TY - GEN
T1 - Dynamic Texture Decoding Using a Neuromorphic Multilayer Tactile Sensor
AU - Nguyen, Harrison
AU - Osborn, Luke
AU - Iskarous, Mark
AU - Shallal, Christopher
AU - Hunt, Christopher
AU - Betthauser, Joseph
AU - Thakor, Nitish
N1 - Funding Information:
This project was partially funded by Johns Hopkins Space Consortium through the Space@Hopkins funding initiative. The SRC and OMP algorithms are primarily based off of lectures from "Compressed Sensing and Sparse Recovery" at Johns Hopkins University taught by Dr. Trac Duy Tran.
Funding Information:
This project was partially funded by Johns Hopkins Space Consortium through the Space@Hopkins funding initiative. The SRC and OMP algorithms are primarily based off of lectures from “Compressed Sensing and Sparse Recovery” at Johns Hopkins University taught by Dr. Trac Duy Tran.
Publisher Copyright:
© 2018 IEEE.
PY - 2018/12/20
Y1 - 2018/12/20
N2 - Prosthetic limbs would benefit from tactile feedback to provide sensory information when interacting with the environment, such as adjusting grasps using force feedback or palpating texture. In this work, we demonstrate how a multilayer tactile sensor can be used for palpation, and enhance the ability to discriminate between touch interfaces. Inspired by mechanoreceptors in skin, the multilayer sensor consists of multiple textile force sensing elements. The novelty of this work lies in the application of a multilayer sensor, one that produces touch receptor like (neuromorphic) output, to texture classification by using a classifier based on sparse recovery. This approach is shown to be capable of palpation, achieving classification accuracies as high as 97% on a distinct texture set. Using compressed sensing and sparse recovery, the multilayer sensor can decode texture under dynamic conditions, potentially providing amputees the ability to perceive rich haptic information while using their prosthesis.
AB - Prosthetic limbs would benefit from tactile feedback to provide sensory information when interacting with the environment, such as adjusting grasps using force feedback or palpating texture. In this work, we demonstrate how a multilayer tactile sensor can be used for palpation, and enhance the ability to discriminate between touch interfaces. Inspired by mechanoreceptors in skin, the multilayer sensor consists of multiple textile force sensing elements. The novelty of this work lies in the application of a multilayer sensor, one that produces touch receptor like (neuromorphic) output, to texture classification by using a classifier based on sparse recovery. This approach is shown to be capable of palpation, achieving classification accuracies as high as 97% on a distinct texture set. Using compressed sensing and sparse recovery, the multilayer sensor can decode texture under dynamic conditions, potentially providing amputees the ability to perceive rich haptic information while using their prosthesis.
KW - Compressed Sensing Sparse Recovery
KW - Haptics
KW - Neuromorphic Model
KW - Supervised Learning
KW - Tactile Sensor
UR - http://www.scopus.com/inward/record.url?scp=85060881471&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85060881471&partnerID=8YFLogxK
U2 - 10.1109/BIOCAS.2018.8584826
DO - 10.1109/BIOCAS.2018.8584826
M3 - Conference contribution
AN - SCOPUS:85060881471
T3 - 2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Proceedings
BT - 2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE Biomedical Circuits and Systems Conference, BioCAS 2018
Y2 - 17 October 2018 through 19 October 2018
ER -