Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Interactive Identification of Granular Materials using Force Measurements

Samuli Hynninen, Tran Nguyen Le, Ville Kyrki

TL;DR

This work tackles granular material identification by enabling a robot to interact directly with loose materials and record force-torque feedback. It proposes an interactive perception pipeline consisting of exploration with a 6-axis F/T sensor, extraction of a combined raw-time-domain plus high-frequency magnitude histogram feature space, and ECOC-SVM classification to identify 11 materials with high accuracy. The authors provide a new real-world dataset of 682 samples, analyze force signal characteristics (magnitude, frequency content, dynamics), and demonstrate near-perfect identification performance using the proposed features. The results suggest that time-domain dynamics and high-frequency energy together capture essential material properties, offering a practical route for manipulation-informed material recognition and opening avenues for estimating material parameters like friction in robotic systems.

Abstract

Despite the potential the ability to identify granular materials creates for applications such as robotic cooking or earthmoving, granular material identification remains a challenging area, existing methods mostly relying on shaking the materials in closed containers. This work presents an interactive material identification framework that enables robots to identify a wide range of granular materials using only force-torque measurements. Unlike prior works, the proposed approach uses direct interaction with the materials. The approach is evaluated through experiments with a real-world dataset comprising 11 granular materials, which we also make publicly available. Results show that our method can identify a wide range of granular materials with near-perfect accuracy while relying solely on force measurements obtained from direct interaction. Further, our comprehensive data analysis and experiments show that a high-performancefeature space must combine features related to the force signal's time-domain dynamics and frequency spectrum. We account for this by proposing a combination of the raw signal and its high-frequency magnitude histogram as the suggested feature space representation. We show that the proposed feature space outperforms baselines by a significant margin. The code and data set are available at: https://irobotics.aalto.fi/identify_granular/.

Interactive Identification of Granular Materials using Force Measurements

TL;DR

This work tackles granular material identification by enabling a robot to interact directly with loose materials and record force-torque feedback. It proposes an interactive perception pipeline consisting of exploration with a 6-axis F/T sensor, extraction of a combined raw-time-domain plus high-frequency magnitude histogram feature space, and ECOC-SVM classification to identify 11 materials with high accuracy. The authors provide a new real-world dataset of 682 samples, analyze force signal characteristics (magnitude, frequency content, dynamics), and demonstrate near-perfect identification performance using the proposed features. The results suggest that time-domain dynamics and high-frequency energy together capture essential material properties, offering a practical route for manipulation-informed material recognition and opening avenues for estimating material parameters like friction in robotic systems.

Abstract

Despite the potential the ability to identify granular materials creates for applications such as robotic cooking or earthmoving, granular material identification remains a challenging area, existing methods mostly relying on shaking the materials in closed containers. This work presents an interactive material identification framework that enables robots to identify a wide range of granular materials using only force-torque measurements. Unlike prior works, the proposed approach uses direct interaction with the materials. The approach is evaluated through experiments with a real-world dataset comprising 11 granular materials, which we also make publicly available. Results show that our method can identify a wide range of granular materials with near-perfect accuracy while relying solely on force measurements obtained from direct interaction. Further, our comprehensive data analysis and experiments show that a high-performancefeature space must combine features related to the force signal's time-domain dynamics and frequency spectrum. We account for this by proposing a combination of the raw signal and its high-frequency magnitude histogram as the suggested feature space representation. We show that the proposed feature space outperforms baselines by a significant margin. The code and data set are available at: https://irobotics.aalto.fi/identify_granular/.
Paper Structure (17 sections, 4 equations, 4 figures, 1 table)

This paper contains 17 sections, 4 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related work
  3. Interactive perception with 6-axis F/T sensor
  4. Granular Material Identification
  5. Interactive Material Identification
  6. Exploration
  7. Feature Extraction
  8. Classification
  9. Dataset and qualitative data analysis
  10. Dataset collection
  11. Qualitative data analysis
  12. Signal magnitude
  13. Frequency content
  14. Signal dynamics
  15. Experiments and Results
  16. ...and 2 more sections

Figures (4)

  • Figure 1: To identify granular materials, we propose to interactively explore the material, recording interaction forces. The raw force measurements are then processed to identify meaningful features to classify the material.
  • Figure 2: Hardware setup and starting position
  • Figure 3: Materials and examples of their F/T measurements on the x- and z-axis, together with mean-variance plots (zoom in for a better view)
  • Figure 4: Confusion matrix for classification with raw + HFMH features on the test dataset.