🤖 AI Summary
This work addresses the challenge of achieving both physical consistency and strong nonlinear modeling capability in vehicle dynamics prediction under highly dynamic autonomous driving scenarios, where existing models often suffer from low accuracy and poor generalization. To overcome this limitation, the authors propose a hybrid vehicle dynamics model that integrates physical priors with data-driven learning. The approach embeds four key physical components—load-sensitive tire forces, longitudinal load transfer, lateral coupling effects, and actuator rate limits—into a neural network architecture constrained by physics. By combining the Pacejka tire model, end-to-end training, and fused simulation–real telemetry data, the method achieves significant improvements: displacement error is reduced by 16.1%–20.6%, yaw rate RMSE drops by 91.3%, inference speed increases by 1.5×, computational cost decreases by 21.6%, and closed-loop lap times improve by 9.5%–17.4% without any track excursions.
📝 Abstract
Accurate modeling of nonlinear vehicle dynamics is essential for high-speed autonomous racing, where controllers operate at the handling limits. Model-based methods are interpretable but rely on simplifying assumptions, while purely learned models capture nonlinearities yet often lack physical consistency and generalization. We propose LE-PAVD (Learning-Enhanced Physics-Aware Vehicle Dynamics), a hybrid model that integrates physics priors with learned components. Our architecture adds four components: load-sensitive Pacejka tire forces, longitudinal load transfer, lateral tire-force effects, and rate-limited actuator inputs. Trained end-to-end on simulation and real-world telemetry, LE-PAVD enforces physical consistency while improving state prediction accuracy. On an unseen track, LE-PAVD reduces average displacement error (ADE) by 16.1$\%$, final displacement error (FDE) by 20.6$\%$, and lowers yaw-rate root mean squared error (RMSE) by 91.3$\%$ versus a deep dynamics baseline, while using 21.6$\%$ fewer FLOPs and achieving approximately 1.50$\times$ faster inference. In closed-loop simulations, LE-PAVD consistently outperforms the baseline by achieving faster lap times by 17.4$\%$ on a training track and 9.5$\%$ on a test track, without any track boundary violations. Overall, LE-PAVD offers a compact, physics-grounded dynamics backbone that improves predictive fidelity and closed-loop performance while reducing inference cost.