TRACK: Telemetry-Based Racing Analysis and Coaching Kit in Sim Racing Games

2026-10-07

AI Summary

This study addresses the absence of an objective quantitative framework for sim racing driving behavior by proposing an unsupervised analytical framework based on telemetry data. Methodologically, a reinforcement learning reference agent is employed for independent normalization, mapping driving sessions into compact geometric fingerprints within a four-dimensional behavioral space to replace predefined labels. By integrating multidimensional feature engineering with rigorously statistically calibrated clustering algorithms, the framework enables driver profiling and performance evaluation. Experiments conducted on the Assetto Corsa Gym dataset reveal that corner types implicitly encode distinct behavioral dimensions, while demonstrating that only speed and consistency remain transferable across different vehicle configurations. These findings establish a robust analytical foundation for personalized driving instruction in simulated environments.

Abstract

This paper presents TRACK (Telemetry-Based Racing Analysis and Coaching Kit), which is a framework for analyzing driving performance in sim racing and profiling how individual drivers behave behind the wheel. We report this framework together with its limitations: we calibrate each clustering result against a null, and when one does not separate from chance, we say so. Instead of restricting ourselves to scoring drivers or sorting them into preset labels, we represent each recording session as a compact geometry in a four-dimensional behavioral space (speed, braking, strategy, and consistency), and we group these fingerprints by their similarity using unsupervised clustering. Over time, we have developed and refined this framework on the open Assetto Corsa Gym (ACGym) dataset. Our study suggests that corner types differ along a behavioral dimension that was not used to define them. It also suggests that when the car changes, only speed and consistency carry over in the restricted population, while repeatability could not be shown there for any of the braking or strategy measures. Cluster separation becomes less distinct as the range of available telemetry widens. Until that repeatability is shown, grouping on the braking and strategy dimensions cannot treat the car as interchangeable, which divides an already small sample into smaller cells. It is also not clear whether a driver's grouping carries over from one corner type to the next. We also normalize each metric against a reinforcement-learning reference agent. The reference does not depend on the sample, so the scale does not shift when the sample does. We intend these results as an analytical foundation for a personalized improvement suggestion system. The sample is small. The cross-car result changes when the sample is defined more broadly. These outcomes are preliminary.

Problem

• sim racing
• driving performance analysis
• driver profiling
• telemetry
• behavioral repeatability

Innovation

• telemetry analysis
• unsupervised clustering
• behavioral fingerprinting
• reinforcement learning normalization
• sim racing