Home // ICAS 2020, The Sixteenth International Conference on Autonomic and Autonomous Systems // View article

Area Inspection by Robot Swarms Through Exploitation of Information Gain

Authors:
Carlos Carbone
Dario Albani
Daniele Nardi
Dimitri Ognibene
Vito Trianni

Keywords: Swarm Robotics; Entropy; Information Gain; Random Walk

Abstract:
We propose a decentralized, collaborative approach for area coverage and mapping by means of a swarm of robots. The approach is hinged on Information Theory, and builds over a Reinforced Random Walk (RRW) specifically tailored for a precision agriculture scenario, but general enough to accommo- date different applications. Here, we improve by considering the estimated uncertainty about the features present in a target area, and by the expected reduction in uncertainty that visiting the target area could provide, that is, the information entropy and information gain, respectively. The latter is exploited to weight the random selection of the next area to explore, taking also into account the presence of nearby agents that could visit the same target area. The proposed approach features no configuration parameters related to the number of agents employed and the size of the field, opening to direct implementation without preliminary tuning and configuration steps.

Pages: 78 to 79

Copyright: Copyright (c) IARIA, 2020

Publication date: September 27, 2020

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-61208-787-0

Location: Lisbon, Portugal

Dates: from September 27, 2020 to October 1, 2020