Deep Dynamics: Vehicle Dynamics Modeling with a Physics-Constrained Neural Network for Autonomous Racing
This addresses the problem of precise and efficient vehicle modeling for autonomous racing, where errors can be severe, but it is incremental as it builds on hybrid physics-data methods.
The paper tackled vehicle dynamics modeling for autonomous racing by introducing Deep Dynamics, a physics-constrained neural network that predicts vehicle states at high speeds (>280 km/h) with improved accuracy and computational efficiency, as validated through simulator and real racecar data.
Autonomous racing is a critical research area for autonomous driving, presenting significant challenges in vehicle dynamics modeling, such as balancing model precision and computational efficiency at high speeds (>280km/h), where minor errors in modeling have severe consequences. Existing physics-based models for vehicle dynamics require elaborate testing setups and tuning, which are hard to implement, time-intensive, and cost-prohibitive. Conversely, purely data-driven approaches do not generalize well and cannot adequately ensure physical constraints on predictions. This paper introduces Deep Dynamics, a physics-constrained neural network (PCNN) for vehicle dynamics modeling of an autonomous racecar. It combines physics coefficient estimation and dynamical equations to accurately predict vehicle states at high speeds and includes a unique Physics Guard layer to ensure internal coefficient estimates remain within their nominal physical ranges. Open-loop and closed-loop performance assessments, using a physics-based simulator and full-scale autonomous Indy racecar data, highlight Deep Dynamics as a promising approach for modeling racecar vehicle dynamics.