LLM-based robot personality simulation and cognitive system

Abstract The inherence of personality in human-robot interaction enhances conversational dynamics and user experience. The deployment of Chat GPT-4 within a cognitive robot framework is designed by using state-space realization to emulate specific personality traits, incorporating elements of emotio...

Full description

Saved in:
Bibliographic Details
Main Authors: Jia-Hsun Lo, Han-Pang Huang, Jie-Shih Lo
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-01528-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849309779462193152
author Jia-Hsun Lo
Han-Pang Huang
Jie-Shih Lo
author_facet Jia-Hsun Lo
Han-Pang Huang
Jie-Shih Lo
author_sort Jia-Hsun Lo
collection DOAJ
description Abstract The inherence of personality in human-robot interaction enhances conversational dynamics and user experience. The deployment of Chat GPT-4 within a cognitive robot framework is designed by using state-space realization to emulate specific personality traits, incorporating elements of emotion, motivation, visual attention, and both short-term and long-term memory. The encoding and retrieval of long-term memory are facilitated through document embedding techniques, while emotions are generated based on predictions of future events. This framework processes textual and visual information, responding or initiating actions in accordance with the configured personality settings and cognitive processes. The constancy and effectiveness of the personality simulation have been compared to human baseline and validated via two personality assessments: the International Personality Item Pool – Neuroticism, Extraversion and Openness (IPIP-NEO) and the Big Five personality test. Our proposed personality model of cognitive robot is designed by using Kelly’s role construct repertory, Cattell’s 16 personality factors and preferences, which are analyzed by construct validity and compared to human subjects. Theory of mind is observed in personality simulation, which perform better second-order of belief compared to other agent on the improved theory of mind dataset (ToMi dataset). Based on the proposed methods, our designed robot, Mobi, is enable to chat based on its own personality, handle social conflicts and understand user’s intent. Such simulations can achieve a high degree of human likeness, characterized by conversations that are flexible and imbued with intention.
format Article
id doaj-art-0d5f510aec6f4a97a1a1b03dbe4c3639
institution Kabale University
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-0d5f510aec6f4a97a1a1b03dbe4c36392025-08-20T03:53:58ZengNature PortfolioScientific Reports2045-23222025-05-0115111710.1038/s41598-025-01528-8LLM-based robot personality simulation and cognitive systemJia-Hsun Lo0Han-Pang Huang1Jie-Shih Lo2Department of Mechanical Engineering, National Taiwan UniversityDepartment of Mechanical Engineering, National Taiwan UniversityDepartment of Health Psychology, Chang Jung Christian UniversityAbstract The inherence of personality in human-robot interaction enhances conversational dynamics and user experience. The deployment of Chat GPT-4 within a cognitive robot framework is designed by using state-space realization to emulate specific personality traits, incorporating elements of emotion, motivation, visual attention, and both short-term and long-term memory. The encoding and retrieval of long-term memory are facilitated through document embedding techniques, while emotions are generated based on predictions of future events. This framework processes textual and visual information, responding or initiating actions in accordance with the configured personality settings and cognitive processes. The constancy and effectiveness of the personality simulation have been compared to human baseline and validated via two personality assessments: the International Personality Item Pool – Neuroticism, Extraversion and Openness (IPIP-NEO) and the Big Five personality test. Our proposed personality model of cognitive robot is designed by using Kelly’s role construct repertory, Cattell’s 16 personality factors and preferences, which are analyzed by construct validity and compared to human subjects. Theory of mind is observed in personality simulation, which perform better second-order of belief compared to other agent on the improved theory of mind dataset (ToMi dataset). Based on the proposed methods, our designed robot, Mobi, is enable to chat based on its own personality, handle social conflicts and understand user’s intent. Such simulations can achieve a high degree of human likeness, characterized by conversations that are flexible and imbued with intention.https://doi.org/10.1038/s41598-025-01528-8Human robot interactionLarge language modelRobot personality and cognitionTheory of mind
spellingShingle Jia-Hsun Lo
Han-Pang Huang
Jie-Shih Lo
LLM-based robot personality simulation and cognitive system
Scientific Reports
Human robot interaction
Large language model
Robot personality and cognition
Theory of mind
title LLM-based robot personality simulation and cognitive system
title_full LLM-based robot personality simulation and cognitive system
title_fullStr LLM-based robot personality simulation and cognitive system
title_full_unstemmed LLM-based robot personality simulation and cognitive system
title_short LLM-based robot personality simulation and cognitive system
title_sort llm based robot personality simulation and cognitive system
topic Human robot interaction
Large language model
Robot personality and cognition
Theory of mind
url https://doi.org/10.1038/s41598-025-01528-8
work_keys_str_mv AT jiahsunlo llmbasedrobotpersonalitysimulationandcognitivesystem
AT hanpanghuang llmbasedrobotpersonalitysimulationandcognitivesystem
AT jieshihlo llmbasedrobotpersonalitysimulationandcognitivesystem