A Novel Whisker Sensor Used for 3D Contact Point Determination and Contour Extraction

Hannah Emnett, Matthew M. Graff, Mitra J Z Hartmann

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We developed a novel whisker-follicle sensor that measures three mechanical signals at the whisker base. The first two signals are closely related to the two bending moments, and the third is an approximation to the axial force. Previous simulation studies have shown that these three signals are sufficient to determine the three-dimensional (3D) location at which the whisker makes contact with an object. Here we demonstrate hardware implementation of 3D contact point determination and then use continuous sweeps of the whisker to show proof-of principle 3D contour extraction. We begin by using simulations to confirm the uniqueness of the mapping between the mechanical signals at the whisker base and the 3D contact point location for the specific dimensions of the hardware whisker. Multi-output random forest regression is then used to predict the contact point locations of objects based on observed mechanical signals. When calibrated to the simulated data, signals from the hardware whisker can correctly predict contact point locations to within 1.5 cm about 74% of the time. However, if normalized output voltages from the hardware whiskers are used to train the algorithm (without calibrating to simulation), predictions improve to within 1.5 cm for about 96% of contact points and to within 0.6 cm for about 78% of contact points. This improvement suggests that as long as three appropriate predictor signals are chosen, calibrating to simulations may not be required. The sensor was next used to perform contour extraction on a cylinder and a cone. We show that basic contour extraction can be obtained with just two sweeps of the sensor. With further sweeps, it is expected that full 3D shape reconstruction could be achieved.
Original languageEnglish (US)
Title of host publicationProceedings of Robotics
Subtitle of host publicationScience and Systems XIV
EditorsHadas Kress-Gazit, Siddhartha Srinivasa, Tom Howard, Nikolay Atanasov
Number of pages10
DOIs
StatePublished - 2018

Fingerprint

Crystal whiskers
Point contacts
Sensors
Hardware
Bending moments
Cones
Electric potential

Cite this

Emnett, H., Graff, M. M., & Hartmann, M. J. Z. (2018). A Novel Whisker Sensor Used for 3D Contact Point Determination and Contour Extraction. In H. Kress-Gazit, S. Srinivasa, T. Howard, & N. Atanasov (Eds.), Proceedings of Robotics: Science and Systems XIV https://doi.org/10.15607/RSS.2018.XIV.059
Emnett, Hannah ; Graff, Matthew M. ; Hartmann, Mitra J Z. / A Novel Whisker Sensor Used for 3D Contact Point Determination and Contour Extraction. Proceedings of Robotics: Science and Systems XIV. editor / Hadas Kress-Gazit ; Siddhartha Srinivasa ; Tom Howard ; Nikolay Atanasov. 2018.
@inproceedings{c002133711b342309a70e7fdce58ba91,
title = "A Novel Whisker Sensor Used for 3D Contact Point Determination and Contour Extraction",
abstract = "We developed a novel whisker-follicle sensor that measures three mechanical signals at the whisker base. The first two signals are closely related to the two bending moments, and the third is an approximation to the axial force. Previous simulation studies have shown that these three signals are sufficient to determine the three-dimensional (3D) location at which the whisker makes contact with an object. Here we demonstrate hardware implementation of 3D contact point determination and then use continuous sweeps of the whisker to show proof-of principle 3D contour extraction. We begin by using simulations to confirm the uniqueness of the mapping between the mechanical signals at the whisker base and the 3D contact point location for the specific dimensions of the hardware whisker. Multi-output random forest regression is then used to predict the contact point locations of objects based on observed mechanical signals. When calibrated to the simulated data, signals from the hardware whisker can correctly predict contact point locations to within 1.5 cm about 74{\%} of the time. However, if normalized output voltages from the hardware whiskers are used to train the algorithm (without calibrating to simulation), predictions improve to within 1.5 cm for about 96{\%} of contact points and to within 0.6 cm for about 78{\%} of contact points. This improvement suggests that as long as three appropriate predictor signals are chosen, calibrating to simulations may not be required. The sensor was next used to perform contour extraction on a cylinder and a cone. We show that basic contour extraction can be obtained with just two sweeps of the sensor. With further sweeps, it is expected that full 3D shape reconstruction could be achieved.",
author = "Hannah Emnett and Graff, {Matthew M.} and Hartmann, {Mitra J Z}",
note = "http://www.roboticsproceedings.org/rss14/p59.pdf",
year = "2018",
doi = "10.15607/RSS.2018.XIV.059",
language = "English (US)",
isbn = "978-0992374747",
editor = "Hadas Kress-Gazit and Siddhartha Srinivasa and Tom Howard and Nikolay Atanasov",
booktitle = "Proceedings of Robotics",

}

Emnett, H, Graff, MM & Hartmann, MJZ 2018, A Novel Whisker Sensor Used for 3D Contact Point Determination and Contour Extraction. in H Kress-Gazit, S Srinivasa, T Howard & N Atanasov (eds), Proceedings of Robotics: Science and Systems XIV. https://doi.org/10.15607/RSS.2018.XIV.059

A Novel Whisker Sensor Used for 3D Contact Point Determination and Contour Extraction. / Emnett, Hannah; Graff, Matthew M.; Hartmann, Mitra J Z.

Proceedings of Robotics: Science and Systems XIV. ed. / Hadas Kress-Gazit; Siddhartha Srinivasa; Tom Howard; Nikolay Atanasov. 2018.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A Novel Whisker Sensor Used for 3D Contact Point Determination and Contour Extraction

AU - Emnett, Hannah

AU - Graff, Matthew M.

AU - Hartmann, Mitra J Z

N1 - http://www.roboticsproceedings.org/rss14/p59.pdf

PY - 2018

Y1 - 2018

N2 - We developed a novel whisker-follicle sensor that measures three mechanical signals at the whisker base. The first two signals are closely related to the two bending moments, and the third is an approximation to the axial force. Previous simulation studies have shown that these three signals are sufficient to determine the three-dimensional (3D) location at which the whisker makes contact with an object. Here we demonstrate hardware implementation of 3D contact point determination and then use continuous sweeps of the whisker to show proof-of principle 3D contour extraction. We begin by using simulations to confirm the uniqueness of the mapping between the mechanical signals at the whisker base and the 3D contact point location for the specific dimensions of the hardware whisker. Multi-output random forest regression is then used to predict the contact point locations of objects based on observed mechanical signals. When calibrated to the simulated data, signals from the hardware whisker can correctly predict contact point locations to within 1.5 cm about 74% of the time. However, if normalized output voltages from the hardware whiskers are used to train the algorithm (without calibrating to simulation), predictions improve to within 1.5 cm for about 96% of contact points and to within 0.6 cm for about 78% of contact points. This improvement suggests that as long as three appropriate predictor signals are chosen, calibrating to simulations may not be required. The sensor was next used to perform contour extraction on a cylinder and a cone. We show that basic contour extraction can be obtained with just two sweeps of the sensor. With further sweeps, it is expected that full 3D shape reconstruction could be achieved.

AB - We developed a novel whisker-follicle sensor that measures three mechanical signals at the whisker base. The first two signals are closely related to the two bending moments, and the third is an approximation to the axial force. Previous simulation studies have shown that these three signals are sufficient to determine the three-dimensional (3D) location at which the whisker makes contact with an object. Here we demonstrate hardware implementation of 3D contact point determination and then use continuous sweeps of the whisker to show proof-of principle 3D contour extraction. We begin by using simulations to confirm the uniqueness of the mapping between the mechanical signals at the whisker base and the 3D contact point location for the specific dimensions of the hardware whisker. Multi-output random forest regression is then used to predict the contact point locations of objects based on observed mechanical signals. When calibrated to the simulated data, signals from the hardware whisker can correctly predict contact point locations to within 1.5 cm about 74% of the time. However, if normalized output voltages from the hardware whiskers are used to train the algorithm (without calibrating to simulation), predictions improve to within 1.5 cm for about 96% of contact points and to within 0.6 cm for about 78% of contact points. This improvement suggests that as long as three appropriate predictor signals are chosen, calibrating to simulations may not be required. The sensor was next used to perform contour extraction on a cylinder and a cone. We show that basic contour extraction can be obtained with just two sweeps of the sensor. With further sweeps, it is expected that full 3D shape reconstruction could be achieved.

U2 - 10.15607/RSS.2018.XIV.059

DO - 10.15607/RSS.2018.XIV.059

M3 - Conference contribution

SN - 978-0992374747

BT - Proceedings of Robotics

A2 - Kress-Gazit, Hadas

A2 - Srinivasa, Siddhartha

A2 - Howard, Tom

A2 - Atanasov, Nikolay

ER -

Emnett H, Graff MM, Hartmann MJZ. A Novel Whisker Sensor Used for 3D Contact Point Determination and Contour Extraction. In Kress-Gazit H, Srinivasa S, Howard T, Atanasov N, editors, Proceedings of Robotics: Science and Systems XIV. 2018 https://doi.org/10.15607/RSS.2018.XIV.059