(Georgia Institute of Technology, 2010)
Dellaert, Frank; Fathi, Alireza; Cunningham, Alex; Paluri, Balmanohar; Ni, Kai
We present a novel paradigm for massively distributed,
large-scale multi-robot mapping. Our goal is to explore
techniques that can support continuous mapping over an
indefinite amount of time. We argue that to scale to city or
even global scales the concept of a single globally consistent map
has to be abandoned, and present an infrastructure-supported
solution where most of the inference and map-maintenance is
done on local "map-servers", rather than on the robot itself.
The main technical contribution in the paper is a factor-graph-based
scheme for making this possible, and a novel local map
representation, local exponential maps, that enable indefinite
map updates while remaining self-consistent over time. We
present initial experimental results both in simulation and using
real data, although a full-scale deployment and evaluation of
the technique is left for future work.
(Georgia Institute of Technology, 2010)
Fathi, Alireza; Cunningham, Alex; Paluri, Balmanohar; Ni, Kai; Dellaert, Frank
EasySLAM is a robust, accurate, efficient and
easy-to-use visual SLAM framework which uses the unique
properties of planar landmarks to navigate robots in societal
settings. Due to the use of landmarks which can be associated
with semantics, a hybrid symbolic-metric SLAM variant is
obtained that makes the maps immediately usable for human-robot
interaction, high-level monitoring, and semantic analysis.
EasySLAM associates a set of landmarks to each part of the
house (e.g. kitchen, living room, bathroom, bedroom, etc.) and
takes navigation commands such as "go to kitchen". Loalization
and mapping, planning and navigation results are presented
with an inexpensive, commercially available robot and uniquely
identifiable markers.
SLAM with planar landmarks is easy, robust, and fills the
real need in both research and society, and we have a system
that everyone can use.