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

2025-06-12

AI Summary

This study addresses the challenges of modeling limb–granular medium interactions for robotic locomotion—namely, high computational cost, difficulty in capturing dynamic coupling, and poor long-term prediction accuracy. We propose an online predictive framework integrating dimensionality reduction, surrogate modeling, and data assimilation. Specifically, we introduce the first coupled application of sequential truncated higher-order singular value decomposition (ST-HOSVD), Gaussian process regression (GPR), and reduced-order particle filtering (RO-PF), enabling efficient, long-horizon prediction jointly driven by high-fidelity simulations and sparse experimental data. The method reduces computational time by several orders of magnitude; achieves prediction accuracy comparable to full-order simulations when using simulation-only data; and surpasses pure-simulation performance in long-term predictions after incorporating experimental measurements. Furthermore, it successfully recovers the physical scaling law governing peak resistive forces. This work establishes a novel, interpretable, and generalizable paradigm for dynamic modeling of robots operating in granular environments.

Technology Category

• Intelligent Robots: State Estimation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Predict robot-granular terrain interactions using data-driven modeling
• Reduce computational time versus physics-based simulations
• Enhance robot navigation in unknown complex terrains

Innovation

• Integration of dimension reduction and surrogate modeling
• Combines offline simulation with sparse experimental data
• Significantly reduces computational time versus simulations