多约束条件下基于改进遗传算法的移动机器人路径规划

针对在多约束条件下移动机器人在路径规划中搜索效率低、收敛速度慢的缺点,提出多约束条件下基于改进遗传算法的移动机器人路径规划,充分考虑路径长度、平滑度以及困难度这3种因素的影响,通过分析多约束条件下遗传算法在初始化种群时计算方法的不足,提出利用SPS(surrounding point set)算法,通过在障碍物周围生成点来产生初始路径,以提高算法快速生成初始种群的能力;增加平滑算子和删除算子,删除相对最终路径而言不必要的点,同时使路径更加平滑;结合小生境法以保持种群多样性,避免出现算法早熟现象.仿真结果表明,改进后的算法在路径长度,路径平滑度以及路径困难度方面均有一定的优势,同时算法的收敛速度也略有提高.

Path planning of mobile robot based on improved genetic algorithms under multiple constraints

Aiming at those disadvantages of low search efficiency and slow convergence speed of mobile robot in path planning under multiple constraints, a path planning of mobile robot based on improved genetic algorithm under multiple constraints is proposed, and the influence of path length, smoothness and difficulty are fully considered. Firstly, by analyzing the shortcomings of genetic algorithm in initializing population under multiple constraints, we propose surrounding point set(SPS) to generate the initial path by generating points around obstacles, so as to improve the ability of the algorithm to quickly generate initial population. Then, smoothing operator and deleting operator are added to delete unnecessary points relative to the final path and make the path smoother. Finally, the niche method is combined to maintain the diversity of population and avoid the phenomenon of prematurity. Compared with many algorithms, the experimental results show that the improved algorithm has certain advantages in path length, path smoothness and path difficulty, and the convergence speed of the algorithm is also slightly improved.