Robot does the aizu-bandaisan
p2pnet news | Off Topic:- Japanese scientists have programmed a life-sized robot to mimic the steps of the Japanese performer demonstrating the aizu-bandaisan folk dance with amazing dexterity.

Says The Telegraph:
Shin’ichiro Nakaoka and colleagues at the University of Tokyo have overcome difficulties with programming robots to carry out complex leg movements without their losing stability.
They used software allowing their robot HRP-2 to copy the moves of a human dance teacher through video motion capture technology.
HRP-2 then watched dance instructor Hisako Yamada performing a Japanese folk routine called Aizu-Bandaisan, before accurately reproducing her performance just minutes later.
The newspaper includes a video of the robot performing alongside a dancer and the robot’s fluidity is pretty impressive. Check it out.
For now, “Although its rendition of the mainly upper-body aizu bandaisan dance is impressive, the robot – produced by Kawada Industries – has difficulty with complicated leg movements,” says Guardian Unlimited.
“Any step more demanding than lifting a foot is likely to result in the 58kg automaton losing its balance and falling over. The team published its results in the International Journal of Robotics Research.”
And, notes The Telegraph, “The Aizu-Bandaisan is primarily a dance involving upper body moves, and roboticists are still some way from creating robots able to produce Darcy Bussell-style arabesques or high tempo Irish dance moves.”
Not quite Knees up Mother Brown, perhaps.
But still …..
Click the mic on the right to hear David Bannister’s p2pnetcast of this story. .
Also See:
The Telegraph – Dancing robot copies human moves, August 9, 2007
Guardian Unlimited – Left leg in, left leg out: robot learns a few dance steps, August 9, 2007
Use free p2pnet newsfeeds for your site. It’s really easy!
Subscribe to p2pnet.net | | rss feed: http://p2pnet.net/p2p.rss | | Mobile – http://p2pnet.net/index-wml.php
Net access blocked by government restrictions? Use Psiphon from the Citizen Lab at the University of Toronto. Go here for details. Download here.






