Application of genetic algorithm on autonomous agents for virtual navigation in Unity3D

  • Jesús Iván Rubio-Sandoval Universidad Autónoma de Tamaulipas
  • Adolfo Josué Rodríguez-Rodríguez Universidad Autónoma de Tamaulipas
  • Jose Lázaro Martínez-Rodríguez Universidad Autonoma de Tamaulipas
  • David Tomás Vargas-Requena Universidad Autónoma de Tamaulipas
  • Juan Carlos Huerta-Mendoza Universidad Autónoma de Tamaulipas
  • Wenceslao Eduardo Rodríguez-Rodríguez Universidad Autónoma de Tamaulipas
Keywords: genetic algorithms, virtual environment, unity3D, autonomous navigation

Abstract

This paper presents a software implementation of genetic algorithms on autonomous agents that can navigate a virtual environment created in Unity3D to find an indicated destination. The fitness of the autonomous agents is calculated mainly through a proposed fitness function, which evaluates the performance to heuristically find a destination on three different scenarios with different difficulty and simulation parameters. Based on the obtained results, it is determined that the complexity of the scenarios, the established parameters, and the randomness of the algorithm affect the performance of individuals in finding their destination, but without the need to establish a map of predefined routes.

Published
2020-12-14
How to Cite
Rubio-Sandoval, J. I., Rodríguez-Rodríguez, A. J., Martínez-Rodríguez, J. L., Vargas-Requena, D. T., Huerta-Mendoza, J. C., & Rodríguez-Rodríguez, W. E. (2020). Application of genetic algorithm on autonomous agents for virtual navigation in Unity3D. International Journal of Combinatorial Optimization Problems and Informatics, 12(1), 9-20. Retrieved from https://ijcopi.org/ojs/article/view/200
Section
Articles