Forgot your password?
typodupeerror
Robotics Social Networks

Advanced Social Skills For Humanoid Robots 92

Posted by kdawson
from the attention-in-the-uncanny-valley dept.
Lanxon writes "A pan-European team of robotics researchers began a project this year that could see humanoid bots interact with groups of people in a realistic, anthropomorphic way for the first time. The 'humanoids with auditory and visual abilities in populated spaces' (HUMAVIPS) project has the ambitious goal of making humanoid bots just a bit more human by building algorithms that will enable bots to mimic what psychologists call the 'cocktail party effect' — the human ability to focus attention on just one person in the midst of other people, voices and background noise."
This discussion has been archived. No new comments can be posted.

Advanced Social Skills For Humanoid Robots

Comments Filter:
  • by BadAnalogyGuy (945258) <BadAnalogyGuy@gmail.com> on Tuesday February 16, 2010 @04:00AM (#31153148)

    That's not true. Sometimes it is necessary to have a droid who understands the binary language of moisture vaporators. That's something even poor moisture farmers need.

  • Hello, real world! (Score:1, Informative)

    by Anonymous Coward on Tuesday February 16, 2010 @07:17AM (#31153856)

    Just checked through the research proposal (not much info, sadly), and am both disappointed and pleased.

    First of all, there is almost nothing new on what the researchers want to do there.
    Cocktail party problem has been described and aimed at a gazilion times, and many groups have been dealing with that kinds of problems, even in the context of robotics (see work at Honda in Germany).
    Already at the end of the 90s, people at MIT people were already researching in attention systems.

    On the other hand, finally roboticists are focusing on relaxing the severe scenario constraints they put into their systems so that the algorithms can work, instead of going for the small delta in the "cognitive" ability that grants them the next paper, but does not solve the underlying problems.
    Robotics needs to face the same real world we and the animals do (e.g. Boston Dynamics's big dog), before we can speak of any type of intelligence.
    And for that, I'm glad they get my taxpayer euros.

We can predict everything, except the future.

Working...