My very clear vision for the ideal Roomba is one you never see and you never touch. Our research priorities are explicitly focused on the Roomba of the future that will deliver on the promise of automatically cleaning your floor.

In the end, robots do things that people can do. So there is a cost above which you can hire somebody to do it, and that bounds the opportunity.

When I was building robots in the early 1990s, the problems of voice recognition, image understanding, VOIP, even touchscreen technologies - these were robotics problems.

The answer is navigation, manipulation, and implementation of more sophisticated intelligence. The idea that a robot will become more aware of its environment, that telling it to "go to the kitchen" means something - navigation and understanding of the environment is a robot problem. Those are the technological frontiers of the robotics industry.

Building robot versions of people is very expensive.

When we built Roomba, we explicitly designed it to not have a face. We didn't want to think it was cute, we wanted people to take it seriously so we gave it more of an industrial look. People personified their Roomba anyway. Over 80 percent of people name their robot. We did nothing to encourage people to do that but they do it anyway.

I was focused on building things from an early age. When I was about 3, our toilet broke, and my mother was ready to call the plumber. I told her I would fix it and asked her to get my Richard Scarry book 'How Things Work in Busytown.' Between the picture of a toilet and the text she read to me explaining how the parts worked, I fixed it.