Knowledge Representation and Interactive Learning of Domain Knowledge for Human-Robot Interaction

Mohan Sridharan, Benjamin Meadows

Research output: Chapter in Book/Report/Conference proceedingConference contribution

39 Downloads (Pure)

Abstract

This paper describes an integrated architecture for representing, reasoning with, and interactively learning domain knowledge in the context of human-robot collaboration. Specifically, Answer Set Prolog, a declarative language, is used to represent and reason with incomplete commonsense knowledge about the domain. Non-monotonic logical reasoning identifies knowledge gaps and guides the interactive learning of relations that represent actions, and of axioms that encode affordances and action preconditions and effects. Learning uses probabilistic models of uncertainty, and observations from active exploration, reactive action execution, and human (verbal) descriptions. The learned actions and axioms are used for subsequent reasoning. The architecture is evaluated on a simulated robot assisting humans in an indoor domain.
Original languageEnglish
Title of host publicationProceedings of the 2nd Workshop on Integrated Planning, Acting, and Execution (IntEx 2018)
EditorsTiago Vaquero, Mark Roberts, Sara Bernardini, Tim Niemueller, Simone Fratini
PublisherInternational Conference on Automated Planning and Scheduling
Pages60-68
Number of pages9
Publication statusPublished - 24 Jun 2018
EventWorkshop on Integrated Planning, Acting and Execution at ICAPS 2018 - Delft, Netherlands
Duration: 25 Jun 201825 Jun 2018

Conference

ConferenceWorkshop on Integrated Planning, Acting and Execution at ICAPS 2018
Country/TerritoryNetherlands
CityDelft
Period25/06/1825/06/18

Fingerprint

Dive into the research topics of 'Knowledge Representation and Interactive Learning of Domain Knowledge for Human-Robot Interaction'. Together they form a unique fingerprint.

Cite this