English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Social insects such as ants communicate via pheromones which allows them tocoordinate their activity and solve complex tasks as a swarm, e.g. foraging forfood. This behavior was shaped through evolutionary processes. In computationalmodels, self-coordination in swarms has been implemented using probabilistic orsimple action rules to shape the decision of each agent and the collectivebehavior. However, manual tuned decision rules may limit the behavior of theswarm. In this work we investigate the emergence of self-coordination andcommunication in evolved swarms without defining any explicit rule. We evolve aswarm of agents representing an ant colony. We use an evolutionary algorithm tooptimize a spiking neural network (SNN) which serves as an artificial brain tocontrol the behavior of each agent. The goal of the evolved colony is to findoptimal ways to forage for food and return it to the nest in the shortestamount of time. In the evolutionary phase, the ants are able to learn tocollaborate by depositing pheromone near food piles and near the nest to guideother ants. The pheromone usage is not manually encoded into the network;instead, this behavior is established through the optimization procedure. Weobserve that pheromone-based communication enables the ants to perform betterin comparison to colonies where communication via pheromone did not emerge. Weassess the foraging performance by comparing the SNN based model to a rulebased system. Our results show that the SNN based model can efficientlycomplete the foraging task in a short amount of time. Our approach illustratesself coordination via pheromone emerges as a result of the networkoptimization. This work serves as a proof of concept for the possibility ofcreating complex applications utilizing SNNs as underlying architectures formulti-agent interactions where communication and self-coordination is desired.

Emergent communication enhances foraging behaviour in evolved swarms controlled by Spiking Neural Networks