Distributed target identification in robotic swarms

Paolo Stegagno, Caterina Massidda, Heinrich Bulthoff

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The ability to identify the target of a common action is fundamental for the development of a multi-robot team able to interact with the environment. In most existing systems, the identification is carried on individually, based on either color coding, shape identification or complex vision systems. Those methods usually assume a broad point of view over the objects, which are observed in their entirety. This assumption is sometimes difficult to fulfill in practice, and in particular in swarm systems, constituted by a multitude of small robots with limited sensing and computational capabilities. In this paper, we propose a method for target identification with a heterogeneous swarm of low-informative spatially-distributed sensors employing a distributed version of the naive Bayes classifier. Despite limited individual sensing capabilities, the recursive application of the Bayes law allows the identification if the robots cooperate sharing the information that they are able to gather from their limited points of view. Simulation results show the effectiveness of this approach highlighting some properties of the developed algorithm.

Original languageEnglish
Title of host publicationProceedings of the ACM Symposium on Applied Computing
PublisherAssociation for Computing Machinery
Pages307-313
Number of pages7
Volume13-17-April-2015
ISBN (Print)9781450331968
DOIs
Publication statusPublished - 2015 Apr 13
Externally publishedYes
Event30th Annual ACM Symposium on Applied Computing, SAC 2015 - Salamanca, Spain
Duration: 2015 Apr 132015 Apr 17

Other

Other30th Annual ACM Symposium on Applied Computing, SAC 2015
CountrySpain
CitySalamanca
Period15/4/1315/4/17

Fingerprint

Identification (control systems)
Robotics
Robots
Classifiers
Color
Sensors

ASJC Scopus subject areas

  • Software

Cite this

Stegagno, P., Massidda, C., & Bulthoff, H. (2015). Distributed target identification in robotic swarms. In Proceedings of the ACM Symposium on Applied Computing (Vol. 13-17-April-2015, pp. 307-313). Association for Computing Machinery. https://doi.org/10.1145/2695664.2695922

Distributed target identification in robotic swarms. / Stegagno, Paolo; Massidda, Caterina; Bulthoff, Heinrich.

Proceedings of the ACM Symposium on Applied Computing. Vol. 13-17-April-2015 Association for Computing Machinery, 2015. p. 307-313.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Stegagno, P, Massidda, C & Bulthoff, H 2015, Distributed target identification in robotic swarms. in Proceedings of the ACM Symposium on Applied Computing. vol. 13-17-April-2015, Association for Computing Machinery, pp. 307-313, 30th Annual ACM Symposium on Applied Computing, SAC 2015, Salamanca, Spain, 15/4/13. https://doi.org/10.1145/2695664.2695922
Stegagno P, Massidda C, Bulthoff H. Distributed target identification in robotic swarms. In Proceedings of the ACM Symposium on Applied Computing. Vol. 13-17-April-2015. Association for Computing Machinery. 2015. p. 307-313 https://doi.org/10.1145/2695664.2695922
Stegagno, Paolo ; Massidda, Caterina ; Bulthoff, Heinrich. / Distributed target identification in robotic swarms. Proceedings of the ACM Symposium on Applied Computing. Vol. 13-17-April-2015 Association for Computing Machinery, 2015. pp. 307-313
@inproceedings{0c9eb8c3574b4c86babbd6ae12357235,
title = "Distributed target identification in robotic swarms",
abstract = "The ability to identify the target of a common action is fundamental for the development of a multi-robot team able to interact with the environment. In most existing systems, the identification is carried on individually, based on either color coding, shape identification or complex vision systems. Those methods usually assume a broad point of view over the objects, which are observed in their entirety. This assumption is sometimes difficult to fulfill in practice, and in particular in swarm systems, constituted by a multitude of small robots with limited sensing and computational capabilities. In this paper, we propose a method for target identification with a heterogeneous swarm of low-informative spatially-distributed sensors employing a distributed version of the naive Bayes classifier. Despite limited individual sensing capabilities, the recursive application of the Bayes law allows the identification if the robots cooperate sharing the information that they are able to gather from their limited points of view. Simulation results show the effectiveness of this approach highlighting some properties of the developed algorithm.",
author = "Paolo Stegagno and Caterina Massidda and Heinrich Bulthoff",
year = "2015",
month = "4",
day = "13",
doi = "10.1145/2695664.2695922",
language = "English",
isbn = "9781450331968",
volume = "13-17-April-2015",
pages = "307--313",
booktitle = "Proceedings of the ACM Symposium on Applied Computing",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Distributed target identification in robotic swarms

AU - Stegagno, Paolo

AU - Massidda, Caterina

AU - Bulthoff, Heinrich

PY - 2015/4/13

Y1 - 2015/4/13

N2 - The ability to identify the target of a common action is fundamental for the development of a multi-robot team able to interact with the environment. In most existing systems, the identification is carried on individually, based on either color coding, shape identification or complex vision systems. Those methods usually assume a broad point of view over the objects, which are observed in their entirety. This assumption is sometimes difficult to fulfill in practice, and in particular in swarm systems, constituted by a multitude of small robots with limited sensing and computational capabilities. In this paper, we propose a method for target identification with a heterogeneous swarm of low-informative spatially-distributed sensors employing a distributed version of the naive Bayes classifier. Despite limited individual sensing capabilities, the recursive application of the Bayes law allows the identification if the robots cooperate sharing the information that they are able to gather from their limited points of view. Simulation results show the effectiveness of this approach highlighting some properties of the developed algorithm.

AB - The ability to identify the target of a common action is fundamental for the development of a multi-robot team able to interact with the environment. In most existing systems, the identification is carried on individually, based on either color coding, shape identification or complex vision systems. Those methods usually assume a broad point of view over the objects, which are observed in their entirety. This assumption is sometimes difficult to fulfill in practice, and in particular in swarm systems, constituted by a multitude of small robots with limited sensing and computational capabilities. In this paper, we propose a method for target identification with a heterogeneous swarm of low-informative spatially-distributed sensors employing a distributed version of the naive Bayes classifier. Despite limited individual sensing capabilities, the recursive application of the Bayes law allows the identification if the robots cooperate sharing the information that they are able to gather from their limited points of view. Simulation results show the effectiveness of this approach highlighting some properties of the developed algorithm.

UR - http://www.scopus.com/inward/record.url?scp=84955470522&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84955470522&partnerID=8YFLogxK

U2 - 10.1145/2695664.2695922

DO - 10.1145/2695664.2695922

M3 - Conference contribution

AN - SCOPUS:84955470522

SN - 9781450331968

VL - 13-17-April-2015

SP - 307

EP - 313

BT - Proceedings of the ACM Symposium on Applied Computing

PB - Association for Computing Machinery

ER -