In Situ Soil Property Estimation for Autonomous Earthmoving Using Physics-Infused Neural Networks

TL;DR

This paper introduces a physics-infused neural network (PINN) for in situ soil property estimation, enabling accurate force prediction in autonomous earthmoving by integrating physics models with learning-based methods.

Contribution

The paper presents a novel PINN approach that combines physics-based earthmoving models with neural networks for real-time soil property estimation.

Findings

Average force prediction error less than 2kN (13%)

Accurate soil parameter estimates even with model deviations

Validated using simulated earthmoving scenarios

Abstract

A novel, learning-based method for in situ estimation of soil properties using a physics-infused neural network (PINN) is presented. The network is trained to produce estimates of soil cohesion, angle of internal friction, soil-tool friction, soil failure angle, and residual depth of cut which are then passed through an earthmoving model based on the fundamental equation of earthmoving (FEE) to produce an estimated force. The network ingests a short history of kinematic observations along with past control commands and predicts interaction forces accurately with average error of less than 2kN, 13% of the measured force. To validate the approach, an earthmoving simulation of a bladed vehicle is developed using Vortex Studio, enabling comparison of the estimated parameters to pseudo-ground-truth values which is challenging in real-world experiments. The proposed approach is shown to enable accurate estimation of interaction forces and produces meaningful parameter estimates even when the model and the environmental physics deviate substantially.