Enhancing Robot Explanation Capabilities through Vision-Language Models: a Preliminary Study by Interpreting Visual Inputs for Improved Human-Robot Interaction

TL;DR

This study enhances robot explanation systems by integrating vision-language models to analyze visual inputs alongside logs, improving the accuracy and detail of explanations during human-robot interactions.

Contribution

The paper introduces a novel approach combining VLMs with LLMs for better explanation generation in robots, expanding previous log-based methods with visual context analysis.

Findings

Visual interpretation improves obstacle identification accuracy.

Enhanced explanations are more precise and contextually relevant.

System shows promise for more intuitive human-robot communication.

Abstract

This paper presents an improved system based on our prior work, designed to create explanations for autonomous robot actions during Human-Robot Interaction (HRI). Previously, we developed a system that used Large Language Models (LLMs) to interpret logs and produce natural language explanations. In this study, we expand our approach by incorporating Vision-Language Models (VLMs), enabling the system to analyze textual logs with the added context of visual input. This method allows for generating explanations that combine data from the robot's logs and the images it captures. We tested this enhanced system on a basic navigation task where the robot needs to avoid a human obstacle. The findings from this preliminary study indicate that adding visual interpretation improves our system's explanations by precisely identifying obstacles and increasing the accuracy of the explanations provided.