研究机器人路径规划问题,传统的遗传算法存在早熟收敛和收敛速度慢,影响路径规划的效率,针对移动机器人路径规划的难题,为了提高路径规划的效率,提出一种基于遗传模拟退火算法的移动机器人最优路径规划方法.应用简化编码长度的技术简化了工作路径编码方式,对于基于遗传算法产生初始路径种群后的各路径的适应值进行评价.经过多次交叉、变异,并借助模拟退火中Metropolis算法的随机移动准则制定了高效的温度更新函数,获得了从起始点到目标点的一条全局最优路径,并在MAlLAB环境中进行了仿真.仿真果证明算法的收敛速度、搜索质量和最优路径规划效率都有了明显的提高.%Premature and lower convergent speed is two puzzling problems in applying genetic algorithm, a genetically simulated annealing algorithm of optimum path planning for mobile robots is proposed. Changing of two - dimensional codes into one - dimensional codes is adopted to simplify the encoding path. An initialization population was produced based on genetic algorithm, and the fitness value of each path is evaluated. An efficient temperature updating function was devised through a series crossover and mutation. And by adopting the random moving rule of Metropolis algorithm, a global optimal path was obtained from the starting point to the target point. Finally, the feasibility and efficiency of this algorithm are verified in the Matlab environmen. The simulation results demonstrate that the proposed algorithm has achieved considerable improvements in convergence speed, search quality and the best path compared to the basic genetic algorithm.
展开▼
