改进粒子群算法和动态窗口法的动态路径规划

Dynamic Path Planning by Combing the Improved Particle Swarm Algorithm and Dynamic Window Approach

针对粒子群算法收敛速度慢、精度低以及只适用于静态环境等问题,提出改进粒子群-差分进化和动态窗口法的混合算法.首先利用差分进化算法改进粒子群算法寻优机制,对粒子群算法进行优化,构造新的适应度函数,实现对全局的路径规划;然后,根据生成的路径,提取关键中节点作为动态窗口法的局部目标点,采用动态窗口法进行局部路径规划,使起始航向角继承上一次到达局部目标点的航向角,生成从起始点到目标点的最短且平滑的路径.最后,将所提算法应用于不同试验场景进行路径规划仿真试验,并与现有算法进行对比分析,结果表明所提算法可行性强,具有更高的搜索能力.

Aiming at the problems of slow convergence speed,low accuracy,and only being suitable for the static environment of parti-cle swarm algorithm,this paper proposes a hybrid algorithm of improved particle swarm-differential evolution and dynamic window approach.First,the differential evolution algorithm is used to improve the optimization mechanism of the particle swarm algorithm,op-timize the particle swarm algorithm,construct a new fitness function,and realize the global path planning.Then,according to the gen-erated path,extract the key middle node as the dynamic window method for local target points.This paper uses the dynamic window approach for local path planning and makes the starting heading angle inherit the heading angle of the last time reaching the local target point,which can generate the shortest and smooth path from the starting point to the target point.Finally,the proposed algorithm is ap-plied to different test scenarios for path planning simulation tests and compared with existing algorithms.The results show that the pro-posed algorithm is more feasible and has higher search capabilities.