• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Dobby: A Conversational Service Robot Driven by GPT-4.
Carson Stark, Bohkyung Chun, Casey Charleston, Varsha Ravi,
Luis Pabon, Surya Sunkari, Tarun Mohan, Peter Stone, and Justin
Hart.
In International Symposium on Robot and Human Interactive Communication (RO-MAN), January 2024.
[PDF]863.8kB [poster.pdf]892.0kB
This work introduces a robotics platform which comprehensively integratesmulti-step action execution, natural language understanding, and memory tointeractively perform service tasks in accordance with variable needs andintentions of users. The proposed architecture is built around an AI agent,derived from GPT-4, which is embedded in an embodied system. Our approachutilizes semantic matching, plan validation, and state messages to ground theagent in the physical world, en-abling a seamless merger between communicationand behavior. We demonstrate the advantages of this system with an HRI studycomparing mobile robots with and without conversational AI capabilities in afree-form tour-guide scenario. The increased adaptability of the system ismeasured along five dimensions: flexible task planning, interactive explorationof information, emotional-friendliness, personalization, and increased overalluser satisfaction.
@InProceedings{carson_stark_ROMAN2024,
author = {Carson Stark and Bohkyung Chun and Casey Charleston and Varsha Ravi and Luis Pabon and Surya Sunkari and Tarun Mohan and Peter Stone and Justin Hart},
title = {Dobby: A Conversational Service Robot Driven by GPT-4},
booktitle = {International Symposium on Robot and Human Interactive Communication (RO-MAN)},
year = {2024},
month = {January},
location = {Austin, United States},
abstract = {This work introduces a robotics platform which comprehensively integrates
multi-step action execution, natural language understanding, and memory to
interactively perform service tasks in accordance with variable needs and
intentions of users. The proposed architecture is built around an AI agent,
derived from GPT-4, which is embedded in an embodied system. Our approach
utilizes semantic matching, plan validation, and state messages to ground the
agent in the physical world, en-abling a seamless merger between communication
and behavior. We demonstrate the advantages of this system with an HRI study
comparing mobile robots with and without conversational AI capabilities in a
free-form tour-guide scenario. The increased adaptability of the system is
measured along five dimensions: flexible task planning, interactive exploration
of information, emotional-friendliness, personalization, and increased overall
user satisfaction.
},
}
Generated by bib2html.pl (written by Patrick Riley ) on Fri Jul 12, 2024 23:00:34