In-Situ Soil-Property Estimation and Bayesian Mapping with a Simulated Compact Track Loader

TL;DR

This paper presents a novel soil-property mapping system using a simulated compact track loader, combining physics-based modeling, neural networks, and Bayesian updates to enable soil-aware autonomous earthmoving in complex terrains.

Contribution

It introduces an integrated system that estimates soil properties in situ and maps them in real-time, extending autonomous earthmoving capabilities to unstructured environments.

Findings

Accurately identifies soil regions requiring higher interaction forces.

Successfully integrates physics-based models with neural networks for soil property prediction.

Demonstrates real-time Bayesian updating of soil maps in simulation.

Abstract

Existing earthmoving autonomy is largely confined to highly controlled and well-characterized environments due to the complexity of vehicle-terrain interaction dynamics and the partial observability of the terrain resulting from unknown and spatially varying soil conditions. In this chapter, a a soil-property mapping system is proposed to extend the environmental state, in order to overcome these restrictions and facilitate development of more robust autonomous earthmoving. A GPU accelerated elevation mapping system is extended to incorporate a blind mapping component which traces the movement of the blade through the terrain to displace and erode intersected soil, enabling separately tracking undisturbed and disturbed soil. Each interaction is approximated as a flat blade moving through a locally homogeneous soil, enabling modeling of cutting forces using the fundamental equation of earthmoving (FEE). Building upon our prior work on in situ soil-property estimation, a method is devised to extract approximate geometric parameters of the model given the uneven terrain, and an improved physics infused neural network (PINN) model is developed to predict soil properties and uncertainties of these estimates. A simulation of a compact track loader (CTL) with a blade attachment is used to collect data to train the PINN model. Post-training, the model is leveraged online by the mapping system to track soil property estimates spatially as separate layers in the map, with updates being performed in a Bayesian manner. Initial experiments show that the system accurately highlights regions requiring higher relative interaction forces, indicating the promise of this approach in enabling soil-aware planning for autonomous terrain shaping.