Many keynotes and talks concerning ubicomp/pervasive computing and 'internet of things' conclude with "Sensors are only the beginning...actuators will be next...".
Indeed, we are getting there. Robots are slowly entering homes mainly lawn mowers and vacuum cleaners . In  the developers of Roomba clearly explain why single purpose robots, e.g. vacuum cleaning, convince consumers instead of everything-else-slaves nobody can yet believe in.
Meanwhile, we bough a robot for our lab. I immediately took it home and tried it out:
My experiences completely match with : Roomba does not really clean well, but it does it automatically, so who cares? It works without intervention and it's just fascinating. The device is rather dumb, which is nicely described as 'random walk': it just goes straight, turns around obstacles and wanders criss cross around the room which the instructions call 'robot intelligence to efficiently clean the whole floor'.
Anyway, Roomba is a rather cheap and robust platform. Even if its dumb, attaching a mobile phone will offer new opportunities for developing applications . Stay tuned...
 World Robotics 2008
 Jones, J.L., "Robots at the tipping point: the road to iRobot Roomba," Robotics & Automation Magazine, IEEE , vol.13, no.1, pp. 76-78, March 2006.
 Forlizzi, J. and DiSalvo, C. 2006. Service robots in the domestic environment: a study of the roomba vacuum in the home. In Proceedings of the 1st ACM SIGCHI/SIGART Conference on Human-Robot interaction (Salt Lake City, Utah, USA, March 02 - 03, 2006). HRI '06. ACM, New York, NY, 258-265.
 Tribelhorn, B.; Dodds, Z., "Evaluating the Roomba: A low-cost, ubiquitous platform for robotics research and education," Robotics and Automation, 2007 IEEE International Conference on , vol., no., pp.1393-1399, 10-14 April 2007