移动机器人势场跳点优化蚁群算法避障规划

Obstacle Avoidance Planning of Mobile Robot Based on PotentialField Jump Point Optimization Ant Colony Algorithm

随着智能控制技术研究的不断深入,移动机器人避障规划问题在智能制造领域得到广泛的应用。为了弥补蚁群算法(ACO)临过快收敛以及会造成局部最优的问题,引入势场跳点(PJP)对蚁群算法进行优化,更新补齐获得的最优路径全局信息素浓度,设计了一种基于势场跳点优化蚁群算法(PJPACO)的移动机器人避障规划。给出了PJPACO控制流程,并展开仿真和实验测试分析。仿真研究结果表明:以PJPACO算法形成更少路径转折点,具备更快收敛速度并且可以获得更优路径。通过试验验证发现,PJPACO算法获得了比ACO算法更短寻路时间,机器人可以达到更短行走路径,加入PJP算法后构建的ACO算法可以更高效规划机器人路径。该研究对提高移动机器人的工作效率具有很好的实际指导意义,可以拓宽到目标识别等领域。

With the development of intelligent control technology,mobile robot obstacle avoidance planning has been widely used in intelligent manufacturing.In order to make up for the problem of rapid convergence of ant colony(ACO)algorithm and local optimization,potential field jump points were introduced to optimize the ant colony algorithm,and the global pheromone concentration of the optimal path was updated and filled out.A mobile robot obstacle avoidance planning based on potential field jump point optimization ant Colony algorithm(PJPACO)was designed.The control flow of PJPACO is given,and simulation and experimental analysis are carried out.The simulation results show that the PJPACO algorithm has fewer path inflection points,faster convergence speed and better path.Through experimental verification,it is found that PJPACO algorithm can obtain a shorter path finding time than ACO algorithm,and the robot can achieve a shorter walking path.The ACO algorithm built after adding PJP algorithm can plan the robot path more efficiently.This research has a very good practical guiding significance for improving the work efficiency of mobile robots,and can be extended to target recognition and other fields.