INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS AND DATA SCIENCE

Neuroevolutionary Control for Autonomous Racing in Continuous Action Spaces

1.lindsey wilson university

Published in issue

October 2026

Volume / Issue

Vol. 1 No. 5

Access

Open access

View PDF

The article details presented on this page reflect the published version of record. Readers may access the full-text PDF, review the citation information, and export the reference in supported citation formats.

Abstract

This paper applies Neuroevolution of Augmenting Topologies (NEAT) to learn control policies for autonomous racing in a simulated continuous action space. We evolve neural networks to optimize racing performance through a multi-stage experimental framework, evaluating their ability to learn steering, speed regulation, and trajectory planning. Results show that NEAT can discover near-optimal steering behaviors but struggles with simultaneous acceleration and positioning optimization, revealing challenges in evolving policies for complex multi-output control tasks. The study offers insights into fitness function design, state representation, and curriculum learning in neuroevolution for dynamic control applications.
Keywords:Continuous ControlAutonomous RacingNeuroevolutionNeural NetworksReinforcement LearningNeuroevolution of Augmenting Topologies (NEAT)

Cite this Article

Use the following citation when referencing this publication in academic or professional work.

S. Vangala, "Neuroevolutionary Control for Autonomous Racing in Continuous Action Spaces", Int. J. Intell. Syst. Data Sci., vol. 1, no. 5, Oct. 2026, doi: https://doi.org/10.67231/1jn9e149.

DOWNLOAD CITATION

Neuroevolutionary Control for Autonomous Racing in Continuous Action Spaces | International Journal of Intelligent Systems and Data Science