Workshop AGV path planning method based on improved ant colony algorithm and dynamic window

Abstract

The invention discloses a workshop AGV path planning method based on an improved ant colony algorithm and a dynamic window, and the method comprises the steps: randomly placing m ants at n task points, and adding a dynamic inertia weight to guarantee the randomness of each ant; after the ants traverse all the task points once, calculating the length of a path passed by each ant and a corresponding fitness function, wherein a path corresponding to the minimum value of the fitness function is an optimal global path, obtaining a task point sequence according to the sequence of workshops passed by the ants in the optimal global path, and when working according to the task point sequence, if an obstacle is encountered and a workshop which is not reached exists, planning a local path for avoiding the obstacle in a global path working process by adopting a dynamic window method; according to the method, the planned repeated paths can be reduced when the number of task points is large, the improved ant colony algorithm enhances the capability of jumping out of the local extremum at the initial stage of the algorithm, finer search is carried out at the later stage of the algorithm, the path optimization capability is improved, and optimal global path planning is achieved.

Description

technical field [0001] The invention relates to an automatic guided vehicle (AGV) used for workshop distribution, in particular to a path planning method for an AGV trolley. Background technique [0002] Automatic Guided Vehicle (AGV), as a mobile robot with high degree of automation, good flexibility and strong anti-interference ability, is widely used in logistics and storage systems. When the workshop issues a distribution task, the AGV car needs to receive the task from the starting point, pass through the warehouses of each task point, and finally reach the target workshop. During the delivery process of the existing AGV trolley, there are many repeated paths and the problem of a long total path. With the popularization of AGV cars, there will be problems of path interference and collision when multiple AGVs work at the same time, which cannot fully reflect the intelligence of the AGV cars, resulting in low delivery efficiency of the cars. Therefore, the path planning ...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the shortcomings of the existing technology that the ant colony algorithm is easy to fall into local optimum and the AGV car encounters obstacles and stops delivery, and proposes a workshop AGV car path planning based on the improved ant colony algorithm and dynamic window The method can reduce repeated paths when there are many task points, improve path optimization capabilities, have higher optimization accuracy and stability, and improve operating efficiency

Images