Multimodal Human-Autonomous Agents Interaction Using Pre-Trained Language and Visual Foundation Models

TL;DR

This paper presents a multimodal interaction framework enabling natural vocal and textual communication between humans and autonomous robots, leveraging pre-trained language and visual models for understanding and executing commands.

Contribution

It extends existing methods by integrating large language models, visual language models, and speech recognition to improve natural human-robot interaction capabilities.

Findings

87.55% vocal command decoding accuracy

86.27% commands execution success rate

0.89 seconds average latency

Abstract

In this paper, we extended the method proposed in [21] to enable humans to interact naturally with autonomous agents through vocal and textual conversations. Our extended method exploits the inherent capabilities of pre-trained large language models (LLMs), multimodal visual language models (VLMs), and speech recognition (SR) models to decode the high-level natural language conversations and semantic understanding of the robot's task environment, and abstract them to the robot's actionable commands or queries. We performed a quantitative evaluation of our framework's natural vocal conversation understanding with participants from different racial backgrounds and English language accents. The participants interacted with the robot using both spoken and textual instructional commands. Based on the logged interaction data, our framework achieved 87.55% vocal commands decoding accuracy, 86.27% commands execution success, and an average latency of 0.89 seconds from receiving the participants' vocal chat commands to initiating the robot's actual physical action. The video demonstrations of this paper can be found at https://linusnep.github.io/MTCC-IRoNL/.