Un nou servei computacional basat en el moviment obre noves possibilitats a l'estudi del comportament animal enfocat en la biologia de les abelles.
Des de l'Institut Tecnològic de Georgia es busquen paral·lelismes entre el llenguatge dels robots i dels animals. Les formigues i les abelles, animals de per si socials, són un fantàstic model per exemplificar la complexitat del llenguatge entre individus, model que pot ser traslladat a la tecnologia robòtica.
L'equip dirigit per l'investigador Balch han motoritzat el moviment d'aquest insecte a fi de traslladar el seu mecanisme dialèctic a la societat artificial formada per robots.
Autor: Jane Sanders
Article sencer en anglès
A new computer vision system for automated analysis of animal movement
-- honey bee activities, in particular -- is expected to accelerate animal
behavior research, which also has implications for biologically inspired
design of robots and computers.
 |
| Georgia Tech researchers
led by Tucker Balch from the College of Computing are gathering
data on the behavior of bees and ants using a compter vision
system. Software can recognize which marked bee is doing which
job. |
| Georgia Tech Photo:
Nicole Cappello |
|
|
The animal movement analysis system is part of the
BioTracking
Project, an effort conducted by Georgia Institute of Technology robotics
researchers led by
Tucker
Balch, an assistant professor of computing.
"We believe the language of behavior is common between robots and
animals," Balch said. "That means, potentially, that we could
videotape ants for a long period of time, learn their 'program' and run
it on a robot."
Social insects, such as ants and bees, represent the existence of successful
large-scale, robust behavior forged from the interaction of many, simple
individuals, Balch explained. Such behavior can offer ideas on how to
organize a cooperating colony of robots capable of complex operations.
To expedite the understanding of such behavior, Balch's team developed
a computer vision system that automates analysis of animal movement --
once an arduous and time-consuming task. Researchers are using the system
to analyze data on the sequential movements that encode information --
for example in bees, the location of distant food sources, Balch said.
He will present the research at the Second International Workshop on the
Mathematics and Algorithms of Social Insects on Dec. 16-17 at Georgia
Tech.
Information on the workshop
 |
| Georgia Tech researcher
Tucker Balch examines bees whose behavior is being studied for
potential implications on the efficient behavior of robots.
What they learn may help engineers organize colonies of cooperating
robots. |
| Georgia Tech Photo:
Nicole Cappello |
|
|
With an 81.5 percent accuracy rate, the system can automatically analyze
bee movements and label them based on examples provided by human experts.
This level of labeling accuracy is high enough to allow researchers to
build a subsequent system to accurately determine the behavior of a bee
from its sequence of motions, Balch explained.
For example, one sequence of motions bees commonly perform are waggle
dances consisting of arcing to the right, waggling (walking in a generally
straight line while oscillating left and right), arcing to the left, waggling
and so on. These motions encode the locations of distant food sources,
according to Cornell University Professor of Biology Thomas Seeley, who
has collaborated with Balch on this project. Balch is also working with
Professor Deborah Gordon of Stanford University on related work with ants.
Balch's animal movement analysis system has several components. First,
researchers shoot 15 minutes of videotape of bees -- some of which are
marked with a bright-colored paint and returned to an observation hive.
Then computer vision-based tracking software converts the video of the
marked bees into x- and y-coordinate location information for each animal
in each frame of the footage. Some segments of this data are hand labeled
by a researcher and then used as motion examples for the automated analysis
system.
 |
| Georgia Tech researchers
tag honey bees being studied as part of the National Science
Foundation-sponsored BioTracking Project. A vision system follows
the bees' behaviors. |
| Georgia Tech Photo:
Nicole Cappello |
|
|
In future work, Balch and his colleagues will build a system that can
learn executable models of these behaviors and then run the models in
simulation. These simulations, Balch explained, would reveal the accuracy
of the models. Researchers don't yet know if these models will yield better
computer programming algorithms, though they are hopeful based on what
previous research has revealed.
"Computer scientists have borrowed some of the algorithms discovered
by biologists working with insects to challenging problems in computing,"
Balch said. "One example is network routing, which dictates the path
data takes across the Internet. In this case the insect-based network
routing algorithm, investigated by Marco Dorigo, is the best solution
to date."
But challenges lie ahead for researchers. They will have to grapple with
differences between the motor and sensory capabilities of robots and insects,
Balch added.
Balch's research team members include graduate student Adam Feldman,
Assistant Professor of Computing Frank Dellaert and researcher Zia Khan.
More information about their project is available at
borg.cc.gatech.edu/biotracking.
The project is funded by a grant from the
National
Science Foundation.
In related research with Professor Kim Wallen at Emory University's Yerkes
National Primate Research Center, Balch and Khan are also observing monkeys
with a similar computer vision system. They hope these studies will yield
behavior models that can be implemented in computer code.
The research team is learning about the spatial memory of and social
interaction among monkeys. Already, they can track the movements of individual
monkeys as they search for and find hidden treats in a large enclosure.
Later, they want to observe a troop of 60 to 80 monkeys living together
in a larger compound.
So far, researchers have learned that male and female monkeys have different
spatial memories. Males apparently remember the physical distance to food,
while females follow landmarks to find treats, Balch says.
"We're involved to measure precisely where the monkeys go and how
long it takes them to find the food," Balch explains. "We use
the information from experiments to test hypotheses on spatial memory.
We're more interested in the social systems among these animals. But we
need this basic capability to track monkeys in 3D. So this work is a first
step in this direction."
Ultimately, Balch and his colleagues in the Georgia Tech
College
of Computing's "Borg
Lab" -- named after the Borg of "Star Trek" fame --
want to use this animal behavior information to design robots that work
effectively with people in dynamic, noisy and unknown environments such
as those faced by military and law enforcement officials.
Balch will present his research team's findings on the bee movement system
at the December workshop to prominent biologists, mathematicians, engineers
and computer scientists who gather to share ideas about mathematical and
algorithmic models of social insect behavior. Balch organized the workshop
with Carl Anderson, a visiting assistant professor of natural systems
in the Georgia Tech School of Industrial and Systems Engineering. For
more information on the workshop, see
www.insects.gatech.edu.
RESEARCH NEWS & PUBLICATIONS OFFICE
Georgia Institute of Technology
177 North Avenue NW
Atlanta, Georgia 30332 USA
MEDIA RELATIONS CONTACTS: gtresearchnews@gatech.edu
TECHNICAL CONTACT: Tucker Balch (404-385-2861); E-mail:
(tucker@cc.gatech.edu).
WRITER: Jane Sanders
