A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction

Smart sensors are an integral part of the Fourth Industrial Revolution and are widely used to add safety measures to human–robot interaction applications. With the advancement of machine learning methods in resource-constrained environments, smart sensor systems have become increasingly powerful. As...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Christoph Scholl, Andreas Tobola, Klaus Ludwig, Dario Zanca, Bjoern M. Eskofier
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	capacitive sensor system smart sensors human–robot interaction data quality signal processing embedded AI Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/e9774b2b930f4268b003853fbb14d4f4
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e9774b2b930f4268b003853fbb14d4f4
record_format	dspace
spelling	oai:doaj.org-article:e9774b2b930f4268b003853fbb14d4f42021-11-11T19:11:32ZA Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction10.3390/s212172101424-8220https://doaj.org/article/e9774b2b930f4268b003853fbb14d4f42021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7210https://doaj.org/toc/1424-8220Smart sensors are an integral part of the Fourth Industrial Revolution and are widely used to add safety measures to human–robot interaction applications. With the advancement of machine learning methods in resource-constrained environments, smart sensor systems have become increasingly powerful. As more data-driven approaches are deployed on the sensors, it is of growing importance to monitor data quality at all times of system operation. We introduce a smart capacitive sensor system with an embedded data quality monitoring algorithm to enhance the safety of human–robot interaction scenarios. The smart capacitive skin sensor is capable of detecting the distance and angle of objects nearby by utilizing consumer-grade sensor electronics. To further acknowledge the safety aspect of the sensor, a dedicated layer to monitor data quality in real-time is added to the embedded software of the sensor. Two learning algorithms are used to implement the sensor functionality: (1) a fully connected neural network to infer the position and angle of objects nearby and (2) a one-class SVM to account for the data quality assessment based on out-of-distribution detection. We show that the sensor performs well under normal operating conditions within a range of 200 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula> and also detects abnormal operating conditions in terms of poor data quality successfully. A mean absolute distance error of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>11.6</mn></mrow></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula> was achieved without data quality indication. The overall performance of the sensor system could be further improved to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7.5</mn></mrow></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula> by monitoring the data quality, adding an additional layer of safety for human–robot interaction.Christoph SchollAndreas TobolaKlaus LudwigDario ZancaBjoern M. EskofierMDPI AGarticlecapacitive sensor systemsmart sensorshuman–robot interactiondata qualitysignal processingembedded AIChemical technologyTP1-1185ENSensors, Vol 21, Iss 7210, p 7210 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	capacitive sensor system smart sensors human–robot interaction data quality signal processing embedded AI Chemical technology TP1-1185
spellingShingle	capacitive sensor system smart sensors human–robot interaction data quality signal processing embedded AI Chemical technology TP1-1185 Christoph Scholl Andreas Tobola Klaus Ludwig Dario Zanca Bjoern M. Eskofier A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction
description	Smart sensors are an integral part of the Fourth Industrial Revolution and are widely used to add safety measures to human–robot interaction applications. With the advancement of machine learning methods in resource-constrained environments, smart sensor systems have become increasingly powerful. As more data-driven approaches are deployed on the sensors, it is of growing importance to monitor data quality at all times of system operation. We introduce a smart capacitive sensor system with an embedded data quality monitoring algorithm to enhance the safety of human–robot interaction scenarios. The smart capacitive skin sensor is capable of detecting the distance and angle of objects nearby by utilizing consumer-grade sensor electronics. To further acknowledge the safety aspect of the sensor, a dedicated layer to monitor data quality in real-time is added to the embedded software of the sensor. Two learning algorithms are used to implement the sensor functionality: (1) a fully connected neural network to infer the position and angle of objects nearby and (2) a one-class SVM to account for the data quality assessment based on out-of-distribution detection. We show that the sensor performs well under normal operating conditions within a range of 200 <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula> and also detects abnormal operating conditions in terms of poor data quality successfully. A mean absolute distance error of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>11.6</mn></mrow></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula> was achieved without data quality indication. The overall performance of the sensor system could be further improved to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>7.5</mn></mrow></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula><inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mi mathvariant="normal">m</mi></semantics></math></inline-formula> by monitoring the data quality, adding an additional layer of safety for human–robot interaction.
format	article
author	Christoph Scholl Andreas Tobola Klaus Ludwig Dario Zanca Bjoern M. Eskofier
author_facet	Christoph Scholl Andreas Tobola Klaus Ludwig Dario Zanca Bjoern M. Eskofier
author_sort	Christoph Scholl
title	A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction
title_short	A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction
title_full	A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction
title_fullStr	A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction
title_full_unstemmed	A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction
title_sort	smart capacitive sensor skin with embedded data quality indication for enhanced safety in human–robot interaction
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/e9774b2b930f4268b003853fbb14d4f4
work_keys_str_mv	AT christophscholl asmartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT andreastobola asmartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT klausludwig asmartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT dariozanca asmartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT bjoernmeskofier asmartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT christophscholl smartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT andreastobola smartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT klausludwig smartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT dariozanca smartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction AT bjoernmeskofier smartcapacitivesensorskinwithembeddeddataqualityindicationforenhancedsafetyinhumanrobotinteraction
_version_	1718431618438266880

A Smart Capacitive Sensor Skin with Embedded Data Quality Indication for Enhanced Safety in Human–Robot Interaction

Ejemplares similares