DEM中基于遗传与蚁群的混合路径规划算法

现有启发式算法在DEM路径规划中因数据量巨大，效率较低。针对该问题，提出一种基于遗传和蚁群的混合路径规划算法。该算法在遗传过程中，通过在初始群体生成阶段构建选择因子，使得在节点搜索时更加倾向于终点方向，提高初始群体生成效率；对变异过程中变异节点的变异区间进行限制，避免产生路径断点；在蚁群寻优过程中，根据遗传过程产生的路径信息，采用自适应信息素初始化与更新策略，提高算法搜索效率。测试结果表明，混合算法能够在规则网格DEM数据下搜索出符合条件的路径，并具有较好的效率。

Hybrid path planning algorithm based on genetics and ant colony in DEM

The existing heuristic algorithm has low efficiency in the DEM path planning because of the large amount of data. In order to solve this problem, this paper proposed a hybrid path planning algorithm based on genetic algorithm and ant colony algorithm. In the genetic process, the algorithm constructed the selection factor in the initial population generation stage, which made the searched node more incline to the end direction and improved the efficiency of the initial population generation. And the algorithm restricted the variation interval of the mutation node during the mutation process to avoid the path break point. In the ant colony optimization process, according to the path information generated by the genetic process, it adopted the adaptive pheromone initialization and updated strategies to improve the algorithm search efficiency. Simulation experiments show that the hybrid algorithm can search the qualified path efficiently under the rule grid DEM.