When Robots Get Chatty: Grounding Multimodal Human-Robot Conversation and Collaboration

TL;DR

This paper explores integrating large language models with robotic sensory and perceptual systems to enable natural, social, and open-ended human-robot conversations and collaborations.

Contribution

It introduces a modular framework for grounding LLMs with robot perceptions and capabilities, enhancing social and cognitive interaction in robots.

Findings

LLMs enable emergent cognition in robots.

The system supports natural language-based control and interaction.

Qualitative and quantitative results show promising potential.

Abstract

We investigate the use of Large Language Models (LLMs) to equip neural robotic agents with human-like social and cognitive competencies, for the purpose of open-ended human-robot conversation and collaboration. We introduce a modular and extensible methodology for grounding an LLM with the sensory perceptions and capabilities of a physical robot, and integrate multiple deep learning models throughout the architecture in a form of system integration. The integrated models encompass various functions such as speech recognition, speech generation, open-vocabulary object detection, human pose estimation, and gesture detection, with the LLM serving as the central text-based coordinating unit. The qualitative and quantitative results demonstrate the huge potential of LLMs in providing emergent cognition and interactive language-oriented control of robots in a natural and social manner.