Neural Network Tire Force Modeling for Automated Drifting

TL;DR

This paper introduces a neural network-based tire force model for automated vehicle drifting, demonstrating improved path tracking over traditional models by capturing complex tire dynamics at friction limits.

Contribution

The paper presents a neural network architecture as a drop-in replacement for physics-based tire models in automated drifting control systems.

Findings

Neural network model outperforms brush tire model in path tracking

Model captures unmodeled tire dynamics during drifting

Enhanced control accuracy with neural network tire model

Abstract

Automated drifting presents a challenge problem for vehicle control, requiring models and control algorithms that can precisely handle nonlinear, coupled tire forces at the friction limits. We present a neural network architecture for predicting front tire lateral force as a drop-in replacement for physics-based approaches. With a full-scale automated vehicle purpose-built for the drifting application, we deploy these models in a nonlinear model predictive controller tuned for tracking a reference drifting trajectory, for direct comparisons of model performance. The neural network tire model exhibits significantly improved path tracking performance over the brush tire model in cases where front-axle braking force is applied, suggesting the neural network's ability to express previously unmodeled, latent dynamics in the drifting condition.