On Task Recognition and Generalization in Long-Term Robot Teaching

Several research efforts address the challenge of having users incrementally teach or demonstrate a task to a robot. We are interested in an autonomous robot that persists over time and the problem of teaching it an additional task. We believe that the assumption that a user would know all the tasks previously taught to the robot does not hold. We hence investigate the problem of recognizing when a user is teaching a task similar to one the robot already knows and performing task autocompletion. In this extended abstract, we briefly discuss our approach, and report the results of an experiment run with human teachers.