Geminoid F android unveiled

By | April 5, 2010

Japanese robotics researcher Hiroshi Ishiguro is continuing his quest to build androids that look and behave as close to human as possible. After creating an android copy of his young daughter, a TV celebrity and himself, earlier today he announced that he has created a new state-of-the-art android called Geminoid F.

The new android is a clone of a 20-year old female model both in appearance and behavior. It has been designed using new actuation methods that allow for a larger number of facial expressions to be displayed using less hardware. According to the press release,

The humanoid robot “Geminoid HI-1” which has previously been developed by ATR Intelligent Robotics and Communication Laboratories (ATR-IRC) has a complicated body structure with 46-degree-of-freedom. In contrast, the newly-developed Geminoid F has minimum degrees of freedom required for tele-operation and has been designed to re-create more natural facial expressions like smiling. By limiting the number of moving parts, development cost was significantly reduced. In addition, wide applications in practical scenes can be expected by adopting the appearance of a more friendly woman.

It all sounds good on paper but what does it look in real life? You can be the judge of Ishiguro’s newest android after watching it in action in the the following video.


[source]

3 thoughts on “Geminoid F android unveiled

  1. Deaconballs

    This group does make unbelievable robots. I buy the "looks human" but not the "acts human". The strategy of acting human is to create state cases. IE. if playing ball react this way when someone has blue ball in hand and is looking at you. It is very sophisticated but requires an omniscient understanding of the environment and predictable scenarios. This is much better than I have seen from other humanoids but is still very limited in scope. Before it "acts human" it must be able to react to novel experiences with appropriate behaviors.

  2. Anonymous

    This is Right. Robots shouldn’t be given artificial intelligence. They could use it for all the wrong reasons. If they are given the ability to learn, they could be able to react and adapt. They could learn how to make weapons of mass destruction and possibly use them for their own needs. We could create a new race, equal to ours. If that race is able to learn, adapt, solve, and appear as human, they could cause a lot of trouble. If they appear human, they could act as another man and be able to cause tensions with other people or countries. If mankind has an exact equal, which could look like us, speak like us, learn like us, and act like us, which could be classified as clones and possible destroy a nation. They could cause national superiority and could cause all-out war. I'm not saying that they shouldn’t exist. All I’m saying is that they shouldn’t be able to become too advanced to be able to be a human clone. I agree with this article and they should be able to exist. They could help with a lot of trouble we have already created, but they might be able to destroy the world. I'm not saying that they’ll turn evil on us, but they could be programmed to do the wrong things.

  3. Deaconballs

    I think someone has been watching too many movies. The learning in artificial intelligence is limited in scope to the application that it is designed for. Ie. a face recognition program can't all of a sudden learn to walk. The human brain doesn't even work like what Anonymous thinks robots will do without specific regions of the brain (which we don't understand and until we do we could never reproduce). The part of the brain that is design for vision can't all of a sudden produce arm movements. The brain is plastic but that only means very limited and small changes.

Comments are closed.