PV powered neuromorphic sensors with optical connectivity

George-Iulian Uleru, Alexandru Barleanu, Mircea Hulea, Zabih Ghassemlooy

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


The spiking neural networks (SNN) benefits from low power consumption, very good signal-to-noise ratio and the ability to model rigorously the physiology of the biological neural areas. In robotics, the SNN can be used in different applications including motion control where the neural module drives the actuators based on the information from sensors. The most suitable type of sensing devices in biomimetic robotics are the neuromorphic sensors (NS) with spiking output which can include an optical transmitter for wireless connectivity. Considering that the reduced energy consumption is a critical characteristic for the SNN, in this work we evaluate the possibility of using photovoltaic (PV) panels to power the NS with optical output. The focus is on the recently introduced type of NS with integrated force sensing resistor (FSR) that uses a module based on a light emitting diode (LED) to generate optical pulses. We measured the responses of this NS with the load mass when it is powered by a PV panel, and the results show that the NS operates in nominal conditions despite the slight variations of the used supply voltage. Moreover, the NS is able to transmit optical pulses which frequency depends on the load mass.
Original languageEnglish
Title of host publication2024 7th International Balkan Conference on Communications and Networking (BalkanCom)
PublisherIEEE Canada
Number of pages5
ISBN (Electronic)9798350365955
ISBN (Print)9798350365962
Publication statusPublished - 3 Jun 2024
Event7th International Balkan Conference on Communications and Networking (BalkanCom) - Ljubljana, Slovenia
Duration: 3 Jun 20246 Jun 2024
Conference number: 7


Conference7th International Balkan Conference on Communications and Networking (BalkanCom)
Abbreviated titleBalkanCom

Cite this