Self-Organized Construction by Minimal Surprise

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kaiser, Tanja Katharina, Hamann, Heiko
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914785319190528
author Kaiser, Tanja Katharina
Hamann, Heiko
author_facet Kaiser, Tanja Katharina
Hamann, Heiko
contents For the robots to achieve a desired behavior, we can program them directly, train them, or give them an innate driver that makes the robots themselves desire the targeted behavior. With the minimal surprise approach, we implant in our robots the desire to make their world predictable. Here, we apply minimal surprise to collective construction. Simulated robots push blocks in a 2D torus grid world. In two variants of our experiment we either allow for emergent behaviors or predefine the expected environment of the robots. In either way, we evolve robot behaviors that move blocks to structure their environment and make it more predictable. The resulting controllers can be applied in collective construction by robots.
format Preprint
id arxiv_https___arxiv_org_abs_2405_02980
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Self-Organized Construction by Minimal Surprise
Kaiser, Tanja Katharina
Hamann, Heiko
Robotics
Multiagent Systems
Neural and Evolutionary Computing
For the robots to achieve a desired behavior, we can program them directly, train them, or give them an innate driver that makes the robots themselves desire the targeted behavior. With the minimal surprise approach, we implant in our robots the desire to make their world predictable. Here, we apply minimal surprise to collective construction. Simulated robots push blocks in a 2D torus grid world. In two variants of our experiment we either allow for emergent behaviors or predefine the expected environment of the robots. In either way, we evolve robot behaviors that move blocks to structure their environment and make it more predictable. The resulting controllers can be applied in collective construction by robots.
title Self-Organized Construction by Minimal Surprise
topic Robotics
Multiagent Systems
Neural and Evolutionary Computing
url https://arxiv.org/abs/2405.02980