Emotion AI has its first sale and paying customer! Antics Technologies, Cambridge, UK, is integrating our technology with their market leading consumer animation toolkit, Antics 5.0.

Our technology will be used to make it as easy as 1 – 2 – 3 for non professional users to create professional looking emotionally expressive “in movie” characters whose expressions are complex, easily adjustable and believable. Only Emotion AI technology can enable all of these benefits.

Busy recently on a large project but I hope to get back into the swing of posting soon!

Some of you may have seen an article in wired about emotion in games “Can a game make you cry?” citing a research report entitled “Videogames: The Impact of Emotion”. What a poorly researched, sloppy piece of science journalism this is. Add this to the litany of poor science journalism. The thrust of the piece is that “gamers” appreciate emotion in games but it is somewhat misleading in this respect. What we understand by the premise is that game players appreciate more than just killing but also appreciate emotional interaction, this is not what the survey really says. It merely points out the obvious that games give players a sense of competive achievement along with doses of fear and adreneline. What it also fails to mention is that the author, Bowen Research is an agency that specializes exclusively on “Young male consumers, from boys to young adults” so the Wired article reference to “gamers” in fact only represents a sub set of that category.

The research article itself seems trivial at best but can only be read in its entirety upon payment of almost $1000! Im in the wrong business! Perhaps the full report offers some deeper insights, I wonder if the Wired reporter even read it?

On a continuing basis I am looking for a small number of Gurus to help in the expansion of Emotion AI. If you have seen what we do here you will see that our requirements are both broad and very deep, hence the need for Guru level people. This will be a long term search but if you would like to know more and have a particular interest in any of our fields (Computational Neuroscience, real time gesture and behavior simulation, associated graphics technologies, toolkit plug in development etc) drop me a line.

This looks very interesting, Carnigie Mellon developing an “expressive robot” system as a platform along with tools to allow content creators to build content easily. From the specification (i.e. Maya plug in etc) it sounds like they are making a commerical venture of this. The system is called Interbots.

I seem to be getting a growing number of readers, either I am doing something right or word is out that there is a mad man rambling here! I would encourage you to dig through the previous posts, there is a lot of interesting stuff there. Please feel free to comment, I seem to get very few comments and while I am happy to keep rambling I am also keen to learn from your comments, thanks!

I have been tackling an interesting problem recently which has introduced itself as we have increased the fidelity of our system and in turn run it on a low powered device (mobile phone/cell phone/keitai, whatever your preference). That is the difference between what we usually refer to as “Real Time”, i.e. TV time at 24 – 60fps and what I am calling Human Real Time. This is the lowest processing time achievable by humans in terms of receiving an input signal, routing it, processing by the various required sub systems and finally outputting a behavior. This is generally thought to be around 15 milliseconds (around 60fps), I use 10 milliseconds which is 100 frames per second. » Read more: “TV Real Time” or “Human Real Time”?

I have been working hard recently on building a mobile device demo of the emotion ai engine controlling the Mobile Mascots J2ME Graphics engine with a 3D character. The demo is initially running on Vodafone handsets but should work on any Java handset (as long as it can handle 1MB downloads, hopefully 256k later as the current size is around 300k including the model). The mobile Mascots engine is being ported to the BREW environment soon so that will enable another set of handsets. The character looks very cool and remarkably fluid even given the small window size and reduced frame rate (around 12fps non optimized).

We are also looking at creating a web applet version which would allow me to put a demo on the web site for you to play with. Seeing the engine in action answers so many questions.