无人机在边境勘测中的路径优化问题研究
A Study of the Path Optimisation Problem of Unmanned Aerial Vehicles in Border Survey

使用复合翼无人机实施边境勘测，已经成为部分边防部队边境勘测的重要手段。采用无人机进行边境勘测，极大提高了作业效率，实现高山、河流、雪地等恶劣艰苦环境的巡逻，尤其对担负新疆、西藏边防线上的巡逻任务来说，无人机代替分队巡逻、勘测具有重要意义。针对无人机对边防线上多个边境目标实施勘测时的路径优化问题，本文通过建立数学模型，在人工蜂群算法(Artificial Bee Colony Algorithm, ABC)、模拟退火算法(Simulated Annealing, SA)、遗传算法(Generation Algorithm, GA)、蚁群算法(Ant Colony Algorithm, ACA)等智能算法基础上进行优化，尝试采用头脑风暴优化算法(Brain Storm Optimization Algorithm, BSO)进行路径优化，并仿真实验求解，通过对求解结果、收敛度进行综合分析，得出BOS算法较其他算法收敛度较好，路径更优化，极大节省了巡逻时间、提高作业效率、为当前部分队采用无人机进行边境勘测的路径优化问题提供新方法。
The use of composite-winged drones to carry out border surveys has become an important means of border surveys for some border defence forces. The use of UAVs to carry out border surveys greatly improves operational efficiency and achieves the patrolling of harsh and difficult environments such as high mountains, rivers, snow, etc. Especially for patrolling tasks on the borderline of Xinjiang and Tibet, UAVs are of great significance, unlike detachment patrolling and surveying. This paper addresses the path optimization problem for unmanned aerial vehicles (UAVs) conducting surveys on multiple border targets along the border defense line. By establishing a mathematical model, we optimize the problem based on various intelligent algorithms, including the Artificial Bee Colony Algorithm (ABC), Simulated Annealing (SA), Genetic Algorithm (GA), and Ant Colony Algorithm (ACA). Additionally, we explore path optimization using the Brain Storm Optimization Algorithm (BSO) and conduct simulation experiments for problem-solving. Through a comprehensive analysis of the results and convergence performance, we find that the BSO algorithm demonstrates better convergence and more optimized paths compared to the other algorithms, significantly reducing patrol time and enhancing operational efficiency. This provides a new approach to the path optimization issue for UAVs used in border surveying in some current units.