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

2025-07-29

AI Summary

Existing autonomous earthmoving systems exhibit insufficient robustness in complex, unknown, and spatially heterogeneous soil environments—primarily due to partial observability of terrain geometry and challenges in modeling vehicle–soil interactions. This paper proposes a soil-aware framework integrating blind-spot mapping with an improved physics-informed neural network (PINN). Leveraging GPU-accelerated elevation mapping and tool–terrain interaction modeling, the framework predicts cutting forces under a local homogeneity assumption, enabling joint estimation and Bayesian updating of disturbed and undisturbed soil states within a hierarchical architecture. Its key innovation lies in the first integration of PINNs into an autonomous planning closed loop, explicitly encoding soil mechanical constraints and producing uncertainty-quantified soil property estimates. Experimental results demonstrate accurate identification of high-resistance zones and significantly improved adaptability and reliability in terrain shaping within simulation environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Estimating soil properties in real-time for autonomous earthmoving
• Mapping disturbed and undisturbed soil layers using Bayesian updates
• Developing a physics-infused neural network for soil property prediction

Innovation

• GPU accelerated elevation mapping system
• Physics infused neural network (PINN) model
• Bayesian soil property tracking