The most interesting developments with Asimo, as far as I am concerned, were the gesture recognition routines. Sadly, there was none of that in his latest appearance at Robo Japan 2008. The camera is used ‘only’ to detect humans, receive objects from them or hand them over. That is an interesting trick too.
ASIMO uses eye cameras on its head and force sensors on its wrists to detect the motion of people. It can reliably hand objects to people, and receive them as well.
Day one of the ROBO-ONE 14 competition in Yokohama featured champion OmniZero.7 doing his usual outstanding job of surprising and delighting both the judges and the crowds. For more information visit Robots Dreams at http://www.robots-dreams.com
ROBO ONE is a competition between robots with a jury. Kind of a beauty pageant, I guess.
Here, four Asimo robots are dancing a really nice choreography. Quite entertaining, but not because of how they interact with humans. It is entertaining to see how someone managed to build a robot with the right movement parameters and then managed to program it to dance in this way. One could also admire the aesthetics of the movements or of the synchronization.
Here is a robot that appears to be quite social. But is it just a script which she/it is going through or does she also interact with people? Perhaps this is a typical example of a robot that is made to ‘appear human’ in what she does, but not in how she observes other humans and interacts with them.
I am trying to put together a plan to work on social robotics. If I look at the following collection of odd robots I suddenly get a sense of urgency. The only reason for most of these robots is that they are entertaining.
Thanks to JL for these nice links to four strange gesture videos:
‘Nonviolent Gestures’ (comments are in Dutch)
As you can see in the fifth and last video these ‘gestures’ are part of a kind of hippie cult around the concept of nonviolent communication. Some people even created a Hyve for it (which is a Dutch version of Facebook).
Almost needless to say, I believe that our perceptual sensitivity to insults prevents this initiative to avoid ‘violent communication’ from succeeding. An insult is in the eye of the beholder and not in the message as such. If a non-violent communicator speaks hippie-talk to me, I will still be on the look-out for any disrespectful or derogatory undertones, and possibly end up feeling insulted anyway. Vice versa, I would much rather get a cheery finger from a card buddy if I just beat him in a game, then a solemn statement about his feelings. For all its good intentions, this nonviolent communication seems born out of frustration with humanity and a certain arrogance in thinking human nature could be improved with a few easy guidelines.
So, mister Rosenberg, please take your touchy-feely, softspoken message, stuff it where the sun doesn’t shine, and go **** yourself. Or should I say, I understand you have problems with fairly normal human communication, I see that you think you have found a better way for us, but I do not share your problem nor do I believe in your solution.
Ah well, perhaps I shouldn’t have written anything about it. If he reads my opinion he will probably be insulted anyway, no matter how I phrase it. Or he just thinks I am too dense to understand him. Or worse still, I am ‘part of the problem, not of the solution’.
Edward S. Klima was a linguist who, together with his wife Ursula Bellugi, wrote ‘The Signs of Language‘ (1979). He was one of the first scholars to pay serious attention to sign languages, ASL grammar in particular, and helped to get them recognized as proper languages. He died on Sept. 25 in the La Jolla section of San Diego, at age 77.
Her is his obituary by the NY Times.
I never met Edward Klima, but I greatly enjoyed reading The Signs of Language, which, I think, presaged much of what has been done in sign language research since.
Let us broaden our horizon.
Let me turn your gesture perspective to new topics (well, revisited actually, see here).
Let us ponder emotion.
Pieter Desmet created the PrEmo method and interface (source)
Several colleagues here are studying ‘design and emotion’. One of the methods developed to evaluate people’s emotional response to product is PrEmo. It shows a little guy in different pictures that represent different emotions. The trick is, however, that they are not pictures but animations with sounds. So, the little guy makes facial expressions, gestures, and some exclamations. Of course, the question immediately comes up how reliably these gestures represent the intended emotions. Does everyone see it the same way? Apparently, Gael showed me some results, people do see it the same way for most of the pictures. Yet, some of them, such as surprise, are not see reliably perceived.
Sadly, the animations, which are in flash, are not available publicly. I understood there is licensing involved, and you have to see them to be able to really evaluate the gestures.
If you want to read more about emotion and how it can be measured: The Design & Emotion Society is quite a useful resource. You can register as a member for free and then they provide a good knowledge base. Another site is the HUMAINE Portal. With them you have to pay a small amount.
I would almost forget, but I also presented some work at the FG2008 conference: Acceptability Ratings by Humans and Automatic Gesture Recognition for Variations in Sign Productions.
Abstract: In this study we compare human and machine acceptability judgments for extreme variations in sign productions. We gathered acceptability judgments of 26 signers and scores of three different Automatic Gesture Recognition (AGR) algorithms that could potentially be used for automatic acceptability judgments, in which case the correlation between human ratings and AGR scores may serve as an ‘acceptability performance’ measure. We found high human-human correlations, high AGR-AGR correlations, but low human-AGR correlations. Furthermore, in a comparison between acceptability and classification performance of the different AGR methods, classification performance was found to be an unreliable predictor of acceptability performance.
Snapshots of the three signs used in the experiment.
Examples of three manipulations of the sign SAW. We tested about 68 sign manipulations in total. These were run through the automatic recognition algorithms we had been working on and they were rated by human signers. The paper is about how humans and machines can be compared.
One of the more interesting lectures at the FG2008 conference was a keynote speech delivered by Nadia Magnenat-Thalmann, director of the MIRALab in Geneva. She talked about Communicating with a Virtual Human or a Robot that has Emotions, Memory and Personality. She went far beyond the simplistic notion of expressing ‘the six basic emotions’ and talked about how mood, personality and relationships may affect our facial expressions.
The talk by Magnenat-Thalmann focused on facial expression. (source)
By coincidence I got an invitation to write a paper for another conference, organized by Anton Nijholt and Nadia Magnenat-Thalmann (and others), called the Conference on Computer Animation and Social Agents (CASA 2009). It is organized by people from the University of Twente but held in Amsterdam. Call for papers: deadline February 2009.
Nadia also mentioned a researcher at Utrecht University called Arjan Egges. He got his PhD at the MIRALab and is now working on “the integration of motion capture animation with navigation and object manipulation”.
Powered by WordPress & Theme by Anders Norén