DMCA
Preprint Version Distributed Target Identification in Robotic Swarms
BibTeX
@MISC{Stegagno_preprintversion,
author = {Paolo Stegagno and Caterina Massidda and Heinrich H. Bülthoff},
title = {Preprint Version Distributed Target Identification in Robotic Swarms},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
The ability to identify the target of a common action is fun-damental 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 as-sumption 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 capa-bilities. In this paper, we propose a method for target iden-tification with a heterogeneous swarm of low-informative spatially-distributed sensors employing a distributed version of the naive Bayes classifier. Despite limited individual sens-ing 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. 1.
Keyphrases
preprint version distributed target identification robotic swarm limited point broad point heterogeneous swarm target iden-tification low-informative spatially-distributed sensor developed algorithm bayes law complex vision system swarm system small robot multi-robot team color coding limited individual sens-ing capability common action naive bayes classifier computational capa-bilities limited sensing simulation result recursive application distributed version shape identification
