Neural network based terramechanics modeling and estimation for deformable terrains

TL;DR

This paper introduces a neural network-based terramechanics model and terrain estimator that are efficient, differentiable, and accurate, enabling improved model predictive control on deformable terrains.

Contribution

It develops a novel neural network terramechanics model that is twice continuously differentiable and more accurate than existing models, suitable for control applications.

Findings

Neural network model predicts lateral tire forces accurately.

Terrain estimator converges within 2% of true parameters.

Using estimated terrain improves bicycle model predictions significantly.

Abstract

In this work, a neural network based terramechanics model and terrain estimator are presented with an outlook for optimal control applications such as model predictive control. Recognizing the limitations of the state-of-the-art terramechanics models in terms of operating conditions, computational cost, and continuous differentiability for gradient-based optimization, an efficient and twice continuously differentiable terramechanics model is developed using neural networks for dynamic operations on deformable terrains. It is demonstrated that the neural network terramechanics model is able to predict the lateral tire forces accurately and efficiently compared to the Soil Contact Model as a state-of-the-art model. Furthermore, the neural network terramechanics model is implemented within a terrain estimator and it is shown that using this model the estimator converges within around 2% of the true terrain parameter. Finally, with model predictive control applications in mind, which typically rely on bicycle models for their predictions, it is demonstrated that utilizing the estimated terrain parameter can reduce prediction errors of a bicycle model by orders of magnitude. The result is an efficient, dynamic, twice continuously differentiable terramechanics model and estimator that has inherent advantages for implementation in model predictive control as compared to previously established models.