Evolving Neural Controllers for Xpilot-AI Racing Using Neuroevolution of Augmenting Topologies

TL;DR

This paper uses NEAT to evolve neural controllers for Xpilot-AI racing, achieving significant performance improvements and demonstrating NEAT's ability to develop effective strategies in complex simulated physics environments.

Contribution

It introduces a method for evolving neural controllers for Xpilot-AI racing using NEAT, showcasing improved performance and strategic behavior in a challenging physics-based simulation.

Findings

Controllers improved lap times by up to 32%

Evolved controllers developed human-like racing strategies

Demonstrated NEAT's effectiveness in complex physics environments

Abstract

This paper investigates the development of high-performance racing controllers for a newly implemented racing mode within the Xpilot-AI platform, utilizing the Neuro Evolution of Augmenting Topologies (NEAT) algorithm. By leveraging NEAT's capability to evolve both the structure and weights of neural networks, we develop adaptive controllers that can navigate complex circuits under the challenging space simulation physics of Xpilot-AI, which includes elements such as inertia, friction, and gravity. The racing mode we introduce supports flexible circuit designs and allows for the evaluation of multiple agents in parallel, enabling efficient controller optimization across generations. Experimental results demonstrate that our evolved controllers achieve up to 32% improvement in lap time compared to the controller's initial performance and develop effective racing strategies, such as optimal cornering and speed modulation, comparable to human-like techniques. This work illustrates NEAT's effectiveness in producing robust control strategies within demanding game environments and highlights Xpilot-AI's potential as a rigorous testbed for competitive AI controller evolution.