Robot formations as an emergent collective task using target-following behavior

Saved in:
Bibliographic Details
Main Author: Diego Ariel Bendersky
Format: Artículo científico
Language:en
Published: Asociación Española para la Inteligencia Artificial 2003
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866815726179844096
author Diego Ariel Bendersky
author_facet Diego Ariel Bendersky
contents Robot formations as an emergent collective task using target-following behavior Diego Ariel Bendersky Juan Miguel Santos Ingeniería Robot space Target Action behavior Robot formations imply the establishment and the maintenance of a predetermined geometric shapeby a group of robots. In this work, we achieve formations using robots with proximity sensors of shortdetection range and no inter-robot communication equipment. This fact turns the synthesis probleminto a hard one compared to those cases where the robot has information about the absolute locationof the other robots, or has sensors with a higher range limit. The robot formations emerge from anindividual behavior called target-following which we synthesize using Reinforcement Learning (RL).We propose a task decomposition technique based on an action space transformation that allows us toreduce considerably the time needed for learning and overcomes some difficulties that arise with theuse of RLfor this particular problem. Preliminary results support the feasibility of this method forthe synthesis of robot formation behaviors of different shapes 2003 artículo científico 1137-3601 https://www.redalyc.org/articulo.oa?id=92572103 en http://www.redalyc.org/revista.oa?id=925 Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial application/pdf Asociación Española para la Inteligencia Artificial Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial (España) Num.21 Vol.7
format Artículo científico
id redalyc_92572103
language en
publishDate 2003
publisher Asociación Española para la Inteligencia Artificial
spellingShingle Robot formations as an emergent collective task using target-following behavior
Diego Ariel Bendersky
Ingeniería
Robot
space
Target
Action
behavior
Robot formations as an emergent collective task using target-following behavior Diego Ariel Bendersky Juan Miguel Santos Ingeniería Robot space Target Action behavior Robot formations imply the establishment and the maintenance of a predetermined geometric shapeby a group of robots. In this work, we achieve formations using robots with proximity sensors of shortdetection range and no inter-robot communication equipment. This fact turns the synthesis probleminto a hard one compared to those cases where the robot has information about the absolute locationof the other robots, or has sensors with a higher range limit. The robot formations emerge from anindividual behavior called target-following which we synthesize using Reinforcement Learning (RL).We propose a task decomposition technique based on an action space transformation that allows us toreduce considerably the time needed for learning and overcomes some difficulties that arise with theuse of RLfor this particular problem. Preliminary results support the feasibility of this method forthe synthesis of robot formation behaviors of different shapes 2003 artículo científico 1137-3601 https://www.redalyc.org/articulo.oa?id=92572103 en http://www.redalyc.org/revista.oa?id=925 Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial application/pdf Asociación Española para la Inteligencia Artificial Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial (España) Num.21 Vol.7
title Robot formations as an emergent collective task using target-following behavior
topic Ingeniería
Robot
space
Target
Action
behavior
url https://www.redalyc.org/articulo.oa?id=92572103