Sheepdog, parallel collaborative programming-by-demonstration

We introduce parallel collaborative programming-by-demonstration (PBD) as a principled approach to capturing knowledge on how to perform computer-based procedures by independently recording multiple experts executing these tasks and combining the recordings via a learning algorithm. Traditional PBD has focused on end-user programming for a single user, and does not support parallel collaborative procedure model construction from examples provided by multiple experts. In this paper we discuss how to extend the main aspects of PBD (instrumentation, abstraction, learning, and execution), and we describe the implementation of these extensions in a system called Sheepdog.