High-speed off-road autonomy requires precise closed-loop control for a target vehicle while remaining robust across changing terrains. Recent forward kinodynamic (FKD) prediction foundation models suggest a promising path, starting from a generalist model and specializing it to the target platform. However, effective specialization remains challenging, as it often requires substantial real-world data, and models adapted to one setting can still overfit to specific terrains or driving regimes. \texttt{OptCar} (Optimized Car) presents a recipe for bridging the gap from generalist to specialist FKD models, preserving cross-terrain generalization while optimizing performance for a specific vehicle. \texttt{OptCar} introduces a history-conditioned dynamics adaptation module that encodes recent state-action observations into a dynamics context token, and then fine-tunes the generalist model using limited real-world data together with targeted synthetic rollouts from environment-specific system identification. In closed-loop model predictive control (MPC) experiments across three terrains and an out-of-distribution cart-pulling task, the largest gains appear at 6 m/s, the highest speed evaluated where slip dominates tracking error. On vegetation and dirt, the most slip-diverse terrain, \texttt{OptCar} reduces 6 m/s trajectory tracking error by roughly 55% relative to a fine-tuned AnyCar baseline and remains the most accurate even when an unseen cart payload changes the dynamics. With only 5 minutes of real data per terrain, \texttt{OptCar} is competitive on road with a specialist trained on 30 minutes of road data and substantially outperforms it once the terrain changes.
Blogger's Review: This study demonstrates the immense potential of adapting general models to specific environments in high-speed autonomy. With the history-conditioned dynamics adaptation module, \texttt{OptCar} effectively utilizes limited data, significantly improving tracking accuracy. Future research could explore maintaining this superior performance in more complex environments.