Swarm SLAM: Challenges and Perspectives
A robot swarm is a decentralized system characterized by locality of sensing and communication, self-organization, and redundancy. These characteristics allow robot swarms to achieve scalability, flexibility and fault tolerance, properties that are especially valuable in the context of simultaneous...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-03-01
|
Series: | Frontiers in Robotics and AI |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/frobt.2021.618268/full |
id |
doaj-56aec1cdc3574359b05dc6d082d8e520 |
---|---|
record_format |
Article |
spelling |
doaj-56aec1cdc3574359b05dc6d082d8e5202021-03-17T09:05:59ZengFrontiers Media S.A.Frontiers in Robotics and AI2296-91442021-03-01810.3389/frobt.2021.618268618268Swarm SLAM: Challenges and PerspectivesMiquel Kegeleirs0Giorgio Grisetti1Mauro Birattari2IRIDIA, Université libre de Bruxelles, Brussels, BelgiumDIAG, Sapienza Università di Roma, Rome, ItalyIRIDIA, Université libre de Bruxelles, Brussels, BelgiumA robot swarm is a decentralized system characterized by locality of sensing and communication, self-organization, and redundancy. These characteristics allow robot swarms to achieve scalability, flexibility and fault tolerance, properties that are especially valuable in the context of simultaneous localization and mapping (SLAM), specifically in unknown environments that evolve over time. So far, research in SLAM has mainly focused on single- and centralized multi-robot systems—i.e., non-swarm systems. While these systems can produce accurate maps, they are typically not scalable, cannot easily adapt to unexpected changes in the environment, and are prone to failure in hostile environments. Swarm SLAM is a promising approach to SLAM as it could leverage the decentralized nature of a robot swarm and achieve scalable, flexible and fault-tolerant exploration and mapping. However, at the moment of writing, swarm SLAM is a rather novel idea and the field lacks definitions, frameworks, and results. In this work, we present the concept of swarm SLAM and its constraints, both from a technical and an economical point of view. In particular, we highlight the main challenges of swarm SLAM for gathering, sharing, and retrieving information. We also discuss the strengths and weaknesses of this approach against traditional multi-robot SLAM. We believe that swarm SLAM will be particularly useful to produce abstract maps such as topological or simple semantic maps and to operate under time or cost constraints.https://www.frontiersin.org/articles/10.3389/frobt.2021.618268/fullswarm roboticsSLAMdistributed systemsmappingexploration schemeslocalization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Miquel Kegeleirs Giorgio Grisetti Mauro Birattari |
spellingShingle |
Miquel Kegeleirs Giorgio Grisetti Mauro Birattari Swarm SLAM: Challenges and Perspectives Frontiers in Robotics and AI swarm robotics SLAM distributed systems mapping exploration schemes localization |
author_facet |
Miquel Kegeleirs Giorgio Grisetti Mauro Birattari |
author_sort |
Miquel Kegeleirs |
title |
Swarm SLAM: Challenges and Perspectives |
title_short |
Swarm SLAM: Challenges and Perspectives |
title_full |
Swarm SLAM: Challenges and Perspectives |
title_fullStr |
Swarm SLAM: Challenges and Perspectives |
title_full_unstemmed |
Swarm SLAM: Challenges and Perspectives |
title_sort |
swarm slam: challenges and perspectives |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Robotics and AI |
issn |
2296-9144 |
publishDate |
2021-03-01 |
description |
A robot swarm is a decentralized system characterized by locality of sensing and communication, self-organization, and redundancy. These characteristics allow robot swarms to achieve scalability, flexibility and fault tolerance, properties that are especially valuable in the context of simultaneous localization and mapping (SLAM), specifically in unknown environments that evolve over time. So far, research in SLAM has mainly focused on single- and centralized multi-robot systems—i.e., non-swarm systems. While these systems can produce accurate maps, they are typically not scalable, cannot easily adapt to unexpected changes in the environment, and are prone to failure in hostile environments. Swarm SLAM is a promising approach to SLAM as it could leverage the decentralized nature of a robot swarm and achieve scalable, flexible and fault-tolerant exploration and mapping. However, at the moment of writing, swarm SLAM is a rather novel idea and the field lacks definitions, frameworks, and results. In this work, we present the concept of swarm SLAM and its constraints, both from a technical and an economical point of view. In particular, we highlight the main challenges of swarm SLAM for gathering, sharing, and retrieving information. We also discuss the strengths and weaknesses of this approach against traditional multi-robot SLAM. We believe that swarm SLAM will be particularly useful to produce abstract maps such as topological or simple semantic maps and to operate under time or cost constraints. |
topic |
swarm robotics SLAM distributed systems mapping exploration schemes localization |
url |
https://www.frontiersin.org/articles/10.3389/frobt.2021.618268/full |
work_keys_str_mv |
AT miquelkegeleirs swarmslamchallengesandperspectives AT giorgiogrisetti swarmslamchallengesandperspectives AT maurobirattari swarmslamchallengesandperspectives |
_version_ |
1724218530035924992 |