Cargando…

Autonomous driving controllers with neuromorphic spiking neural networks

Autonomous driving is one of the hallmarks of artificial intelligence. Neuromorphic (brain-inspired) control is posed to significantly contribute to autonomous behavior by leveraging spiking neural networks-based energy-efficient computational frameworks. In this work, we have explored neuromorphic...

Descripción completa

Detalles Bibliográficos
Autores principales: Halaly, Raz, Ezra Tsur, Elishai
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451073/
https://www.ncbi.nlm.nih.gov/pubmed/37636326
http://dx.doi.org/10.3389/fnbot.2023.1234962
_version_ 1785095348085063680
author Halaly, Raz
Ezra Tsur, Elishai
author_facet Halaly, Raz
Ezra Tsur, Elishai
author_sort Halaly, Raz
collection PubMed
description Autonomous driving is one of the hallmarks of artificial intelligence. Neuromorphic (brain-inspired) control is posed to significantly contribute to autonomous behavior by leveraging spiking neural networks-based energy-efficient computational frameworks. In this work, we have explored neuromorphic implementations of four prominent controllers for autonomous driving: pure-pursuit, Stanley, PID, and MPC, using a physics-aware simulation framework. We extensively evaluated these models with various intrinsic parameters and compared their performance with conventional CPU-based implementations. While being neural approximations, we show that neuromorphic models can perform competitively with their conventional counterparts. We provide guidelines for building neuromorphic architectures for control and describe the importance of their underlying tuning parameters and neuronal resources. Our results show that most models would converge to their optimal performances with merely 100–1,000 neurons. They also highlight the importance of hybrid conventional and neuromorphic designs, as was suggested here with the MPC controller. This study also highlights the limitations of neuromorphic implementations, particularly at higher (> 15 m/s) speeds where they tend to degrade faster than in conventional designs.
format Online
Article
Text
id pubmed-10451073
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-104510732023-08-26 Autonomous driving controllers with neuromorphic spiking neural networks Halaly, Raz Ezra Tsur, Elishai Front Neurorobot Neuroscience Autonomous driving is one of the hallmarks of artificial intelligence. Neuromorphic (brain-inspired) control is posed to significantly contribute to autonomous behavior by leveraging spiking neural networks-based energy-efficient computational frameworks. In this work, we have explored neuromorphic implementations of four prominent controllers for autonomous driving: pure-pursuit, Stanley, PID, and MPC, using a physics-aware simulation framework. We extensively evaluated these models with various intrinsic parameters and compared their performance with conventional CPU-based implementations. While being neural approximations, we show that neuromorphic models can perform competitively with their conventional counterparts. We provide guidelines for building neuromorphic architectures for control and describe the importance of their underlying tuning parameters and neuronal resources. Our results show that most models would converge to their optimal performances with merely 100–1,000 neurons. They also highlight the importance of hybrid conventional and neuromorphic designs, as was suggested here with the MPC controller. This study also highlights the limitations of neuromorphic implementations, particularly at higher (> 15 m/s) speeds where they tend to degrade faster than in conventional designs. Frontiers Media S.A. 2023-08-11 /pmc/articles/PMC10451073/ /pubmed/37636326 http://dx.doi.org/10.3389/fnbot.2023.1234962 Text en Copyright © 2023 Halaly and Ezra Tsur. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Halaly, Raz
Ezra Tsur, Elishai
Autonomous driving controllers with neuromorphic spiking neural networks
title Autonomous driving controllers with neuromorphic spiking neural networks
title_full Autonomous driving controllers with neuromorphic spiking neural networks
title_fullStr Autonomous driving controllers with neuromorphic spiking neural networks
title_full_unstemmed Autonomous driving controllers with neuromorphic spiking neural networks
title_short Autonomous driving controllers with neuromorphic spiking neural networks
title_sort autonomous driving controllers with neuromorphic spiking neural networks
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451073/
https://www.ncbi.nlm.nih.gov/pubmed/37636326
http://dx.doi.org/10.3389/fnbot.2023.1234962
work_keys_str_mv AT halalyraz autonomousdrivingcontrollerswithneuromorphicspikingneuralnetworks
AT ezratsurelishai autonomousdrivingcontrollerswithneuromorphicspikingneuralnetworks