Robots that learn to communicate: A developmental approach to personally and physically situated human-robot conversations

Naoto Iwahashi, Komei Sugiura, Ryo Taguchi, Takayuki Nagai, Tadahiro Taniguchi

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

10 Citations (Scopus)


This paper summarizes the online machine learning method LCore, which enables robots to learn to communicate with users from scratch through verbal and behavioral interaction in the physical world. LCore combines speech, visual, and tactile information obtained through the interaction, and enables robots to learn beliefs regarding speech units, words, the concepts of objects, motions, grammar, and pragmatic and communicative capabilities. The overall belief system is represented by a dynamic graphical model in an integrated way. Experimental results show that through a small, practical number of learning episodes with a user, the robot was eventually able to understand even fragmental and ambiguous utterances, respond to them with confirmation questions and/or actions, generate directive utterances, and answer questions, appropriately for the given situation. This paper discusses the importance of a developmental approach to realize personally and physically situated human-robot conversations.

Original languageEnglish
Title of host publicationDialog with Robots - Papers from the AAAI Fall Symposium, Technical Report
PublisherAI Access Foundation
Number of pages6
ISBN (Print)9781577354871
Publication statusPublished - 2010
Externally publishedYes
Event2010 AAAI Fall Symposium - Arlington, VA, United States
Duration: 2010 Nov 112010 Nov 13

Publication series

NameAAAI Fall Symposium - Technical Report


Conference2010 AAAI Fall Symposium
Country/TerritoryUnited States
CityArlington, VA

ASJC Scopus subject areas

  • General Engineering


Dive into the research topics of 'Robots that learn to communicate: A developmental approach to personally and physically situated human-robot conversations'. Together they form a unique fingerprint.

Cite this