Learning environmental knowledge from task-based human-robot dialog

This paper presents an approach for learning environmental knowledge from task-based human-robot dialog. Previous approaches to dialog use domain knowledge to constrain the types of language people are likely to use. In contrast, by introducing a joint probabilistic model over speech, the resulting semantic parse and the mapping from each element of the parse to a physical entity in the building (e. g. , grounding), our approach is flexible to the ways that untrained people interact with robots, is robust to speech to text errors and is able to learn referring expressions for physical locations in a map (e. g. , to create a semantic map). Our approach has been evaluated by having untrained people interact with a service robot. Starting with an empty semantic map, our approach is able ask 50% fewer questions than a baseline approach, thereby enabling more effective and intuitive human robot dialog.

Authors

• Thomas Kollar
• Vittorio Perera
• Daniele Nardi
• Manuela Veloso

Keywords

• Robots
• Knowledge based systems
• Grounding
• Speech
• Speech recognition
• Semantics
• Natural languages
• Environmental Knowledge
• Probabilistic Model
• Semantic Map
• Service Robots
• Knowledge Base
• Local Environment
• Natural Language
• Sequence Of Frames
• Mobile Robot
• Conditional Random Field
• Floor Of Building
• Previous Word
• Dialogue System