Simulation of the autonomous maze navigation using the NEAT algorithm

Ia.V. Omelianenko


The article deals with the problem of finding a solution for the navigational task of navigating a maze by an autonomous agent controlled by an artificial neural network (ANN). A solution to this problem was proposed by training the controlling ANN using the method of neuroevolution of augmenting topologies (NEAT).
A description of the mathematical apparatus for determining the goal-oriented objective function to measure fitness of the decision-making agent, suitable for optimizing the training of ANN in the process of neuroevolution, was given. Based on the invented objective function, a software was developed to control the neuroevolutionary process using the Python programming language.
A system for simulating the behavior of an autonomous robot that can navigate through a maze using input signals from various types of sensors has been created. The simulation system allows to imitate the behavior of a physical robot in a large number of experiments in a short time and with minimal expenses.
The experiments performed using the created simulation system to find the optimal values of hyperparameters, which can be used for successful training of the controlling ANN by the method of neuroevolution, are presented.
Additionally, the implemented new methods of visualizing the training process are described. These methods significantly simplify the search for optimal hyperparameters of the NEAT algorithm, due to the visual demonstration of the effect of changing one or another parameter on the training process.

Prombles in programming 2023; 4: 76-89


genetic algorithms; neuroevolution of augmenting topologies; autonomous maze navigation; NEAT; autonomous robot simulator


Jean-Baptiste Mouret and Stephane Doncieux. 2012. Encouraging behavioral diversity in evolutionary robotics: An empirical study. Evolutionary computation 20, 1 (2012), 91-133. CrossRef

Joel Lehman and Kenneth O Stanley. 2010. Revising the evolutionary computation abstraction: minimal criteria novelty search. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2010). ACM, 103-110. CrossRef

Joel Lehman and Kenneth O Stanley. 2011. Abandoning objectives: Evolution through the search for novelty alone. Evolutionary computation 19, 2 (2011), 189-223. CrossRef

Kenneth O Stanley and Risto Miikkulainen. 2002. Evolving neural networks through augmenting topologies. Evolutionary computation 10, 2 (2002), 99-127. CrossRef

Justin K Pugh, Lisa B Soros, and Kenneth O Stanley. 2016. Quality diversity: A new frontier for evolutionary computation. Frontiers in Robotics and AI 3 (2016), 40. CrossRef

Jonathan C. Brant and Kenneth O. Stanley. 2017. Minimal criterion coevolution: a new approach to open-ended search. In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO '17). Association for Computing Machinery, New York, NY, USA, 67-74.

Iaroslav Omelianenko. Hands-On Neuro-evolution with Python: Build high-performing artificial neural network architectures using neuroevolution-based algorithms. Birmingham, UK: Packt Publishing Ltd, 2019. ISBN: 9781838824914, 368 pp.

Iaroslav Omelianenko. Creation of Autonomous Artificial Intelligent Agents Using Novelty Search Method of Fitness Function Optimization. NewGround LLC, Sept. 2018,

Iaroslav Omelianenko. "Autonomous Artificial Intelligent Agents". In: Machine Learning and the City. John Wiley Sons, Ltd, 2022. Chap. 12, pp. 263-285. ISBN: 9781119815075, CrossRef

McIntyre, A., Kallada, M., Miguel, C. G., Feher de Silva, C., & Netto, M. L. neat-python,



  • There are currently no refbacks.