Authors: David Sobrín-Hidalgo, Miguel A. González-Santamarta, Ángel M. Guerrero-Higueras, Francisco J. Rodríguez-Lera, Vicente Matellán-Olivera

Published on: February 06, 2024

Impact Score: 8.22

Arxiv code: Arxiv:2402.04206

Summary

• What is new: This paper presents a novel system for generating explanations of an autonomous robot’s actions using Large Language Models and a Retrieval Augmented Generation method.
• Why this is important: The challenge of making autonomous robots’ actions understandable to humans in Human-Robot Interaction scenarios.
• What the research proposes: Developing an explanation-generating system that leverages Large Language Models and Retrieval Augmented Generation to synthesize explanations from robots’ activity logs.
• Results: The system was successfully tested in a European Robotics League navigation task, with validation questionnaires showing positive feedback on the quality of explanations from technical users.

Technical Details

Technological frameworks used: Retrieval Augmented Generation (RAG)

Models used: Large Language Models (LLMs)

Data used: Logs from autonomous systems

Potential Impact

Robotics manufacturers, companies involved in the development of human-robot interaction technologies, and enterprises focusing on improving transparency and trust in autonomous systems.

Want to implement this idea in a business?

We have generated a startup concept here: ExplainBot.