Can Large Language Models Help Developers with Robotic Finite State Machine Modification?

Abstract

Understanding robot behaviors and experiences through natural language is crucial for developing intelligent and transparent robotic systems. Recent advancement in large language models (LLMs) makes it possible to translate complex, multi-modal robotic experiences into coherent, human-readable narratives. However, grounding real-world robot experiences into natural language is challenging due to many reasons, such as multi-modal nature of data, differing sample rates, and data volume. We introduce RONAR, an LLM-based system that generates natural language narrations from robot experiences, aiding in behavior announcement, failure analysis, and human interaction to recover failure. Evaluated across various scenarios, RONAR outperforms state-of-the-art methods and improves failure recovery efficiency. Our contributions include a multi-modal framework for robot experience narration, a comprehensive real-robot dataset, and empirical evidence of RONAR’s effectiveness in enhancing user experience in system transparency and failure analysis.

BibTeX Entry

@article{gan2024can,
  author = {Gan, Xiangyu and Song, Yuxin Ray and Walker, Nick and Cakmak, Maya},
  title = {Can Large Language Models Help Developers with Robotic Finite State Machine Modification?},
  location = {Munich, Germany},
  cofirst = {2},
  year = {2024},
  month = nov,
  booktitle = {LangRob Workshop at Conference on Robot Learning (CoRL)},
  wwwtype = {workshop}
}