Mistry, Vivek (University of York), Smith, William (University of York)

AutoF1: An RNN-Based Approach to Simulating Strategic Decision-Making in Formula 1

Scheduled for presentation during the Video Session "On-Demand Video Presentations" (VP-VP), Saturday, November 22, 2025, 08:00−18:00, On-Demand Platform

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on April 2, 2026

Abstract

This paper addresses the challenges of providing real-time decision support for Formula One strategy engineers concerning car setup and tyre changes through the development of an AI-driven simulation tool. We investigate this by applying machine learning techniques, specifically recurrent neural networks, to historical race data obtained via the FastF1 Python library. This research demonstrates the process of structuring detailed race data for neural network training to build a simulation model capable of predicting race outcomes and aiding strategic decisions. The evaluation showed the simulation model’s performance against historical races and illustrated its application through case studies simulating alternative strategies, which show efficient simulation capabilities. Finally, we explore future directions for enhancing the model’s granularity and exploring advanced architectures were discussed.