Using Ants as a Genetic Crossover Operator in GLS to Solve STSP

TL;DR

This paper introduces a novel ant-based crossover operator integrated into a Genetic Local Search framework to improve solutions for the Symmetric Traveling Salesman Problem, combining ant colony principles with genetic algorithms.

Contribution

It proposes a new crossover operator inspired by ants and incorporates it into GLS for solving STSP, enhancing existing optimization techniques.

Findings

The ant-inspired crossover improves solution quality.

The integrated GLS outperforms traditional methods on benchmark STSP instances.

The approach demonstrates effective synergy between ant colony and genetic algorithms.

Abstract

Ant Colony Algorithm (ACA) and Genetic Local Search (GLS) are two optimization algorithms that have been successfully applied to the Traveling Salesman Problem (TSP). In this paper we define new crossover operator then redefine ACAs ants as operate according to defined crossover operator then put forward our GLS that uses these ants to solve Symmetric TSP (STSP) instances.