chengdu 610299,China

出　　处：《Journal of Mountain Science》2024年第12期4062-4082,共21页山地科学学报（英文）

基　　金：supported by National Natural Science Foundation of China(No.42302336);Project of the Department of Science and Technology of Sichuan Province(No.2024YFHZ0098,No.2023NSFSC0751);Open Project of Chengdu University of Information Technology(KYQN202317,760115027,KYTZ202278,KYTZ202280).

摘　　要：Unmanned aerial vehicle(UAV)paths in the field directly affect the efficiency and accuracy of payload data collection.Path planning of UAV advancing along river valleys in wild environments is one of the first and most difficult problems faced by unmanned surveys of debris flow valleys.This study proposes a new hybrid bat optimization algorithm,GRE-Bat(Good point set,Reverse learning,Elite Pool-Bat algorithm),for unmanned exploration path planning of debris flow sources in outdoor environments.In the GRE-Bat algorithm,the good point set strategy is adopted to evenly distribute the population,ensure sufficient coverage of the search space,and improve the stability of the convergence accuracy of the algorithm.Subsequently,a reverse learning strategy is introduced to increase the diversity of the population and improve the local stagnation problem of the algorithm.In addition,an Elite pool strategy is added to balance the replacement and learning behaviors of particles within the population based on elimination and local perturbation factors.To demonstrate the effectiveness of the GRE-Bat algorithm,we conducted multiple simulation experiments using benchmark test functions and digital terrain models.Compared to commonly used path planning algorithms such as the Bat Algorithm(BA)and the Improved Sparrow Search Algorithm(ISSA),the GRE-Bat algorithm can converge to the optimal value in different types of test functions and obtains a near-optimal solution after an average of 60 iterations.The GRE-Bat algorithm can obtain higher quality flight routes in the designated environment of unmanned investigation in the debris flow gully basin,demonstrating its potential for practical application.

关 键 词：Bat algorithm Unmanned surveys Debris flow gully Path planning Unmanned aerial vehicle Reverse learning 

分 类 号：P642.23[天文地球—工程地质学] TP18[天文地球—地质矿产勘探]