skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: SLURP! Spectroscopy of Liquids Using Robot Pre-Touch Sensing
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.  more » « less
Award ID(s):
1950811
PAR ID:
10442275
Author(s) / Creator(s):
; ; ; ; ; ;
Date Published:
Journal Name:
IEEE International Conference on Robotics and Automation
ISSN:
1049-3492
Page Range / eLocation ID:
3786-3792
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. (, EPJ Web of Conferences)
    Aguirre, M.A.; Luding, S.; Pugnaloni, L.A.; Soto, R. (Ed.)
    We have developed and employed a 3D particle stress tensor and contact force inference technique that employs synchrotron X-ray tomography and diffraction with an optimization algorithm. We have used this technique to study stress and force heterogeneity, particle fracture mechanics, contact-level energy dissipation, and the origin of wave phenomena in 3D granular media for the past five years. Here, we review the technique, describe experimental and numerical sources of uncertainty, and use experimental data and discrete element method simulations to study the method’s accuracy. We find that inferred forces in the strong force network of a 3D granular material are accurately determined even in the presence of noisy stress measurements. 
    more » « less
  2. ; ; ; ; ; ; ; ; (, IEEE Sensors Journal)
    Raman spectroscopy is a common identification and analysis technique used in research and manufacturing industries. This study investigates the use of Raman spectroscopy and deep learning techniques for identifying various nanofabrication chemicals. Four solvents and SU-8 developer were identified inside common chemical storage and distribution containers. The containers attenuated the spectra and contributed varying amounts of background fluorescence, making manual identification difficult. Two varieties of SU-8 photoresist were differentiated inside amber glass jars, and cured samples of three ratios of polydimethylsiloxane (PDMS) were differentiated using Raman microscopy. The neural network accurately identified the nanofabrication chemicals 100% of the time, without additional preprocessing. This investigation demonstrates the use of Raman spectroscopy and neural networks for the identification of nanofabrication chemicals and makes recommendations for use in other challenging identification applications. 
    more » « less
  3. ; ; (, 8th Annual Conference on Robot Learning)
    Legged robot locomotion on sand slopes is challenging due to the complex dynamics of granular media and how the lack of solid surfaces can hinder locomotion. A promising strategy, inspired by ghost crabs and other organisms in nature, is to strategically interact with rocks, debris, and other obstacles to facilitate movement. To provide legged robots with this ability, we present a novel approach that leverages avalanche dynamics to indirectly manipulate objects on a granular slope. We use a Vision Transformer (ViT) to process image representations of granular dynamics and robot excavation actions. The ViT predicts object movement, which we use to determine which leg excavation action to execute. We collect training data from 100 real physical trials and, at test time, deploy our trained model in novel settings. Experimental results suggest that our model can accurately predict object movements and achieve a success rate ≥ 80% in a variety of manipulation tasks with up to four obstacles, and can also generalize to objects with different physics properties. To our knowledge, this is the first paper to leverage granular media avalanche dynamics to indirectly manipulate objects on granular slopes. 
    more » « less
  4. ; ; ; ; ; ; ; (, Advanced Intelligent Systems)
    Skins with asymmetric kirigami scales and soft spikes are integrated to the surface of a base self‐burrowing robot, which consists of a soft one‐segment extending actuator. Friction anisotropy is observed at the interfaces between the burrowing robots and different granular materials. Its effects on the pulling resistance and burrowing characteristics are studied. The results demonstrate that the development of friction and friction anisotropy is affected by the characteristics of the granular material, the asymmetric skins, and the relative size of the asymmetric features to the granular particles. Robots with scales or spikes aligned along the upward direction burrow faster than those aligned against the upward direction, especially in relatively coarser granular materials. Particle image velocimetry analysis on the particle displacement fields around the actuator reveals the complexity of dry granular material interactions with soft robots, implying that aligned scales or spikes can impact the distribution of friction preferentially, opening up many possibilities for thoughtful material and geometry‐based manipulation of friction in the design and optimization of future soft burrowing robots for more versatile locomotion capabilities. 
    more » « less
  5. ; ; ; ; ; (, Optics Express)
    Brillouin spectrometers, used for characterizing material mechanical properties, traditionally employ etalons such as Fabry-Pérot interferometers and virtually imaged phased arrays (VIPA) that use spatial dispersion of the spectrum for measurement. Here, we introduce what we believe to be a novel approach to Brillouin spectroscopy using hot atomic vapors. Using laser induced circular dichroism of the rubidium D2 line in a ladder-type configuration, we developed a narrow-band monochromator for Brillouin analysis. Unlike etalon-based spectrometers, atomic line monochromators operate in free-space, facilitating Brillouin spectroscopy integration with microscopy instruments. We report the transmission and spectral resolution performances of the spectrometer and demonstrate Brillouin spectra measurements in liquids. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email