A neural network based omni light sensor

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

The usage of optical distance-sensors is common in robotics research. These are usually based on photoresistors, photo-transistors or photo-diodes. This paper presents a novel design for a passive sensor configured as a 18 photo-resistors array. The device is designed to locate a light source in R3. In order to simplify the wiring task, we connect all photo-resistors to each other as the edges of an octahedron with an additional center node configuration. We then wire the peripheral pins to analog-digital-converters. The resulting resistance distribution is then analyzed using a dedicated neural network. We present the experimental process, its results and the sensor's accuracy.

Original languageEnglish
Title of host publication2017 13th IEEE International Conference on Control and Automation, ICCA 2017
PublisherIEEE Computer Society
Pages872-875
Number of pages4
ISBN (Electronic)9781538626795
DOIs
StatePublished - 4 Aug 2017
Event13th IEEE International Conference on Control and Automation, ICCA 2017 - Ohrid, Macedonia, The Former Yugoslav Republic of
Duration: 3 Jul 20176 Jul 2017

Publication series

NameIEEE International Conference on Control and Automation, ICCA
ISSN (Print)1948-3449
ISSN (Electronic)1948-3457

Conference

Conference13th IEEE International Conference on Control and Automation, ICCA 2017
Country/TerritoryMacedonia, The Former Yugoslav Republic of
CityOhrid
Period3/07/176/07/17

Fingerprint

Dive into the research topics of 'A neural network based omni light sensor'. Together they form a unique fingerprint.

Cite this