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.

翻译：本文提出了一种基于物理融合神经网络（Physics-Infused Neural Network, PINN）的原位土壤特性智能估算方法。该网络经训练后输出土壤黏聚力、内摩擦角、土壤-机具摩擦角、土壤破坏角及残余切削深度等参数估计值，这些参数随后被输入基于土方工程基本方程（Fundamental Equation of Earthmoving, FEE）的土方作业模型，用于生成估算力。网络通过处理短时段的运动观测历史数据及过往控制指令，可精准预测交互作用力，平均误差低于2kN（占实测力的13%）。为验证该方法，基于Vortex Studio平台开发了铲刀式车辆土方作业仿真系统，实现了与真实实验中难以获取的伪基准参数进行对比。研究证明，该方法不仅能够实现交互作用力的高精度估算，即便在模型与环境物理特性存在显著偏差的情况下，仍能生成具有物理意义的参数估计值。