改进灰狼算法的移动充电机器人路径规划

Path planning of electric vehicle mobile charging robot based on improved gray wolf optimization algorithm

移动充电机器人的出现解决了老旧停车场内电动汽车充电的问题,但停车场内复杂与随机的障碍物环境对其路径规划与避障功能提出了更高的要求。通过对传统灰狼算法的改进,对停车场内的电动汽车移动充电机器人的路径规划问题进行了仿真与分析。灰狼算法迭代速度快,但优化精度低,且容易陷入局部最优,在对停车场地图进行栅格化处理后,从适应度函数、收敛因子以及位置更新函数3个方面对传统灰狼算法进行了改进,并利用MATLAB软件进行了仿真。结果表明改进灰狼算法的平均迭代次数较传统灰狼算法减少了39.4%,路径长度缩短了4.7%,在与其他典型改进灰狼算法对比中路径长度最短。对同一停车场不同车位占用率的移动充电机器人的路径规划利用该算法进行了仿真,结果表明该算法在随机地图与不同目标位置的情况下均可以成功运行,验证了算法的稳定性。

The emergence of mobile charging robots has solved the problem of charging electric vehicles in old parking lots,but the complex and random obstacle environment in parking lots puts forward higher requirements for their path planning and obstacle avoidance functions.The path planning problem of an electric vehicle mobile charging robot in a parking lot was simulated and analyzed by improving the traditional gray wolf optimization algorithm.The gray wolf optimization algorithm has fast iteration speed,but low optimization accuracy,and is prone to falling into local optima.After rasterizing the parking lot map,the traditional gray wolf optimization algorithm was improved from the perspective of fitness function,convergence factor and location update function.Simulation using MATLAB showed that the average iteration number of the improved gray wolf optimization algorithm was reduced by 39.4%compared to the traditional gray wolf optimization algorithm,and the path length was reduced by 4.7%,the path length was the shortest compared with other typical improved gray wolf optimization algorithm.At the same time,the path of mobile charging robots with different occupancy rates in the same parking lot was simulated using this algorithm,and the results showed that the algorithm can successfully run under random maps and different target locations,verifying the stability of the algorithm.