Classification of Household Materials via Spectroscopy

TL;DR

This paper demonstrates that spectroscopy, combined with neural networks, enables accurate, contactless material recognition for robots, achieving over 94% accuracy on flat objects and practical application in home environments.

Contribution

The study introduces the use of spectrometers for robotic material recognition, showing their benefits and effectiveness compared to traditional haptic sensing methods.

Findings

Spectrometers provide fast, accurate, low-noise measurements for material recognition.

Neural networks can classify materials with 94.6% accuracy using spectral data.

The approach generalizes to new objects with 79.1% accuracy.

Abstract

Recognizing an object's material can inform a robot on the object's fragility or appropriate use. To estimate an object's material during manipulation, many prior works have explored the use of haptic sensing. In this paper, we explore a technique for robots to estimate the materials of objects using spectroscopy. We demonstrate that spectrometers provide several benefits for material recognition, including fast response times and accurate measurements with low noise. Furthermore, spectrometers do not require direct contact with an object. To explore this, we collected a dataset of spectral measurements from two commercially available spectrometers during which a robotic platform interacted with 50 flat material objects, and we show that a neural network model can accurately analyze these measurements. Due to the similarity between consecutive spectral measurements, our model achieved a material classification accuracy of 94.6% when given only one spectral sample per object. Similar to prior works with haptic sensors, we found that generalizing material recognition to new objects posed a greater challenge, for which we achieved an accuracy of 79.1% via leave-one-object-out cross-validation. Finally, we demonstrate how a PR2 robot can leverage spectrometers to estimate the materials of everyday objects found in the home. From this work, we find that spectroscopy poses a promising approach for material classification during robotic manipulation.