Dobby: A Conversational Service Robot Driven by GPT-4

TL;DR

Dobby is a robot platform integrating GPT-4-based conversational AI for natural language understanding, decision-making, and physical interaction, demonstrated in a tour-guide scenario with human-robot interaction studies.

Contribution

This work presents a novel robotic system that combines large language model-based conversation with physical task execution, enabling seamless communication and behavior in service robots.

Findings

Effective natural language understanding and interaction

Successful integration of dialogue and physical commands

Positive human-robot interaction outcomes

Abstract

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.