Inverse Resistive Force Theory (I-RFT): Learning granular properties through robot-terrain physical interactions

TL;DR

This paper introduces I-RFT, a physics-informed machine learning framework that accurately estimates granular terrain properties from robot contact forces during natural locomotion, enhancing autonomous terrain exploration.

Contribution

The paper presents a novel integration of granular resistive force theory with Gaussian Processes to infer terrain properties from arbitrary gait trajectories, enabling generalization and physical consistency.

Findings

I-RFT accurately estimates terrain properties across diverse gait trajectories.

Quantified uncertainty helps optimize foot design and gait for better terrain exploration.

The approach enables data-efficient characterization of complex granular environments.

Abstract

For robots to navigate safely and efficiently on soft, granular terrains, it is crucial to gather information about the terrain's mechanical properties, which directly affect locomotion performance. Recent research has developed robotic legs that can accurately sense ground reaction forces during locomotion. However, existing tests of granular property estimation often rely on specific foot trajectories, such as vertical penetration or horizontal shear, limiting their applicability during natural locomotion. To address this limitation, we introduce a physics-informed machine learning framework, Inverse Resistive Force Theory (I-RFT), which integrates the Granular Resistive Force Theory model with Gaussian Processes to infer terrain properties from proprioceptively measured contact forces under arbitrary gait trajectories. By embedding the granular force model within the learning process, I-RFT preserves physical consistency while enabling generalization across diverse motion primitives. Experimental results demonstrate that I-RFT accurately estimates terrain properties across multiple gait trajectories and toe shapes. Moreover, we show that the quantified uncertainty over the terrain resistance stress map could enable robots to optimize foot design and gait trajectories for efficient information gathering. This approach establishes a new foundation for data-efficient characterization of complex granular environments and opens new avenues for locomotion strategies that actively adapt gait for autonomous terrain exploration.