Cargando…
Nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network
Biological systems can exhibit intelligent swarm behavior through relatively independent individual, local interaction and decentralized decision-making. A major research challenge of self-organized swarm intelligence is the coupling influences between individual behaviors. Existing methods optimize...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9676561/ https://www.ncbi.nlm.nih.gov/pubmed/36419441 http://dx.doi.org/10.1016/j.patter.2022.100611 |
_version_ | 1784833625723764736 |
---|---|
author | Zhao, Feifei Zeng, Yi Han, Bing Fang, Hongjian Zhao, Zhuoya |
author_facet | Zhao, Feifei Zeng, Yi Han, Bing Fang, Hongjian Zhao, Zhuoya |
author_sort | Zhao, Feifei |
collection | PubMed |
description | Biological systems can exhibit intelligent swarm behavior through relatively independent individual, local interaction and decentralized decision-making. A major research challenge of self-organized swarm intelligence is the coupling influences between individual behaviors. Existing methods optimize the behavior of multiple individuals simultaneously from a global perspective. However, these methods lack in-depth inspiration from swarm behaviors in nature, so they are short of flexibly adapting to real multi-robot online decision-making tasks. To overcome such limits, this paper proposes a self-organized collision avoidance model for real drones incorporating a bio-inspired reward-modulated spiking neural network (RSNN). The local interaction and autonomous learning of a single individual leads to the emergence of swarm intelligence. We validated the proposed model on swarm collision avoidance tasks (a swarm of unmanned aerial vehicles without central control) in a bounded space, carrying out simulation and real-world experiments. Compared with artificial neural network-based online learning methods, our proposed method exhibits superior performance and better stability. |
format | Online Article Text |
id | pubmed-9676561 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-96765612022-11-22 Nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network Zhao, Feifei Zeng, Yi Han, Bing Fang, Hongjian Zhao, Zhuoya Patterns (N Y) Article Biological systems can exhibit intelligent swarm behavior through relatively independent individual, local interaction and decentralized decision-making. A major research challenge of self-organized swarm intelligence is the coupling influences between individual behaviors. Existing methods optimize the behavior of multiple individuals simultaneously from a global perspective. However, these methods lack in-depth inspiration from swarm behaviors in nature, so they are short of flexibly adapting to real multi-robot online decision-making tasks. To overcome such limits, this paper proposes a self-organized collision avoidance model for real drones incorporating a bio-inspired reward-modulated spiking neural network (RSNN). The local interaction and autonomous learning of a single individual leads to the emergence of swarm intelligence. We validated the proposed model on swarm collision avoidance tasks (a swarm of unmanned aerial vehicles without central control) in a bounded space, carrying out simulation and real-world experiments. Compared with artificial neural network-based online learning methods, our proposed method exhibits superior performance and better stability. Elsevier 2022-10-28 /pmc/articles/PMC9676561/ /pubmed/36419441 http://dx.doi.org/10.1016/j.patter.2022.100611 Text en © 2022 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Article Zhao, Feifei Zeng, Yi Han, Bing Fang, Hongjian Zhao, Zhuoya Nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network |
title | Nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network |
title_full | Nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network |
title_fullStr | Nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network |
title_full_unstemmed | Nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network |
title_short | Nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network |
title_sort | nature-inspired self-organizing collision avoidance for drone swarm based on reward-modulated spiking neural network |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9676561/ https://www.ncbi.nlm.nih.gov/pubmed/36419441 http://dx.doi.org/10.1016/j.patter.2022.100611 |
work_keys_str_mv | AT zhaofeifei natureinspiredselforganizingcollisionavoidancefordroneswarmbasedonrewardmodulatedspikingneuralnetwork AT zengyi natureinspiredselforganizingcollisionavoidancefordroneswarmbasedonrewardmodulatedspikingneuralnetwork AT hanbing natureinspiredselforganizingcollisionavoidancefordroneswarmbasedonrewardmodulatedspikingneuralnetwork AT fanghongjian natureinspiredselforganizingcollisionavoidancefordroneswarmbasedonrewardmodulatedspikingneuralnetwork AT zhaozhuoya natureinspiredselforganizingcollisionavoidancefordroneswarmbasedonrewardmodulatedspikingneuralnetwork |