Autonomous Robots (2018) 42:687–689
https://doi.org/10.1007/s10514-018-9720-y
EDITORIAL
Guest editorial: Special issue on online decision making in multi-robot
coordination
Jen Jen Chung
1,2
· Jan Faigl
3
· Geoffrey A. Hollinger
1
Published online: 26 February 2018
© Springer Science+Business Media, LLC, part of Springer Nature 2018
Online decision making is an important part of robotics prob-
lems in which mobile robots operate in unknown or partially
known dynamic environments with the goal of acquiring
information about some studied phenomena. This can be
found in problems such as autonomous data collection, envi-
ronmental monitoring, and robotic exploration missions that
can be considered as variants of robotic information gath-
ering. The key aspect of these problems is that the overall
mission performance can only be evaluated after the mis-
sion is completed; however, the choice of which action to
take at any time depends on local in-situ conditions that vary
according to the information acquired during the mission.
This special issue aims at presenting the state-of-the-art
in approaches to online decision making for coordinating a
team of mobile robots to fulfill a global mission objective
through the individual actions of each robot. The particular
focus is on missions such as multi-robot exploration, per-
sistent environmental monitoring, and adaptive information
gathering. The fundamental challenge of these missions is
that little or no information about the environment is known
in advance. Therefore, one of the problems that must be
addressed is how to trade-off exploration of the unknown
parts of the environment to collect new information about
the operational environment, and exploitation of the current
knowledge acquired so far to improve the mission perfor-
mance.
B
Jen Jen Chung
jenjen.chung@mavt.ethz.ch
Jan Faigl
faiglj@fel.cvut.cz
https://robotics.fel.cvut.cz/jf/
Geoffrey A. Hollinger
geoff.hollinger@oregonstate.edu
1
Oregon State University, 2000 SW Monroe Ave, Corvallis,
OR 97330, USA
2
ETH Zurich, Leonhardstrasse 21, 8092 Zurich, Switzerland
3
Faculty of Electrical Engineering, Czech Technical University
in Prague, Technická 2, 166 27 Prague 6, Czech Republic
Following an open call for papers, the 12 selected arti-
cles (with a 50% acceptance rate out of 24 submissions)
that comprise this special issue contain a common thread
of distributed planning for multi-robot active perception,
navigation, and manipulation. To solve these challenging
problems, the authors leverage and build on techniques such
as belief space planning, self-organizing maps, Gaussian
Markov random fields, model-free control, homotopy con-
strained optimization, and team orienteering. Collectively
these papers contribute a diverse set of tools for multi-robot
planning and optimization in highly uncertain and dynamic
environments.
A summary of each of the 12 articles is provided below.
Decentralized multi-robot belief space planning in
unknown environments via identification and efficient
re-evaluation of impacted paths (Regev and Indelman)
The first article provides a computationally efficient
method for decentralized belief space planning with appli-
cations in multi-robot autonomous navigation in unknown
environments. By identifying and only updating those paths
that are impacted as a result of an update in the path of another
robot, their method is able to achieve substantial planning
time speed-ups compared to existing approaches.
Online planning for multi-robot active perception with
self-organizing maps (Best, Faigl and Fitch)
This contribution presents a self-organizing map algo-
rithm that jointly optimises the selection and sequence of
viewpoint nodes to allocate to robots that are coordinating
to perform active perception and data collection tasks. The
authors show that their solution allows for efficient online
replanning by adapting previous solutions as new informa-
tion becomes available.
Searching and tracking people with cooperative mobile
robots (Goldhoorn et al.)
This paper discusses a decentralized multi-robot approach
to searching and tracking a human in a dynamic environment
123