This work introduces a robotics platform which embeds a conversational AI agent in an embodied system for natural language understanding and intelligent decision-making for service tasks; integrating task planning and human-like conversation. The agent is derived from a large language model, which has learned from a vast corpus of general knowledge. In addition to generating dialogue, this agent can interface with the physical world by invoking commands on the robot; seamlessly merging communication and behavior. This system is demonstrated in a free-form tour-guide scenario, in an HRI study combining robots with and without conversational AI capabilities. Performance is measured along five dimensions: overall effectiveness, exploration abilities, scrutinization abilities, receptiveness to personification, and adaptability.
@article{arxiv.2310.06303,
title = {Dobby: A Conversational Service Robot Driven by GPT-4},
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},
journal= {arXiv preprint arXiv:2310.06303},
year = {2023}
}