Proc. of the Seventeenth National Conference on Artificial Intelligence
R. Simmons, D. Apfelbaum, W. Burgard, D. Fox, M. Moors,
S. Thrun, and Hakan Younes
Coordination for Multi-RobotExploration
and Mapping
Seventeenth National Conference
on Artificial Intelligence (AAAI), 2000.
Abstract
This paper addresses the problem of exploration and mapping of an unknown
environment by multiple robots. The mapping algorithm is a non-line approach
to likelihood maximization that uses hill climbing to find maps that are
maximallyconsistent with sensor data and odometry. The exploration algorithm
explicitlycoordinates the robots. It tries to maximize overall utility by
minimizingthe potential for overlap in information gain amongst the various
robots. Forboth the exploration and mapping algorithms, most of the computations
aredistributed.The techniques have been tested extensively in real-world
trials and simulations.The results demonstrate the performance improvements
and robustness that accrue fromour multi-robot approach to exploration.
Download
Full paper
[.ps.gz](430 kb, 7 pages)
Bibtex
@INPROCEEDINGS{Sim00Coo,
AUTHOR = {Simmons, R. and Apfelbaum, D. and Burgard,
W. and Fox, D. and Moors, M.and Thrun, S. and Younes H.},
TITLE = {Coordination for Multi-Robot Exploration and
Mapping},
YEAR = {2000},
BOOKTITLE = {Proc.~of the National Conference on Artificial Intelligence
(AAAI)}
}