Smart homes, when applied to elder people, can be considered as residential houses equipped with sensors and automated devices whose goal is to deliver care and monitoring of the people living in them. Assisted living in such homes provides early detection of problems, emergency support and promotion of residential safety and tele-medicine capabilities. In such settings, socially assistive robotics has arisen not only as a main element to support elder or handicapped people in day-life activities or as a therapeutic robot, but also as a crucial interface to the person living in the smart home. Such assistance must be defined in the long-term, and it must attempt to balance the immediate specific needs of the user with the long-term effects that the robot’s and assistance technologies can potentially have on the user’s developmental trajectory. To achieve such long-term support, the robotic system must be able to acquire new concepts, adapt to new situations and learn behaviors to solve new tasks by exploiting its past experiences. The LifeBots project will investigate the use of lifelong technologies as a key resource to adapt to new goals, user’s preferences or environmental issues that require a tailoring of current assistive settings.