# Using Large Language Models for Interpreting Autonomous Robots Behaviors

arXiv: https://arxiv.org/abs/2304.14844 · HTML: https://mlsanity.com/paper/2304.14844/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2023.

## Built on by (most cited first, 4 of 4)

- [Enhancing Robot Explanation Capabilities through Vision-Language Models: a Preliminary Study by Interpreting Visual Inputs for Improved Human-Robot Interaction](https://mlsanity.com/paper/2404.09705/) (2024)
- [Embodied Navigation with Auxiliary Task of Action Description Prediction](https://mlsanity.com/paper/2510.21809/) (2025)
- [Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability through Blockchain and Large Language Models](https://mlsanity.com/paper/2403.09567/) (2024)
- [Enabling Rapid Shared Human-AI Mental Model Alignment via the After-Action Review](https://mlsanity.com/paper/2503.19607/) (2025)

## Abstract (arXiv)

The deployment of autonomous robots in various domains has raised significant concerns about their trustworthiness and accountability. This study explores the potential of Large Language Models (LLMs) in analyzing ROS 2 logs generated by autonomous robots and proposes a framework for log analysis that categorizes log files into different aspects. The study evaluates the performance of three different language models in answering questions related to StartUp, Warning, and PDDL logs. The results suggest that GPT 4, a transformer-based model, outperforms other models, however, their verbosity is not enough to answer why or how questions for all kinds of actors involved in the interaction.