Our goal is to explore the possibility of a robot that can begin to learn, starting with nothing but a seed program, everything that it needs to exhibit intelligent behavior. We imagine a robot that is self-motivated to explore what it doesn't understand, and become bored with what it does. This research is part of a long-term agenda to explore developmental systems. We are considering (and developing) various neural network models of learning and memory.
At BMC, we attempt to work our research into the classroom. In fact, we, along with our colleagues at Swarthmore College, taught the first undergraduate courses in Developmental Robotics.
Developmental Robotics is also beginning to become an international research area. In fact, Douglas Blank and Lisa Meeden have just completed editing a special issue of the journal Connection Science. We also help maintain a Developmental Robotics Wiki for the community of researchers, and hosted the first AAAI Symposium on the topic in 2005.