It looks like a fun workplace – very open and collaborative. I think I saw a few LEGOs in there too.

Video after the jump.

Chung starts off by describing Ugobe’s vision, saying, “We are going after artifical life, and we hope our products create an emotional response in people.” He says that the reason for creating a new company is because industry is not set up to do such things right now. “Creating organic motion and coordinated gestures of moving all 14 motors at different degrees of speed and staying balanced at the same time was a breakthrough we were able to achieve.” Chung continues, “We can program this sort of thing in very little time – hours.” Bob Christopher says that Ugobe has invested over $1 million dollars in creating Pleo and that the toy industry wasn’t prepared to make that kind of investment – hence the new company.

John Sosoka describes the complexity of Pleo. “… there are clutches in the leg so that when the user starts torqueing on the leg, the internals don’t break. But we designed it so that Pleo knows when the leg is moving by an outside force, so he can cry out in pain.” Pleo also has a capacitive touch sensor under his skin to make touching him more lifelike – up until this point toys that featured “touch” only had buttons. Pleo also has high precision motors with high gearing and no backlash to make his motions as smooth and life-like as possible.

One example of Pleo’s lifelike behavior is his response to “lactic acid” code. “… when running all the motors in Pleo, the batteries wear out quickly. We had to write ‘lactic acid’ code to limit the current draw and have Pleo change behaviors and take a rest when the mtors are being inefficient due to current draw.” One of the practical examples of this is, “When Pleo walks, the carpet will drag on his feet. So his force feedback sensors will realizee that he is spending too much energy to walk around. Pleo will try different things to reduce the energy spent.”

Pleo will also come equipped with a SD slot that will allow users to edit his behavior and “adjust his age, hunger, fatigue and basic personality traits.” Christopher says, “We want to give the user the ability to change Pleo’s personality, animations and tricks. We also want to allow developers and hobbyists to take the SDK and motion system and behavior system and choreograph advanced features and animations for new AI functionality.”

Check out the Fall 2006 issue of ROBOT Magazine for the rest of the interview and tons of other great articles!

I’ve been covering the latest Pleo
news at PleoBot and I’ve been surprised to see the reaction to this video.

It’s been rather strong.

I was wondering if I could get some official word from you in response to this?

And here’s what Ugobe says:

My name is Khristine and I work with UGOBE on the PR front. UGOBE forwarded me your e-mail regarding the recent YouTube videos questioning Pleo’s legitimacy. We were all surprised to see this post and the reaction to it as well. In response, and on behalf of UGOBE, I want to let you know that both of the videos in the YouTube post were made for DEMO 2006.

The DEMO Conference offers all presenters exactly six minutes to demonstrate their new products before a live audience. Real working Pleo units will evolve over time by autonomously interacting with the environment, using true AI. But, the prototype version in this demonstration video is not a full working model and was meant to just give people a taste – in condensed form – of Pleo’s range of behaviors and movements.

In the YouTube posting, the video on the right was taped at the conference. The one on the left is simply a backup of the first.

There you have it: 1) Not the final version of Pleo and 2) Two different videos for the same presentation. Seems to make sense to me. Props to Ugobe for taking care of this so quickly.

Still any naysayers?

In the interview they cover how Ugobe differes from WowWee, Ugobe’s laws of robotics, how they plan on creating emotional bonds between users and their products, and availability of SDKs.

We also learn that the product timeframe for Pleo is October or November, with definite shipments in time for Christmas. They also say that the complexity of the robot may be a problem. It’s very detailed and more complex than most things manufactured for a consumer market. They don’t want to cut corners, and they don’t want shortages.

Christopher also says that fine-tuning Pleo’s gearboxes took long hours of work to make them quiet and smooth. We all remember how noisy Furby was. Judging from the videos of Pleo, he’s virtually silent.

When discussing realism, Christopher says thta real-time reaction to events is key. The robot must be able to respond to noises or sights immediately. We expect this from real animals, and Pleo will emulate this.

On the difference between WowWee and Ugobe:

I think Wow Wee’s more focused on this feature-function experience, where you press the button and you make it mad, or press the button and there’s certain things that they can do. Ours is an autonomous feature, it’s actually thinking on its own, where you don’t need a remote control or a joystick to make it do anything.

WowWee’s robots don’t have real AI. It’s all response to direct input. Pleo can think on his own, according to Christopher.

It’s a great read and very informative. Excitement is mounting for Pleo!