森林防火机器人轨迹寻踪技术研究

Research on Path Tracking Technology of Forest Fireproof Robot

蚁群算法是解决森林防火机器人轨迹寻踪问题的有效方法,针对传统蚁群算法收敛速度慢、容易陷入局部最优解的不足,本文设计一种自适应的蚁群算法。信息素启发因子α与期望启发因子β共同起引导蚂蚁搜索的作用,动态调整两者在搜索过程中的取值,提高收敛速度;基于地图位置信息设计改进型的启发式函数,提高前期搜索效率;依据蚂蚁的行进意图扩展禁忌表内容,避免路径交叉,减少蚂蚁的迷失数量;在信息素更新函数中导入转角指标,并通过信息素浓度对比试验确定权重系数的最优取值,使路径更平滑;基于Matlab平台搭建林区仿真地图,对比测试自适应蚁群算法性能。试验结果表明,自适应蚁群算法具有自适应调节能力、不会出现交叉路径,与传统蚁群算法相比,在收敛速度与搜索结果方面有着较好的改善。

Ant colony algorithm is an effective method to solve the problem of track tracking of forest fire protection robot. Aiming at the shortcomings of traditional ant colony algorithm, such as slow convergence speed and easy to fall into the local optimum, an adaptive ant colony algorithm is proposed in this paper to solve these problems. Pheromone heuristic factor α and expectation heuristic factor β work together to guide the ant search. To accelerate the convergence rate, the value of α and β in the search process is dynamically adjusted. The heuristic function based on the information of location is designed to improve the efficiency of early ant search. Based on ant’s intention, the tabu table is expanded to avoid path crossing and reduce the number of lost ants. The corner performance index is added to the update function of pheromone to smooth the search path, and the optimal value of the weight coefficient is determined by the contrast test of pheromone concentration. The simulation map of forest region is built based on Matlab, and the performance of adaptive ant colony algorithm is. Experimental results show that the algorithm has the ability of self-adaptive adjustment, and does not appear cross path. Compared with the traditional ant colony algorithm, the algorithm has better convergence speed and better search results.