Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A multi-robot task assignment method for intelligent storage system

A multi-robot, task allocation technology, applied in the fields of instruments, genetic laws, data processing applications, etc., can solve the problems of difficult selection of linear combination weights, low actual efficiency, and unbalanced task allocation of robots, so as to achieve the problem of system task allocation, improve The effect of science and rationality

Active Publication Date: 2022-04-22
HOHAI UNIV CHANGZHOU
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, most of the multi-robot system task allocation algorithms take the minimization of the total path of the multi-robot system as the primary goal, which leads to the unbalanced task allocation of each robot, and finally leads to some robots waiting for a long time for a robot to return during sorting. In the case of the actual low efficiency
There is also a Single-Function-Optimization (SFO) algorithm whose primary goal is to minimize the linear combination of the variance of the multi-robot system and the total path of the multi-robot system. As a result, the shortcomings of time cost and energy cost cannot be taken into account at the same time

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A multi-robot task assignment method for intelligent storage system
  • A multi-robot task assignment method for intelligent storage system
  • A multi-robot task assignment method for intelligent storage system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0086] It can be seen from Table 3 that as the number of robots increases, the total path length of the robot group increases and the average path decreases, but the maximum travel time of the traditional multi-robot task allocation algorithm is much higher than that of the task allocation algorithm proposed by the present invention (improved -NSGA-II), and the total path of the SFO algorithm is much higher than the first two, and the time cost and energy consumption cost are far inferior to the improved genetic algorithm proposed by the present invention.

[0087] The statistical results of the algorithm in the test data set are as follows:

[0088] Table 3 Performance of improved-NSGA-II algorithm in each data set

[0089]

[0090] figure 2 and image 3 Respectively represent the algorithm of the present invention and the SFO algorithm, the comparison diagram of the energy consumption cost and the time cost of the conventional multi-robot task allocation algorithm, it ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a multi-robot task assignment method for an intelligent storage system. According to the intelligent storage task assignment problem, a multi-objective task assignment model is established, and a time cost function and an energy consumption cost function are designed; A multi-objective genetic algorithm for non-dominated sorting; and a new iterative process is added to the framework of the above-mentioned genetic algorithm to ensure that it can further converge to a better non-dominated solution. The invention obtains a better non-dominated solution by sorting the dominance levels of each optimization component, and improves the probability that the algorithm converges to a better non-dominated solution through population restart and an elite pool mechanism. And at the same time, the present invention takes into account the time cost and energy consumption cost of the multi-robot system in the task allocation problem of the multi-robot system, can solve the task allocation problem in the multi-robot system more systematically, and improve the scientificity and rationality of the task allocation results.

Description

technical field [0001] The invention relates to a multi-robot task assignment method for an intelligent storage system, which belongs to the field of intelligent storage robot control. Background technique [0002] The sorting and transportation of goods is an important part of the intelligent storage system and an important part of the future social Internet of Things system. For the future intelligent warehousing system, the multi-robot system can effectively improve the efficiency of goods sorting and reduce the time of package handling through collaboration. However, multi-robot systems working in the same space are prone to task interference and conflicts, which can lead to problems such as deadlocks. Therefore, the task distribution of multi-robot system is an important part of intelligent storage system. [0003] At present, most of the multi-robot system task allocation algorithms take the minimization of the total path of the multi-robot system as the primary goal...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06Q10/06G06Q10/04G06N3/12
CPCG06Q10/06311G06Q10/047G06N3/126
Inventor 魏长赟蔡帛良张鹏鹏倪福生蒋爽顾磊李洪彬刘增辉
Owner HOHAI UNIV CHANGZHOU
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products