改进蚁群与势场融合算法的平滑路径规划

Improved Smooth Path Planning for Ant Colony and Potential Field Fusion Algorithm

针对不同环境下智能车辆路径搜索问题和传统蚁群算法收敛速度慢、容易陷入局部最优等情况,建立栅格地图模型,设计了一种改进蚁群与势场融合算法的平滑路径规划算法。在传统蚁群算法中引入了势场合力变化系数,与人工势场法相融合,减少了陷入局部最优的情形;引入自适应信息素调整策略和精英蚂蚁增加信息素提高算法收敛速度,保证了算法搜索时的有效性;对规划出的路径进行拐点处理使得路线更加平滑、安全。仿真结果显示:改进算法在稀疏障碍物下比文献[13]算法和基本蚁群算法提升了27.7%、81.1%;密集环境下分别提高36.9%、79.0%,并且路径长度与文献[13]相差很小,拐点数量也要小于其它两种算法,路线更加安全平滑。

Aiming at the problem of intelligent vehicle path search in different environments and the situation in that traditional ant colony algorithm converges slowly and is easy to fall into local optimum,a raster map model is established,and a smooth path planning algorithm is designed to improve the fusion algorithm of ant colony and potential field.In this paper,the change coefficient of the resultant force of the potential field is introduced into the traditional ant colony algorithm,which is combined with the artificial potential field method to reduce the situation of falling into the local optimum.Introducing an adaptive pheromone adjustment strategy and adding elite ants to the pheromone can improve the convergence speed of the algorithm and ensure the effectiveness of the algorithm in search.The inflection point processing of the planned path makes the route smoother and safer.The simulation results show that the improved algorithm in this paper improves by 27.7%and 81.1%compared with the algorithm in literature[13]and the basic ant colony algorithm under sparse obstacles.In the dense environment,the increase is 36.9%and 79.0%respectively.In addition,the difference between the path length and the literature[13]is very small,and the number of inflection points is also smaller than the other two algorithms,so the route is safer and smoothing.