“…Prior work in open-world planning has developed techniques to make robots programmed by expert users more robust to environment variation through the use of commonsense or domain knowledge [19], [20], [21], [22], [23]. Open-world planners can achieve plan goals in environments with variations [19], under-specified plans [21], [24], and partially observed worlds [20] by coupling a knowledge base with declarative programming planners, such as PDDL [19], CRAM [21], or ASP [20]. However, these techniques tend to depend on hand engineered domain knowledge inputs that end-users cannot provide in a new demonstration, such as a taxonomy of relevant concepts or an ontology of the domain.…”