武巍　邹杰

摘要：

针对传统教学优化（TLBO）算法进行航路规划时收敛速度慢、容易陷入局部最优的问题，提出一种自适应交叉教学优化（ACTLBO）算法。首先，该算法令传统教学优化（TLBO）算法的教学因子随着迭代次数而发生变化，提高算法的学习速度；其次，当算法可能要陷入局部最优时，加入一定的扰动，使算法尽可能地跳出局部最优；最后，为了进一步提升算法的收敛效果，在算法中引入遗传算法的交叉环节。利用传统教学优化（TLBO）算法、自适应交叉教学优化（ACTLBO）算法和量子粒子群优化（QPSO）算法进行无人机航路规划，仿真结果表明，在10次规划中，自适应交叉教学优化（ACTLBO）算法有8次找到了全局最优路径，而传统教学优化（TLBO）算法和量子粒子群优化（QPSO）算法分别只找到了2次和1次；而且自适应交叉教学优化（ACTLBO）算法的收敛速度高于另外两种算法。

关键词：

教学优化算法；无人机；航路规划；自适应交叉；局部最优；量子粒子群优化算法

中图分类号：

TP391.9

文献标志码：A

Abstract：

Aiming at the problem of slow convergence and being easy to fall into local optimum in the route planning of the traditional teachinglearningbased optimization algorithm， an adaptive crossover teachinglearningbased optimization algorithm was proposed. Firstly， the teaching factor of the algorithm was changed with the number of iterations， so the learning speed of the algorithm was improved. Secondly， when the algorithm was likely to fall into local optimum， a certain disturbance was added to make the algorithm jump out of local optimum as far as possible. Finally， in order to improve the convergence effect， the crossover link of genetic algorithm was introduced into the algorithm. Then the path planning of Unmanned Aerial Vehicle （UAV） was carried out by using the traditional teachinglearningbased optimization algorithm， the adaptive crossover teachinglearningbased optimization algorithm and the Quantum Particle Swarms Optimization （QPSO） algorithm. The simulation results show that in 10 times of planning， the adaptive crossover teachinglearningbased optimization algorithm finds the global optimal route for 8 times， while the traditional teachinglearningbased optimization algorithm and the QPSO algorithm find the route for only 2 times and 1 time respectively， and the convergence of the adaptive crossover teachinglearningbased optimization algorithm is faster than the other two algorithms.

英文关键词Key words：

teachinglearningbased optimization algorithm； Unmanned Aerial Vehicle （UAV）； route planning； adaptive crossover； local optimum； Quantum Particle Swarms Optimization （QPSO） algorithm

0引言

无人机（Unmanned Aerial Vehicle， UAV）为了完成侦查任务或者对目标进行打击，首先必须对执行任务的区域进行分析，预先规划出一条能够完成任务的航路。目前航路规划的方法有很多：文献[1]采用A*算法进行了无人机航路规划，A*算法易于实现，但是算法是采用节点扩展的方式进行搜索[2]，因此节点扩展方式不同，得到的航路也不同，所以可能会找不到最优路径；文献[3]利用遗传算法进行航路规划，算法从全局最优的角度进行计算，但是遗传算法需要对数据进行编码，实现起来比较困难；……