Implementation of Neural Networks for Car Navigation System Development in a 2D Car Game Simulation Using Genetic Algorithms
Article Sidebar
Main Article Content
Abstract
This study proposes the development of an autonomous car navigation system in a two-dimensional (2D)
car game simulation using Artificial Neural Networks (ANNs) optimized through Genetic Algorithms (GAs). The
objective of this research is to create an adaptive and intelligent navigation system capable of learning various track
conditions and avoiding obstacles effectively. In the proposed approach, neural networks are employed as decision-making
models based on sensor inputs, while genetic algorithms are used to optimize network weights through
evolutionary processes. Each generation consists of 20 autonomous cars, and their performance is evaluated using a
fitness function based on navigation accuracy, obstacle avoidance, and distance traveled along the track. The best-performing
individuals are selected and evolved to produce improved generations. Experimental results demonstrate
a significant improvement in navigation accuracy and adaptability across successive generations, particularly on tracks
with higher difficulty levels. The visualization of neural networks, sensors, and user interface components facilitates
performance monitoring and enhances the interpretability of decision-making processes. The Unity game engine is
utilized as the simulation platform, integrating GameObjects, a physics engine, and visualization tools to provide a
realistic and stable experimental environment. Overall, the results confirm that the integration of neural networks and
genetic algorithms is effective for developing adaptive and efficient autonomous vehicle navigation systems in 2D
game simulations.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
References
[1] E. Goh, O. Al-Tabbaa, and Z. Khan, “Unravelling the complexity of the Video Game Industry: An integrative framework and future research directions,” Telematics and Informatics Reports, vol. 12, Art. no. 100100, Dec. 2023, doi: 10.1016/j.teler.2023.100100.
[2] A. del Bosque, G. Lampropoulos, and D. Vergara, “The Role of Artificial Intelligence in Gaming,” Applied Sciences, vol. 15, no. 23, Art. no. 12358, 2025, doi: 10.3390/app152312358.
[3] H. A. Simon, “Artificial intelligence: an empirical science,” Artificial Intelligence, vol. 77, no. 1, pp. 95–127, Aug. 1995, doi: 10.1016/0004-3702(95)00039-H.
[4] J. Togelius and S. M. Lucas, “Evolving controllers for simulated car racing,” in Proc. 2005 IEEE Congress on Evolutionary Computation (CEC 2005), 2005, vol. 2, pp. 1906–1913, doi: 10.1109/CEC.2005.1554920.
[5] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.
[6] Y. Chen, C. Cheng, Y. Zhang, X. Li, and L. Sun, “A Neural Network-Based Navigation Approach for Autonomous Mobile Robot Systems,” Applied Sciences, vol. 12, no. 15, Art. no. 7796, 2022, doi: 10.3390/app12157796.
[7] R. Mahajan and G. Kaur, “Neural Networks using Genetic Algorithms,” International Journal of Computer Applications, vol. 77, no. 14, pp. 6–11, Sep. 2013, doi: 10.5120/13549-1153.
[8] L. R. Manangka, H. Suprijono, and D. Nurcipto, “Pengenalan Pola Lintasan Berbasis Neural Network Pada Prototype Self-Driving Car,” Elektrika, vol. 12, no. 2, pp. 67–72, 2020.
[9] R. Mahajan and G. Kaur, “Neural Networks Using Genetic Algorithms,” International Journal of Computer Applications, vol. 77, no. 14, pp. 6–11, 2013.
[10] J. H. Holland, Adaptation in Natural and Artificial Systems, Ann Arbor, MI, USA: University of Michigan Press, 1975.
[11] J. Togelius, S. M. Lucas, H. Richter, and J. H. Chiang, “Evolving Controllers for Simulated Car Racing,” in Proc. IEEE Congress on Evolutionary Computation (CEC), 2005, pp. 1906–1913.
[12] S. Arzt, “Neural Network Car Simulation Project,” GitHub Repository, 2020. [Online]. Available: https://github.com/samuelarzt
[13] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.
[14] S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed., Pearson, 2021.
[15] C. Bierwirth, “A Generalized Permutation Approach to Job Shop Scheduling with Genetic Algorithms,” OR Spectrum, vol. 17, no. 2–3, pp. 87–92, 1995.
[16] Y. Chen, C. Cheng, Y. Zhang, X. Li, and L. Sun, “A Neural Network-Based Navigation Approach for Autonomous Mobile Robot Systems,” Applied Sciences, vol. 12, no. 15, Art. no. 7796, 2022.