Coalition formation for Multi-agent Pursuit based on Neural Network and AGRMF Model

TL;DR

This paper introduces a neural network-based approach for forming coalitions in multi-agent pursuit, utilizing AGRMF and SOM to enhance group effectiveness and scalability in pursuit-evasion scenarios.

Contribution

It proposes AGRMF-ANN, a novel neural network combining feature extraction and group generation, with a new group attractiveness function to improve coalition formation.

Findings

Improves coalition formation effectiveness in pursuit scenarios.

Enhances scalability with larger pursuer teams.

Demonstrates better group quality evaluation.

Abstract

An approach for coalition formation of multi-agent pursuit based on neural network and AGRMF model is proposed.This paper constructs a novel neural work called AGRMF-ANN which consists of feature extraction part and group generation part. On one hand,The convolutional layers of feature extraction part can abstract the features of agent group role membership function(AGRMF) for all of the groups,on the other hand,those features will be fed to the group generation part based on self-organizing map(SOM) layer which is used to group the pursuers with similar features in the same group. Besides, we also come up the group attractiveness function(GAF) to evaluate the quality of groups and the pursuers contribution in order to adjust the main ability indicators of AGRMF and other weight of all neural network. The simulation experiment showed that this proposal can improve the effectiveness of coalition formation for multi-agent pursuit and ability to adopt pursuit-evasion problem with the scale of pursuer team growing.