基于改进蚁群算法的泊车系统路径规划

Path Planning of Parking System Based on Improved Ant Colony Algorithm

针对智能立体车库中自动导引运输车（Automated Guided Vehicle,AGV）存取车路径规划问题,提出一种基于改进蚁群算法（IACO）的泊车系统路径规划方法。首先利用栅格法建立环境模型;其次,通过引入新的距离启发函数因子、调整状态转移概率和更改信息素更新规则对传统蚁群算法（TACO）进行优化改进;最后,在不同规格栅格环境下,以路径长度最短、算法收敛代数最小为评价指标,以传统蚁群算法和改进蚁群算法为搜索策略,运用Matlab对AGV存取车路径规划过程进行仿真测试,结果显示：AGV运用传统蚁群算法和改进蚁群算法均能有效避开障碍物,然后搜索到一条从起点到终点的无碰优化路径;与传统蚁群算法相比,改进蚁群算法规划的路径长度最短,开始收敛代数最小,表明改进算法正确、可行及有效,且具有较强的全局搜索能力和较好的收敛性能,能够满足AGV存取车路径规划要求。

Aiming at the path planning problem of AGV accessing cars in intelligent solid garages, the method of path planning of the parking system based on the improved ant colony algorithm is proposed. In the method, firstly, the grid method is utilized to create the working environment model of AGV. Secondly, the traditional ant colony algorithm is optimized through introducing a new distance heuristic function factor and update strategy of pheromone that includes the local updating and global updating of pheromone. Finally, under the different grid environments, the shortest path length and the minimum convergence algebra are used as evaluation indexes, the traditional ant colony algorithm and the improved ant colony algorithm are used as search strategy, the path planning process of AGV accessing cars is simulated with MATLAB software. The results show that the optimized path from the starting point to the end point could be obtained with the traditional ant colony algorithm and the improved ant colony algorithm on the premise of effectively avoiding obstacles. Moreover, the path length and the convergence algebra of the improved ant colony algorithm are optimal through being compared with the traditional ant colony algorithm. The results indicate that the improved ant colony algorithm is correct, feasible and effective, simultaneously exhibits stronger global search ability and better convergence performance, and can meet the requirement of AGV accessing cars in path planning.