利用自适应选择算子结合遗传算法的机器人路径规划方法

Robot motion planning based on adaptive selection operator combined with genetic algorithm

在二维复杂环境中,为了避免机器人运动规划中可能出现的局部陷阱和过早收敛问题,提出一种改进的元启发式算法--自适应遗传算法。首先,利用随机Dijkstra算法创建初始种群;然后,在遗传算法的每一代中,改进所创建的路径,并用自适应算子替代常规选择算子;最后,通过搜索过程中的反馈信息,可以令自适应选择算子在整个算法运行中恰当地控制选择压力。为了验证所提方法的有效性,在MATLAB中进行了仿真实验,并将所提方法与另外两种典型方法进行了对比。实验结果表明,提出的方法可以有效避免路径规划中的局部收敛问题,且在复杂环境中也可以产生可行路径。

In order to avoid local-trap and premature convergence of robot motion planning in 2 D complex environments,this paper proposed an improved metaheuristics-adaptive genetic algorithm( AGA). Firstly,it adopted the random Dijkstra algorithm to create initial population. Secondly,in each generation of the GA,it improved the created paths,and replaced the conventional selection operator in GA with an adaptive one. Finally,by using feedback information of the search process,the adaptive selection operator could control the selective pressure appropriately throughout the algorithm. To validate the effectiveness of the proposed method,it compared the algorithm with two other methods in MATLAB. The results show that the proposed method can avoid the local convergence problem in motion planning,and can generate feasible path in complex environments.