BEE-L Archives

Informed Discussion of Beekeeping Issues and Bee Biology

BEE-L@COMMUNITY.LSOFT.COM

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Peter Borst <[log in to unmask]>
Reply To:
Informed Discussion of Beekeeping Issues and Bee Biology <[log in to unmask]>
Date:
Mon, 1 Mar 2004 11:11:18 -0500
Content-Type:
text/plain
Parts/Attachments:
text/plain (41 lines)
ANALYSIS OF BEE BEHAVIOUR MAY MAKE BETTER ROBOTS

Scientists at the Georgia Institute of Technology in the USA have developed
a new computer vision system which affords an automated analysis of animal
movement - honey bee activities in particular.

The system is expected to accelerate animal behaviour research which will
have implications for the biologically inspired design of robots. A
scientist on the project explained that they believe that the language of
behaviour is common between animals and robots, so potentially they could
for instance videotape like ants for a long period, learn their 'programme'
and run it on a robot. He further explained that as social insects such as
bees and ants represent the existence of successful, large scale, robust
behaviour forged from the interaction of many simple individuals, this can
offer ideas on how to organise a cooperating colony of robots capable of
complex operations. The new system automates what once was a time consuming
and tedious task and the system can be used to analyse data on the
sequential movements that encode information. A prime example of this is the
honey bee dance that encodes information on food source. On this particular
analysis, the team are working with Thomas Seeley* of Cornell University.
The analysis system has several components.

Firstly, researchers shoot 15 minutes of video footage of bees (some of
which are marked. This footage is taken in an observation hive. Then the
computer software converts the bees movements into x and y components to
determine location information for each bee in each frame. Some segments of
this data are hand labelled and used as motion examples for the automated
analysis system. Challenges lie ahead though, especially the fact that
researchers will have to work out differences between the motor and sensory
capabilities of robots and insects.

*Professor Thomas Seeley is professor of Biology at Cornell University and
is the author of Honeybee Ecology, and Wisdom of the Hive. Both well worth
reading. Ed.

from Apis UK -- Used by permission

::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::
-- Visit www.honeybeeworld.com/BEE-L for rules, FAQ and  other info ---
::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::::

ATOM RSS1 RSS2