PIAug -- Physics Informed Augmentation for Learning Vehicle Dynamics for Off-Road Navigation

TL;DR

This paper introduces PIAug, a physics-informed data augmentation method that enhances neural network predictions of off-road vehicle dynamics, especially at high speeds and rare terrains, by leveraging nominal models during training.

Contribution

The paper proposes a novel physics-informed data augmentation technique, PIAug, to improve vehicle dynamics modeling in data-scarce high-speed and aggressive maneuver scenarios.

Findings

Up to 67% reduction in mean trajectory prediction error.

Successful real-world navigation with 4x tighter waypoint constraints.

Enhanced model performance during out-of-domain high-speed maneuvers.

Abstract

Modeling the precise dynamics of off-road vehicles is a complex yet essential task due to the challenging terrain they encounter and the need for optimal performance and safety. Recently, there has been a focus on integrating nominal physics-based models alongside data-driven neural networks using Physics Informed Neural Networks. These approaches often assume the availability of a well-distributed dataset; however, this assumption may not hold due to regions in the physical distribution that are hard to collect, such as high-speed motions and rare terrains. Therefore, we introduce a physics-informed data augmentation methodology called PIAug. We show an example use case of the same by modeling high-speed and aggressive motion predictions, given a dataset with only low-speed data. During the training phase, we leverage the nominal model for generating target domain (medium and high velocity) data using the available source data (low velocity). Subsequently, we employ a physics-inspired loss function with this augmented dataset to incorporate prior knowledge of physics into the neural network. Our methodology results in up to 67% less mean error in trajectory prediction in comparison to a standalone nominal model, especially during aggressive maneuvers at speeds outside the training domain. In real-life navigation experiments, our model succeeds in 4x tighter waypoint tracking constraints than the Kinematic Bicycle Model (KBM) at out-of-domain velocities.