Decentralized Classification in Societies of Autonomous and Heterogeneous Robots

Adriano Fagiolini, Magnus Egerstedt, Antonio Bicchi, Adriano Fagiolini, Giancarlo Zichittella, Simone Martini

Risultato della ricerca: Paper

2 Citazioni (Scopus)

Abstract

This paper addresses the classification problem for a set of autonomous robots that interact with each other. The objective is to classify agents that “behave” in “different way”, due to their own physical dynamics or to the interaction protocol they are obeying to, as belonging to different “species”. This paper describes a technique that allows a decentralized classification system to be built in a systematic way, once the hybrid models describing the behavior of the different species are given. This technique is based on a decentralized identification mechanism, by which every agent classifies its neighbors using only local information. By endowing every agent with such a local classifier, the overall system is enhanced with the ability to run behaviors involving individuals of the same species as well as of different ones. The mechanism can also be used to measure the level of cooperativeness of neighbors and to discover possible intruders among them. General applicability of the proposed solution is shown through examples of multi–agent systems from Biology and from Robotics
Lingua originaleEnglish
Stato di pubblicazionePublished - 2011

Fingerprint

Robots
Multi agent systems
Robotics
Classifiers

All Science Journal Classification (ASJC) codes

  • Software
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Control and Systems Engineering

Cita questo

Fagiolini, A., Egerstedt, M., Bicchi, A., Fagiolini, A., Zichittella, G., & Martini, S. (2011). Decentralized Classification in Societies of Autonomous and Heterogeneous Robots.

Decentralized Classification in Societies of Autonomous and Heterogeneous Robots. / Fagiolini, Adriano; Egerstedt, Magnus; Bicchi, Antonio; Fagiolini, Adriano; Zichittella, Giancarlo; Martini, Simone.

2011.

Risultato della ricerca: Paper

Fagiolini, A, Egerstedt, M, Bicchi, A, Fagiolini, A, Zichittella, G & Martini, S 2011, 'Decentralized Classification in Societies of Autonomous and Heterogeneous Robots'.
Fagiolini A, Egerstedt M, Bicchi A, Fagiolini A, Zichittella G, Martini S. Decentralized Classification in Societies of Autonomous and Heterogeneous Robots. 2011.
Fagiolini, Adriano ; Egerstedt, Magnus ; Bicchi, Antonio ; Fagiolini, Adriano ; Zichittella, Giancarlo ; Martini, Simone. / Decentralized Classification in Societies of Autonomous and Heterogeneous Robots.
@conference{bf9636bab88c4e759ebc24171952d0a8,
title = "Decentralized Classification in Societies of Autonomous and Heterogeneous Robots",
abstract = "This paper addresses the classification problem for a set of autonomous robots that interact with each other. The objective is to classify agents that “behave” in “different way”, due to their own physical dynamics or to the interaction protocol they are obeying to, as belonging to different “species”. This paper describes a technique that allows a decentralized classification system to be built in a systematic way, once the hybrid models describing the behavior of the different species are given. This technique is based on a decentralized identification mechanism, by which every agent classifies its neighbors using only local information. By endowing every agent with such a local classifier, the overall system is enhanced with the ability to run behaviors involving individuals of the same species as well as of different ones. The mechanism can also be used to measure the level of cooperativeness of neighbors and to discover possible intruders among them. General applicability of the proposed solution is shown through examples of multi–agent systems from Biology and from Robotics",
author = "Adriano Fagiolini and Magnus Egerstedt and Antonio Bicchi and Adriano Fagiolini and Giancarlo Zichittella and Simone Martini",
year = "2011",
language = "English",

}

TY - CONF

T1 - Decentralized Classification in Societies of Autonomous and Heterogeneous Robots

AU - Fagiolini, Adriano

AU - Egerstedt, Magnus

AU - Bicchi, Antonio

AU - Fagiolini, Adriano

AU - Zichittella, Giancarlo

AU - Martini, Simone

PY - 2011

Y1 - 2011

N2 - This paper addresses the classification problem for a set of autonomous robots that interact with each other. The objective is to classify agents that “behave” in “different way”, due to their own physical dynamics or to the interaction protocol they are obeying to, as belonging to different “species”. This paper describes a technique that allows a decentralized classification system to be built in a systematic way, once the hybrid models describing the behavior of the different species are given. This technique is based on a decentralized identification mechanism, by which every agent classifies its neighbors using only local information. By endowing every agent with such a local classifier, the overall system is enhanced with the ability to run behaviors involving individuals of the same species as well as of different ones. The mechanism can also be used to measure the level of cooperativeness of neighbors and to discover possible intruders among them. General applicability of the proposed solution is shown through examples of multi–agent systems from Biology and from Robotics

AB - This paper addresses the classification problem for a set of autonomous robots that interact with each other. The objective is to classify agents that “behave” in “different way”, due to their own physical dynamics or to the interaction protocol they are obeying to, as belonging to different “species”. This paper describes a technique that allows a decentralized classification system to be built in a systematic way, once the hybrid models describing the behavior of the different species are given. This technique is based on a decentralized identification mechanism, by which every agent classifies its neighbors using only local information. By endowing every agent with such a local classifier, the overall system is enhanced with the ability to run behaviors involving individuals of the same species as well as of different ones. The mechanism can also be used to measure the level of cooperativeness of neighbors and to discover possible intruders among them. General applicability of the proposed solution is shown through examples of multi–agent systems from Biology and from Robotics

UR - http://hdl.handle.net/10447/62944

M3 - Paper

ER -