4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System

Autores
Pirozzo, Bernardo; Roark, Geraldina; Ruschetti, Cristian; Villar, Sebastián; De Paula, Mariano; Acosta, Gerardo G.
Año de publicación
2025
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Unmanned Aerial Vehicles (UAVs) are versatile platforms with potential applications in precision agriculture, disaster management, and more. A core need across these applications is a navigation system that accurately estimates location based on environmental perception. Commercial UAVs use multiple onboard sensors whose fused data improves localization accuracy. The bioinspired Rat-Simultaneous Localization and Mapping (Rat-SLAM) system, is a promising alternative to beexplored to tackle the localization and mapping problem of UAVs. Its cognitive capabilities, semi-metric map construction, and loop closure make it attractive for localization in complex environments. This work presents an improved Rat-SLAM algorithm for UAVs, focusing on three innovations. First, Spiking Neural Networks (SNNs) are incorporated into Rat-SLAM’s core modules to emulate biological processing with greater efficiency. Second, Neuromorphic Computing models the neurons of the SNNs, assessing the feasibility of implementing SNNs on specialized hardware to reduce software processing, a key advantage for UAVs with limited onboard resources. Third, SNNs are developed based on the Memristive Leaky Integrate-and-Fire model, integratingmemristors into artificial neurons to leverage their low power and memory properties. Our approach was evaluated through trajectory simulations using the Hector Quadrotor UAV in the Gazebo environment within the Robot Operating System, yielding valuable insights and guiding future research directions.
Materia
Ingenierías y Tecnologías
Rat-SLAM
Memristors
Neuromorphic Computing
Neuroscience
Spiking Neural Networks
Unmanned Aerial Vehicles
Nivel de accesibilidad
acceso abierto
Condiciones de uso
http://creativecommons.org/licenses/by/4.0/
Repositorio
CIC Digital (CICBA)
Institución
Comisión de Investigaciones Científicas de la Provincia de Buenos Aires
OAI Identificador
oai:digital.cic.gba.gob.ar:11746/12514

id CICBA_c59235cbcc04e17756fb1285477c31a6
oai_identifier_str oai:digital.cic.gba.gob.ar:11746/12514
network_acronym_str CICBA
repository_id_str 9441
network_name_str CIC Digital (CICBA)
spelling 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation SystemPirozzo, BernardoRoark, GeraldinaRuschetti, CristianVillar, SebastiánDe Paula, MarianoAcosta, Gerardo G.Ingenierías y TecnologíasRat-SLAMMemristorsNeuromorphic ComputingNeuroscienceSpiking Neural NetworksUnmanned Aerial VehiclesUnmanned Aerial Vehicles (UAVs) are versatile platforms with potential applications in precision agriculture, disaster management, and more. A core need across these applications is a navigation system that accurately estimates location based on environmental perception. Commercial UAVs use multiple onboard sensors whose fused data improves localization accuracy. The bioinspired Rat-Simultaneous Localization and Mapping (Rat-SLAM) system, is a promising alternative to beexplored to tackle the localization and mapping problem of UAVs. Its cognitive capabilities, semi-metric map construction, and loop closure make it attractive for localization in complex environments. This work presents an improved Rat-SLAM algorithm for UAVs, focusing on three innovations. First, Spiking Neural Networks (SNNs) are incorporated into Rat-SLAM’s core modules to emulate biological processing with greater efficiency. Second, Neuromorphic Computing models the neurons of the SNNs, assessing the feasibility of implementing SNNs on specialized hardware to reduce software processing, a key advantage for UAVs with limited onboard resources. Third, SNNs are developed based on the Memristive Leaky Integrate-and-Fire model, integratingmemristors into artificial neurons to leverage their low power and memory properties. Our approach was evaluated through trajectory simulations using the Hector Quadrotor UAV in the Gazebo environment within the Robot Operating System, yielding valuable insights and guiding future research directions.2025-02info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfhttps://digital.cic.gba.gob.ar/handle/11746/12514enginfo:eu-repo/semantics/altIdentifier/doi/10.70322/dav.2025.10004info:eu-repo/semantics/altIdentifier/issn/2958-7689info:eu-repo/semantics/openAccesshttp://creativecommons.org/licenses/by/4.0/reponame:CIC Digital (CICBA)instname:Comisión de Investigaciones Científicas de la Provincia de Buenos Airesinstacron:CICBA2025-09-29T13:40:24Zoai:digital.cic.gba.gob.ar:11746/12514Institucionalhttp://digital.cic.gba.gob.arOrganismo científico-tecnológicoNo correspondehttp://digital.cic.gba.gob.ar/oai/snrdmarisa.degiusti@sedici.unlp.edu.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:94412025-09-29 13:40:25.198CIC Digital (CICBA) - Comisión de Investigaciones Científicas de la Provincia de Buenos Airesfalse
dc.title.none.fl_str_mv 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System
title 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System
spellingShingle 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System
Pirozzo, Bernardo
Ingenierías y Tecnologías
Rat-SLAM
Memristors
Neuromorphic Computing
Neuroscience
Spiking Neural Networks
Unmanned Aerial Vehicles
title_short 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System
title_full 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System
title_fullStr 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System
title_full_unstemmed 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System
title_sort 4DoF Rat-SLAM with Memristive Spiking Neural Networks for UAVs Navigation System
dc.creator.none.fl_str_mv Pirozzo, Bernardo
Roark, Geraldina
Ruschetti, Cristian
Villar, Sebastián
De Paula, Mariano
Acosta, Gerardo G.
author Pirozzo, Bernardo
author_facet Pirozzo, Bernardo
Roark, Geraldina
Ruschetti, Cristian
Villar, Sebastián
De Paula, Mariano
Acosta, Gerardo G.
author_role author
author2 Roark, Geraldina
Ruschetti, Cristian
Villar, Sebastián
De Paula, Mariano
Acosta, Gerardo G.
author2_role author
author
author
author
author
dc.subject.none.fl_str_mv Ingenierías y Tecnologías
Rat-SLAM
Memristors
Neuromorphic Computing
Neuroscience
Spiking Neural Networks
Unmanned Aerial Vehicles
topic Ingenierías y Tecnologías
Rat-SLAM
Memristors
Neuromorphic Computing
Neuroscience
Spiking Neural Networks
Unmanned Aerial Vehicles
dc.description.none.fl_txt_mv Unmanned Aerial Vehicles (UAVs) are versatile platforms with potential applications in precision agriculture, disaster management, and more. A core need across these applications is a navigation system that accurately estimates location based on environmental perception. Commercial UAVs use multiple onboard sensors whose fused data improves localization accuracy. The bioinspired Rat-Simultaneous Localization and Mapping (Rat-SLAM) system, is a promising alternative to beexplored to tackle the localization and mapping problem of UAVs. Its cognitive capabilities, semi-metric map construction, and loop closure make it attractive for localization in complex environments. This work presents an improved Rat-SLAM algorithm for UAVs, focusing on three innovations. First, Spiking Neural Networks (SNNs) are incorporated into Rat-SLAM’s core modules to emulate biological processing with greater efficiency. Second, Neuromorphic Computing models the neurons of the SNNs, assessing the feasibility of implementing SNNs on specialized hardware to reduce software processing, a key advantage for UAVs with limited onboard resources. Third, SNNs are developed based on the Memristive Leaky Integrate-and-Fire model, integratingmemristors into artificial neurons to leverage their low power and memory properties. Our approach was evaluated through trajectory simulations using the Hector Quadrotor UAV in the Gazebo environment within the Robot Operating System, yielding valuable insights and guiding future research directions.
description Unmanned Aerial Vehicles (UAVs) are versatile platforms with potential applications in precision agriculture, disaster management, and more. A core need across these applications is a navigation system that accurately estimates location based on environmental perception. Commercial UAVs use multiple onboard sensors whose fused data improves localization accuracy. The bioinspired Rat-Simultaneous Localization and Mapping (Rat-SLAM) system, is a promising alternative to beexplored to tackle the localization and mapping problem of UAVs. Its cognitive capabilities, semi-metric map construction, and loop closure make it attractive for localization in complex environments. This work presents an improved Rat-SLAM algorithm for UAVs, focusing on three innovations. First, Spiking Neural Networks (SNNs) are incorporated into Rat-SLAM’s core modules to emulate biological processing with greater efficiency. Second, Neuromorphic Computing models the neurons of the SNNs, assessing the feasibility of implementing SNNs on specialized hardware to reduce software processing, a key advantage for UAVs with limited onboard resources. Third, SNNs are developed based on the Memristive Leaky Integrate-and-Fire model, integratingmemristors into artificial neurons to leverage their low power and memory properties. Our approach was evaluated through trajectory simulations using the Hector Quadrotor UAV in the Gazebo environment within the Robot Operating System, yielding valuable insights and guiding future research directions.
publishDate 2025
dc.date.none.fl_str_mv 2025-02
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv https://digital.cic.gba.gob.ar/handle/11746/12514
url https://digital.cic.gba.gob.ar/handle/11746/12514
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/doi/10.70322/dav.2025.10004
info:eu-repo/semantics/altIdentifier/issn/2958-7689
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
rights_invalid_str_mv http://creativecommons.org/licenses/by/4.0/
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:CIC Digital (CICBA)
instname:Comisión de Investigaciones Científicas de la Provincia de Buenos Aires
instacron:CICBA
reponame_str CIC Digital (CICBA)
collection CIC Digital (CICBA)
instname_str Comisión de Investigaciones Científicas de la Provincia de Buenos Aires
instacron_str CICBA
institution CICBA
repository.name.fl_str_mv CIC Digital (CICBA) - Comisión de Investigaciones Científicas de la Provincia de Buenos Aires
repository.mail.fl_str_mv marisa.degiusti@sedici.unlp.edu.ar
_version_ 1844618623376687105
score 13.070432