Robotic ecologies are networks of heterogeneous robotic devices pervasively embedded in everyday environments, where they cooperate to perform complex tasks. While their potential makes them increasingly popular, one fundamental problem is how to make them both autonomous and adaptive, so as to reduce the amount of preparation, pre-programming and human supervision that they require in real world applications. The project RUBICON develops learning solutions which yield cheaper, adaptive and efficient coordination of robotic ecologies. The approach we pursue builds upon a unique combination of methods from cognitive robotics, machine learning, planning and agent-based control, and wireless sensor networks. This paperillustrates the innovations advanced by RUBICON in each of these fronts before describing how the resulting techniques have been integrated and applied to a smart home scenario. The resulting system is able to provide useful services and pro-actively assist the users in their activities. RUBICON learns through an incremental and progressive approach driven by the feedback received from its own activities and from the user, while also self-organizing the manner in which it uses available sensors, actuators and other functional components in the process. This paper summarises some of the lessons learned by adopting such an approach and outlines promising directions for future work.