AHCI RESEARCH GROUP
Publications
Papers published in international journals,
proceedings of conferences, workshops and books.
OUR RESEARCH
Scientific Publications
How to
Here you can find the complete list of our publications.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
You can use the tag cloud to select only the papers dealing with specific research topics.
You can expand the Abstract, Links and BibTex record for each paper.
2025
Li, H.; Wang, Z.; Liang, W.; Wang, Y.
X’s Day: Personality-Driven Virtual Human Behavior Generation Journal Article
In: IEEE Transactions on Visualization and Computer Graphics, vol. 31, no. 5, pp. 3514–3524, 2025, ISSN: 10772626 (ISSN).
Abstract | Links | BibTeX | Tags: adult, Augmented Reality, Behavior Generation, Chatbots, Computer graphics, computer interface, Contextual Scene, female, human, Human behaviors, Humans, Long-term behavior, male, Novel task, Personality, Personality traits, Personality-driven Behavior, physiology, Social behavior, User-Computer Interface, Users' experiences, Virtual agent, Virtual environments, Virtual humans, Virtual Reality, Young Adult
@article{li_xs_2025,
title = {X’s Day: Personality-Driven Virtual Human Behavior Generation},
author = {H. Li and Z. Wang and W. Liang and Y. Wang},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105003864932&doi=10.1109%2fTVCG.2025.3549574&partnerID=40&md5=a865bbd2b0fa964a4f0f4190955dc787},
doi = {10.1109/TVCG.2025.3549574},
issn = {10772626 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {IEEE Transactions on Visualization and Computer Graphics},
volume = {31},
number = {5},
pages = {3514–3524},
abstract = {Developing convincing and realistic virtual human behavior is essential for enhancing user experiences in virtual reality (VR) and augmented reality (AR) settings. This paper introduces a novel task focused on generating long-term behaviors for virtual agents, guided by specific personality traits and contextual elements within 3D environments. We present a comprehensive framework capable of autonomously producing daily activities autoregressively. By modeling the intricate connections between personality characteristics and observable activities, we establish a hierarchical structure of Needs, Task, and Activity levels. Integrating a Behavior Planner and a World State module allows for the dynamic sampling of behaviors using large language models (LLMs), ensuring that generated activities remain relevant and responsive to environmental changes. Extensive experiments validate the effectiveness and adaptability of our approach across diverse scenarios. This research makes a significant contribution to the field by establishing a new paradigm for personalized and context-aware interactions with virtual humans, ultimately enhancing user engagement in immersive applications. Our project website is at: https://behavior.agent-x.cn/. © 2025 IEEE. All rights reserved,},
keywords = {adult, Augmented Reality, Behavior Generation, Chatbots, Computer graphics, computer interface, Contextual Scene, female, human, Human behaviors, Humans, Long-term behavior, male, Novel task, Personality, Personality traits, Personality-driven Behavior, physiology, Social behavior, User-Computer Interface, Users' experiences, Virtual agent, Virtual environments, Virtual humans, Virtual Reality, Young Adult},
pubstate = {published},
tppubtype = {article}
}
Developing convincing and realistic virtual human behavior is essential for enhancing user experiences in virtual reality (VR) and augmented reality (AR) settings. This paper introduces a novel task focused on generating long-term behaviors for virtual agents, guided by specific personality traits and contextual elements within 3D environments. We present a comprehensive framework capable of autonomously producing daily activities autoregressively. By modeling the intricate connections between personality characteristics and observable activities, we establish a hierarchical structure of Needs, Task, and Activity levels. Integrating a Behavior Planner and a World State module allows for the dynamic sampling of behaviors using large language models (LLMs), ensuring that generated activities remain relevant and responsive to environmental changes. Extensive experiments validate the effectiveness and adaptability of our approach across diverse scenarios. This research makes a significant contribution to the field by establishing a new paradigm for personalized and context-aware interactions with virtual humans, ultimately enhancing user engagement in immersive applications. Our project website is at: https://behavior.agent-x.cn/. © 2025 IEEE. All rights reserved,
2022
Augello, Agnese
Unveiling the Reasoning Processes of Robots through Introspective Dialogues in a Storytelling System: A Study on the Elicited Empathy Journal Article
In: Cognitive Systems Research, vol. 73, pp. 12–20, 2022, ISSN: 13890417.
Abstract | Links | BibTeX | Tags: ACT-R, Anthropomorphic Robots, Cognitive Architectures, Cognitive Systems, Empathy, Gestural user interfaces, Introspective Dialogs, Personality, Reasoning, Social Agents, Social Practices, Storytelling Robots
@article{augelloUnveilingReasoningProcesses2022,
title = {Unveiling the Reasoning Processes of Robots through Introspective Dialogues in a Storytelling System: A Study on the Elicited Empathy},
author = { Agnese Augello},
doi = {10.1016/j.cogsys.2021.11.006},
issn = {13890417},
year = {2022},
date = {2022-01-01},
journal = {Cognitive Systems Research},
volume = {73},
pages = {12--20},
abstract = {The work studies the empathy elicited by a storytelling system in which the characters in the story are interpreted by humanoid robots and modelled as cognitive agents. The ACT-R architecture is exploited to shape the characters' personalities and equip them with knowledge and behaviours typical of social practices. The narration is enriched with gestures and emotional expressions obtained by setting parameters that can be correlated to some emotions, such as the pitch and speech rate, the LEDs colour and the head inclination. The system has been evaluated by comparing a simple narrative modality with an enhanced one, where an introspective dialogue is adopted to explain and let transparent the internal reasoning processes of the characters. The obtained results show that storytelling affected the cognitive component of empathy, especially through the advanced narrative mode. textcopyright 2022 Elsevier B.V.},
keywords = {ACT-R, Anthropomorphic Robots, Cognitive Architectures, Cognitive Systems, Empathy, Gestural user interfaces, Introspective Dialogs, Personality, Reasoning, Social Agents, Social Practices, Storytelling Robots},
pubstate = {published},
tppubtype = {article}
}
The work studies the empathy elicited by a storytelling system in which the characters in the story are interpreted by humanoid robots and modelled as cognitive agents. The ACT-R architecture is exploited to shape the characters' personalities and equip them with knowledge and behaviours typical of social practices. The narration is enriched with gestures and emotional expressions obtained by setting parameters that can be correlated to some emotions, such as the pitch and speech rate, the LEDs colour and the head inclination. The system has been evaluated by comparing a simple narrative modality with an enhanced one, where an introspective dialogue is adopted to explain and let transparent the internal reasoning processes of the characters. The obtained results show that storytelling affected the cognitive component of empathy, especially through the advanced narrative mode. textcopyright 2022 Elsevier B.V.
Augello, Agnese
Unveiling the reasoning processes of robots through introspective dialogues in a storytelling system: A study on the elicited empathy Journal Article
In: Cognitive Systems Research, vol. 73, pp. 12–20, 2022, ISSN: 13890417.
Abstract | Links | BibTeX | Tags: ACT-R, Anthropomorphic Robots, Cognitive Architectures, Cognitive Systems, Empathy, Gestural user interfaces, Introspective Dialogs, Personality, Reasoning, Social Agents, Social Practices, Storytelling Robots
@article{augello_unveiling_2022,
title = {Unveiling the reasoning processes of robots through introspective dialogues in a storytelling system: A study on the elicited empathy},
author = {Agnese Augello},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85122793053&doi=10.1016%2fj.cogsys.2021.11.006&partnerID=40&md5=4564d1566fc0aa809badb52cd9b60c96},
doi = {10.1016/j.cogsys.2021.11.006},
issn = {13890417},
year = {2022},
date = {2022-01-01},
journal = {Cognitive Systems Research},
volume = {73},
pages = {12–20},
abstract = {The work studies the empathy elicited by a storytelling system in which the characters in the story are interpreted by humanoid robots and modelled as cognitive agents. The ACT-R architecture is exploited to shape the characters’ personalities and equip them with knowledge and behaviours typical of social practices. The narration is enriched with gestures and emotional expressions obtained by setting parameters that can be correlated to some emotions, such as the pitch and speech rate, the LEDs colour and the head inclination. The system has been evaluated by comparing a simple narrative modality with an enhanced one, where an introspective dialogue is adopted to explain and let transparent the internal reasoning processes of the characters. The obtained results show that storytelling affected the cognitive component of empathy, especially through the advanced narrative mode. © 2022 Elsevier B.V.},
keywords = {ACT-R, Anthropomorphic Robots, Cognitive Architectures, Cognitive Systems, Empathy, Gestural user interfaces, Introspective Dialogs, Personality, Reasoning, Social Agents, Social Practices, Storytelling Robots},
pubstate = {published},
tppubtype = {article}
}
The work studies the empathy elicited by a storytelling system in which the characters in the story are interpreted by humanoid robots and modelled as cognitive agents. The ACT-R architecture is exploited to shape the characters’ personalities and equip them with knowledge and behaviours typical of social practices. The narration is enriched with gestures and emotional expressions obtained by setting parameters that can be correlated to some emotions, such as the pitch and speech rate, the LEDs colour and the head inclination. The system has been evaluated by comparing a simple narrative modality with an enhanced one, where an introspective dialogue is adopted to explain and let transparent the internal reasoning processes of the characters. The obtained results show that storytelling affected the cognitive component of empathy, especially through the advanced narrative mode. © 2022 Elsevier B.V.