Data-Driven Prediction of Dynamic Interactions Between Robot Appendage and Granular Material

TL;DR

This paper introduces a data-driven modeling approach combining dimension reduction, surrogate modeling, and data assimilation to predict robot interaction with granular terrain efficiently and accurately, outperforming traditional physics-based simulations.

Contribution

The paper presents a novel integrated data-driven framework that significantly reduces computational time and improves long-horizon prediction accuracy for robot-terrain interactions.

Findings

Orders of magnitude reduction in computational time.

Comparable accuracy to high-fidelity simulations.

Potential to outperform simulations with sparse experimental data.

Abstract

An alternative data-driven modeling approach has been proposed and employed to gain fundamental insights into robot motion interaction with granular terrain at certain length scales. The approach is based on an integration of dimension reduction (Sequentially Truncated Higher-Order Singular Value Decomposition), surrogate modeling (Gaussian Process), and data assimilation techniques (Reduced Order Particle Filter). This approach can be used online and is based on offline data, obtained from the offline collection of high-fidelity simulation data and a set of sparse experimental data. The results have shown that orders of magnitude reduction in computational time can be obtained from the proposed data-driven modeling approach compared with physics-based high-fidelity simulations. With only simulation data as input, the data-driven prediction technique can generate predictions that have comparable accuracy as simulations. With both simulation data and sparse physical experimental measurement as input, the data-driven approach with its embedded data assimilation techniques has the potential in outperforming only high-fidelity simulations for the long-horizon predictions. In addition, it is demonstrated that the data-driven modeling approach can also reproduce the scaling relationship recovered by physics-based simulations for maximum resistive forces, which may indicate its general predictability beyond a case-by-case basis. The results are expected to help robot navigation and exploration in unknown and complex terrains during both online and offline phases.