SLURP! Spectroscopy of Liquids Using Robot Pre-Touch Sensing

TL;DR

This paper introduces a robotic sensing method using VNIR spectroscopy to accurately identify liquids and container materials inside unknown containers, enabling robots to perceive contents without opening them.

Contribution

The work presents a hierarchical spectral inference model trained on a new dataset, achieving high accuracy in identifying liquids and container materials.

Findings

Over 85% accuracy in liquid identification

96% accuracy in container material detection

Dataset of spectral measurements from 180+ container-liquid combinations

Abstract

Liquids and granular media are pervasive throughout human environments. Their free-flowing nature causes people to constrain them into containers. We do so with thousands of different types of containers made out of different materials with varying sizes, shapes, and colors. In this work, we present a state-of-the-art sensing technique for robots to perceive what liquid is inside of an unknown container. We do so by integrating Visible to Near Infrared (VNIR) reflectance spectroscopy into a robot's end effector. We introduce a hierarchical model for inferring the material classes of both containers and internal contents given spectral measurements from two integrated spectrometers. To train these inference models, we capture and open source a dataset of spectral measurements from over 180 different combinations of containers and liquids. Our technique demonstrates over 85% accuracy in identifying 13 different liquids and granular media contained within 13 different containers. The sensitivity of our spectral readings allow our model to also identify the material composition of the containers themselves with 96% accuracy. Overall, VNIR spectroscopy presents a promising method to give household robots a general-purpose ability to infer the liquids inside of containers, without needing to open or manipulate the containers.