Towards Specification Learning from Demonstrations

TitleTowards Specification Learning from Demonstrations
Publication TypeConference Proceedings
Year of Conference2018
AuthorsShah, A., and J. Shah
Conference NameRobotics: Science and Systems (RSS), Workshop on Learning from Demonstrations for High Level Robotics Tasks
Date Published06/2018
AbstractWhen observing task demonstrations, human apprentices are able to identify whether a given task is executed correctly long before they gain expertise in actually performing that task. Prior research into learning from demonstrations (LfD) has failed to capture this notion of the acceptability of an execution; meanwhile, temporal logics provide a flexible language for expressing task specifications. Inspired by this, we present a probabilistic model for inferring task specification as a temporal logic formula. We incorporate methods from probabilistic programming to define our priors, along with a domain-independent likelihood function to enable sampling-based inference. We demonstrate the efficacy of our model for inferring specifications with over 90% similarity between the inferred specification and the ground truth, both within a synthetic domain and a real-world table setting task.
URLhttps://interactive.mit.edu/sites/default/files/documents/RSSWLfD18_paper_2.pdf