Task assignment method for unmanned vehicles based on k-means and discrete particle swarm optimization

Abstract

The invention discloses an unmanned vehicle task allocation method based on K-means and a discrete particle swarm algorithm. The invention discloses a multi-unmanned-vehicle task allocation method based on a means and discrete particle swarm optimization algorithm. The method comprises the following steps that S1, initializing logistics scene information; S2, performing logistics task packaging:using a k-means alothrigm to determine an optimal packaging result by using a means algorithm, wherein the packaging number is k; S3, taking k available unmanned vehicles, and matching the available unmanned vehicles with the execution unmanned vehicle of each task packet; and S4, determining a task sequence of each unmanned vehicle discrete particle swarm algorithm. According to the method, the clustering thought and the swarm intelligence optimization algorithm are combined to answer the task allocation problem of the multiple unmanned vehicles, the discrete particle swarm algorithm is used for task allocation of the multiple unmanned vehicles, the convergence speed of the particle swarm algorithm is high, and the algorithm is more suitable for an actual logistics scene through the discrete iteration mode. And using K-before using particle swarm optimization The tasks are packaged through the means clustering algorithm, the size of the understanding space is greatly reduced, and the task distribution efficiency is improved.

Description

technical field [0001] The invention relates to the field of logistics distribution optimization, in particular to a method for assigning tasks in the field of unmanned logistics. Background technique [0002] With the continuous expansion of the volume of the e-commerce industry and the continuous increase of labor costs, distribution, as the basic link of logistics operation, due to the continuous expansion of its coverage, more frequent data updates, increasingly heavy distribution tasks, and even "door-to-door" With the improvement of service requirements and the increasing popularity of smart logistics, China's logistics has opened the era of unmanned logistics. [0003] The storage efficiency of the unmanned warehouse can reach several times the storage efficiency of traditional beam racks. According to the statistics of an e-commerce logistics company, the sorting capacity of its unmanned sorting center can reach 9,000 pieces per hour, and the efficiency of the suppl...

AI Technical Summary

Problems solved by technology

At present, particle swarm algorithm, ant colony algorithm, simple scanning method, branch and bound method, simulated annealing algorithm, dynamic programming algorithm, etc. are mainly used in the allocation of multiple unmanned vehicles. However, these algorithms currently have certain shortcomings, mainly including: The fit of the actual logistics background is low, the convergence speed is slow, the solution result is not necessarily the optimal solution, and the calculation time is long, etc.

Images