Exploring a GPT-based large language model for variable autonomy in a VR-based human-robot teaming simulation

Simple item page
dc.contributor.authorLakhnati, Younes
dc.contributor.authorPascher, Max
dc.contributor.authorGerken, Jens
dc.date.accessioned2024-05-22T13:18:11Z
dc.date.available2024-05-22T13:18:11Z
dc.date.issued2024-04-03
dc.description.abstractIn a rapidly evolving digital landscape autonomous tools and robots are becoming commonplace. Recognizing the significance of this development, this paper explores the integration of Large Language Models (LLMs) like Generative pre-trained transformer (GPT) into human-robot teaming environments to facilitate variable autonomy through the means of verbal human-robot communication. In this paper, we introduce a novel simulation framework for such a GPT-powered multi-robot testbed environment, based on a Unity Virtual Reality (VR) setting. This system allows users to interact with simulated robot agents through natural language, each powered by individual GPT cores. By means of OpenAI’s function calling, we bridge the gap between unstructured natural language input and structured robot actions. A user study with 12 participants explores the effectiveness of GPT-4 and, more importantly, user strategies when being given the opportunity to converse in natural language within a simulated multi-robot environment. Our findings suggest that users may have preconceived expectations on how to converse with robots and seldom try to explore the actual language and cognitive capabilities of their simulated robot collaborators. Still, those users who did explore were able to benefit from a much more natural flow of communication and human-like back-and-forth. We provide a set of lessons learned for future research and technical implementations of similar systems.en
dc.identifier.urihttp://hdl.handle.net/2003/42516
dc.identifier.urihttp://dx.doi.org/10.17877/DE290R-24352
dc.language.isoenen
dc.relation.ispartofseriesFrontiers in robotics and AI;11
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/de
dc.subjectassistive robotsen
dc.subjectvirtual realityen
dc.subjectevaluationen
dc.subjectshared controlen
dc.subjectvariable autonomyen
dc.subjectlarge language modelen
dc.subjectGPTen
dc.subject.ddc360
dc.subject.ddc370
dc.subject.rswkVirtuelle Realitätde
dc.subject.rswkRoboterde
dc.subject.rswkMensch-Maschine-Kommunikationde
dc.subject.rswkKünstliche Intelligenzde
dc.subject.rswkGroßes Sprachmodellde
dc.titleExploring a GPT-based large language model for variable autonomy in a VR-based human-robot teaming simulationen
dc.typeTexten
dc.type.publicationtypeResearchArticleen
dcterms.accessRightsopen access
eldorado.secondarypublicationtruede
eldorado.secondarypublication.primarycitationLakhnati, Y., Pascher, M. and Gerken, J. (2024) ‘Exploring a GPT-based large language model for variable autonomy in a VR-based human-robot teaming simulation’, Frontiers in robotics and AI, 11. Available at: https://doi.org/10.3389/frobt.2024.1347538en
eldorado.secondarypublication.primaryidentifierhttps://doi.org/10.3389/frobt.2024.1347538de

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
frobt-11-1347538.pdf
Size:
23.18 MB
Format:
Adobe Portable Document Format
Description:
DNB
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
4.85 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Fakultät für Rehabilitationswissenschaften