Natural Language and LLMs in Human-Robot Interaction: Performance and Challenges in a Simulated Setting

Kelvin Olaiya, Giovanni Delnevo, Chiara Ceccarini, Chan Tong Lam, Giovanni Pau, Paola Salomoni

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Natural language provides an intuitive and accessible way for humans to communicate with robots, fostering more natural and flexible interaction across a range of tasks. This study investigates how effectively users can command a robot using natural language within a simulated environment. By employing Gemini Flash 2.0 as the underlying Large Language Model (LLM) to interpret and translate user prompts into executable plans, we explore both the strengths and limitations of this approach. The experiments evaluated user-generated prompts across multiple predefined tasks, revealing a spectrum of outcomes - from successful task completions to errors such as misinterpretations, spatial failures, and hallucinated behaviors where the robot acted on non-existent information. The results highlight how different communication strategies, combining directive and conversational phrasing, influenced task performance. This work contributes to advancing Human-Robot Interaction (HRI) design by emphasizing the potential of LLM-powered systems while addressing the challenges of ambiguity and error resilience in user-driven command structures.

Original languageEnglish
Title of host publicationICHORA 2025 - 2025 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798331510886
DOIs
Publication statusPublished - 2025
Event7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, ICHORA 2025 - Ankara, Turkey
Duration: 23 May 202524 May 2025

Publication series

NameICHORA 2025 - 2025 7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings

Conference

Conference7th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, ICHORA 2025
Country/TerritoryTurkey
CityAnkara
Period23/05/2524/05/25

Keywords

  • AI for Robotics
  • Human-Robot Interaction
  • Large Language Models
  • Zero-Shot Learning

Fingerprint

Dive into the research topics of 'Natural Language and LLMs in Human-Robot Interaction: Performance and Challenges in a Simulated Setting'. Together they form a unique fingerprint.

Cite this