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
Song, T.; Liu, Z.; Zhao, R.; Fu, J.
ElderEase AR: Enhancing Elderly Daily Living with the Multimodal Large Language Model and Augmented Reality Proceedings Article
In: ICVRT - Proc. Int. Conf. Virtual Real. Technol., pp. 60–67, Association for Computing Machinery, Inc, 2025, ISBN: 979-840071018-6 (ISBN).
Abstract | Links | BibTeX | Tags: Age-related, Assisted living, Augmented Reality, Augmented reality technology, Daily Life Support, Daily living, Daily-life supports, Elderly, Elderly users, Independent living, Independent living systems, Language Model, Modeling languages, Multi agent systems, Multi-modal, Multimodal large language model
@inproceedings{song_elderease_2025,
title = {ElderEase AR: Enhancing Elderly Daily Living with the Multimodal Large Language Model and Augmented Reality},
author = {T. Song and Z. Liu and R. Zhao and J. Fu},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-105001924899&doi=10.1145%2f3711496.3711505&partnerID=40&md5=4df693735547b505172657a73359f3ca},
doi = {10.1145/3711496.3711505},
isbn = {979-840071018-6 (ISBN)},
year = {2025},
date = {2025-01-01},
booktitle = {ICVRT - Proc. Int. Conf. Virtual Real. Technol.},
pages = {60–67},
publisher = {Association for Computing Machinery, Inc},
abstract = {Elderly individuals often face challenges in independent living due to age-related cognitive and physical decline. To address these issues, we propose an innovative Augmented Reality (AR) system, “ElderEase AR”, designed to assist elderly users in their daily lives by leveraging a Multimodal Large Language Model (MLLM). This system enables elderly users to capture images of their surroundings and ask related questions, providing context-aware feedback. We evaluated the system’s perceived ease-of-use and feasibility through a pilot study involving 30 elderly users, aiming to enhance their independence and quality of life. Our system integrates advanced AR technology with an intelligent agent trained on multimodal datasets. Through prompt engineering, the agent is tailored to respond in a manner that aligns with the speaking style of elderly users. Experimental results demonstrate high accuracy in object recognition and question answering, with positive feedback from user trials. Specifically, the system accurately identified objects in various environments and provided relevant answers to user queries. This study highlights the powerful potential of AR and AI technologies in creating support tools for the elderly. It suggests directions for future improvements and applications, such as enhancing the system’s adaptability to different user needs and expanding its functionality to cover more aspects of daily living. © 2024 Copyright held by the owner/author(s).},
keywords = {Age-related, Assisted living, Augmented Reality, Augmented reality technology, Daily Life Support, Daily living, Daily-life supports, Elderly, Elderly users, Independent living, Independent living systems, Language Model, Modeling languages, Multi agent systems, Multi-modal, Multimodal large language model},
pubstate = {published},
tppubtype = {inproceedings}
}
Elderly individuals often face challenges in independent living due to age-related cognitive and physical decline. To address these issues, we propose an innovative Augmented Reality (AR) system, “ElderEase AR”, designed to assist elderly users in their daily lives by leveraging a Multimodal Large Language Model (MLLM). This system enables elderly users to capture images of their surroundings and ask related questions, providing context-aware feedback. We evaluated the system’s perceived ease-of-use and feasibility through a pilot study involving 30 elderly users, aiming to enhance their independence and quality of life. Our system integrates advanced AR technology with an intelligent agent trained on multimodal datasets. Through prompt engineering, the agent is tailored to respond in a manner that aligns with the speaking style of elderly users. Experimental results demonstrate high accuracy in object recognition and question answering, with positive feedback from user trials. Specifically, the system accurately identified objects in various environments and provided relevant answers to user queries. This study highlights the powerful potential of AR and AI technologies in creating support tools for the elderly. It suggests directions for future improvements and applications, such as enhancing the system’s adaptability to different user needs and expanding its functionality to cover more aspects of daily living. © 2024 Copyright held by the owner/author(s).
Dongye, X.; Weng, D.; Jiang, H.; Tian, Z.; Bao, Y.; Chen, P.
Personalized decision-making for agents in face-to-face interaction in virtual reality Journal Article
In: Multimedia Systems, vol. 31, no. 1, 2025, ISSN: 09424962 (ISSN).
Abstract | Links | BibTeX | Tags: Decision making, Decision-making process, Decisions makings, Design frameworks, Face-to-face interaction, Feed-back based, Fine tuning, Human-agent interaction, Human–agent interaction, Integrated circuit design, Intelligent virtual agents, Language Model, Large language model, Multi agent systems, Multimodal Interaction, Virtual environments, Virtual Reality
@article{dongye_personalized_2025,
title = {Personalized decision-making for agents in face-to-face interaction in virtual reality},
author = {X. Dongye and D. Weng and H. Jiang and Z. Tian and Y. Bao and P. Chen},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85212947825&doi=10.1007%2fs00530-024-01591-7&partnerID=40&md5=d969cd926fdfd241399f2f96dbf42907},
doi = {10.1007/s00530-024-01591-7},
issn = {09424962 (ISSN)},
year = {2025},
date = {2025-01-01},
journal = {Multimedia Systems},
volume = {31},
number = {1},
abstract = {Intelligent agents for face-to-face interaction in virtual reality are expected to make decisions and provide appropriate feedback based on the user’s multimodal interaction inputs. Designing the agent’s decision-making process poses a significant challenge owing to the limited availability of multimodal interaction decision-making datasets and the complexities associated with providing personalized interaction feedback to diverse users. To overcome these challenges, we propose a novel design framework that involves generating and labeling symbolic interaction data, pre-training a small-scale real-time decision-making network, collecting personalized interaction data within interactions, and fine-tuning the network using personalized data. We develop a prototype system to demonstrate our design framework, which utilizes interaction distances, head orientations, and hand postures as inputs in virtual reality. The agent is capable of delivering personalized feedback from different users. We evaluate the proposed design framework by demonstrating the utilization of large language models for data labeling, emphasizing reliability and robustness. Furthermore, we evaluate the incorporation of personalized data fine-tuning for decision-making networks within our design framework, highlighting its importance in improving the user interaction experience. The design principles of this framework can be further explored and applied to various domains involving virtual agents. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.},
keywords = {Decision making, Decision-making process, Decisions makings, Design frameworks, Face-to-face interaction, Feed-back based, Fine tuning, Human-agent interaction, Human–agent interaction, Integrated circuit design, Intelligent virtual agents, Language Model, Large language model, Multi agent systems, Multimodal Interaction, Virtual environments, Virtual Reality},
pubstate = {published},
tppubtype = {article}
}
Intelligent agents for face-to-face interaction in virtual reality are expected to make decisions and provide appropriate feedback based on the user’s multimodal interaction inputs. Designing the agent’s decision-making process poses a significant challenge owing to the limited availability of multimodal interaction decision-making datasets and the complexities associated with providing personalized interaction feedback to diverse users. To overcome these challenges, we propose a novel design framework that involves generating and labeling symbolic interaction data, pre-training a small-scale real-time decision-making network, collecting personalized interaction data within interactions, and fine-tuning the network using personalized data. We develop a prototype system to demonstrate our design framework, which utilizes interaction distances, head orientations, and hand postures as inputs in virtual reality. The agent is capable of delivering personalized feedback from different users. We evaluate the proposed design framework by demonstrating the utilization of large language models for data labeling, emphasizing reliability and robustness. Furthermore, we evaluate the incorporation of personalized data fine-tuning for decision-making networks within our design framework, highlighting its importance in improving the user interaction experience. The design principles of this framework can be further explored and applied to various domains involving virtual agents. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.
2024
Chaccour, C.; Saad, W.; Debbah, M.; Poor, H. V.
Joint Sensing, Communication, and AI: A Trifecta for Resilient THz User Experiences Journal Article
In: IEEE Transactions on Wireless Communications, vol. 23, no. 9, pp. 11444–11460, 2024, ISSN: 15361276 (ISSN).
Abstract | Links | BibTeX | Tags: Artificial intelligence, artificial intelligence (AI), Behavioral Research, Channel state information, Computer hardware, Cramer-Rao bounds, Extended reality (XR), Hardware, Joint sensing and communication, Learning systems, machine learning, machine learning (ML), Machine-learning, Multi agent systems, reliability, Resilience, Sensor data fusion, Tera Hertz, Terahertz, terahertz (THz), Terahertz communication, Wireless communications, Wireless sensor networks, X reality
@article{chaccour_joint_2024,
title = {Joint Sensing, Communication, and AI: A Trifecta for Resilient THz User Experiences},
author = {C. Chaccour and W. Saad and M. Debbah and H. V. Poor},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85190170739&doi=10.1109%2fTWC.2024.3382192&partnerID=40&md5=da12c6f31faacaa08118b26e4570843f},
doi = {10.1109/TWC.2024.3382192},
issn = {15361276 (ISSN)},
year = {2024},
date = {2024-01-01},
journal = {IEEE Transactions on Wireless Communications},
volume = {23},
number = {9},
pages = {11444–11460},
abstract = {In this paper a novel joint sensing, communication, and artificial intelligence (AI) framework is proposed so as to optimize extended reality (XR) experiences over terahertz (THz) wireless systems. Within this framework, active reconfigurable intelligent surfaces (RISs) are incorporated as pivotal elements, serving as enhanced base stations in the THz band to enhance Line-of-Sight (LoS) communication. The proposed framework consists of three main components. First, a tensor decomposition framework is proposed to extract unique sensing parameters for XR users and their environment by exploiting the THz channel sparsity. Essentially, the THz band's quasi-opticality is exploited and the sensing parameters are extracted from the uplink communication signal, thereby allowing for the use of the same waveform, spectrum, and hardware for both communication and sensing functionalities. Then, the Cramér-Rao lower bound is derived to assess the accuracy of the estimated sensing parameters. Second, a non-autoregressive multi-resolution generative AI framework integrated with an adversarial transformer is proposed to predict missing and future sensing information. The proposed framework offers robust and comprehensive historical sensing information and anticipatory forecasts of future environmental changes, which are generalizable to fluctuations in both known and unforeseen user behaviors and environmental conditions. Third, a multi-agent deep recurrent hysteretic Q-neural network is developed to control the handover policy of RIS subarrays, leveraging the informative nature of sensing information to minimize handover cost, maximize the individual quality of personal experiences (QoPEs), and improve the robustness and resilience of THz links. Simulation results show a high generalizability of the proposed unsupervised generative artificial intelligence (AI) framework to fluctuations in user behavior and velocity, leading to a 61% improvement in instantaneous reliability compared to schemes with known channel state information. © 2002-2012 IEEE.},
keywords = {Artificial intelligence, artificial intelligence (AI), Behavioral Research, Channel state information, Computer hardware, Cramer-Rao bounds, Extended reality (XR), Hardware, Joint sensing and communication, Learning systems, machine learning, machine learning (ML), Machine-learning, Multi agent systems, reliability, Resilience, Sensor data fusion, Tera Hertz, Terahertz, terahertz (THz), Terahertz communication, Wireless communications, Wireless sensor networks, X reality},
pubstate = {published},
tppubtype = {article}
}
In this paper a novel joint sensing, communication, and artificial intelligence (AI) framework is proposed so as to optimize extended reality (XR) experiences over terahertz (THz) wireless systems. Within this framework, active reconfigurable intelligent surfaces (RISs) are incorporated as pivotal elements, serving as enhanced base stations in the THz band to enhance Line-of-Sight (LoS) communication. The proposed framework consists of three main components. First, a tensor decomposition framework is proposed to extract unique sensing parameters for XR users and their environment by exploiting the THz channel sparsity. Essentially, the THz band's quasi-opticality is exploited and the sensing parameters are extracted from the uplink communication signal, thereby allowing for the use of the same waveform, spectrum, and hardware for both communication and sensing functionalities. Then, the Cramér-Rao lower bound is derived to assess the accuracy of the estimated sensing parameters. Second, a non-autoregressive multi-resolution generative AI framework integrated with an adversarial transformer is proposed to predict missing and future sensing information. The proposed framework offers robust and comprehensive historical sensing information and anticipatory forecasts of future environmental changes, which are generalizable to fluctuations in both known and unforeseen user behaviors and environmental conditions. Third, a multi-agent deep recurrent hysteretic Q-neural network is developed to control the handover policy of RIS subarrays, leveraging the informative nature of sensing information to minimize handover cost, maximize the individual quality of personal experiences (QoPEs), and improve the robustness and resilience of THz links. Simulation results show a high generalizability of the proposed unsupervised generative artificial intelligence (AI) framework to fluctuations in user behavior and velocity, leading to a 61% improvement in instantaneous reliability compared to schemes with known channel state information. © 2002-2012 IEEE.
Ding, P.; Liu, J.; Sun, M.; Li, L.; Liu, H.
Enhancing Computational Processing Performance for Generative AI Large Models with Autonomous Decision-Making in Metaverse Applications Proceedings Article
In: Proc. - IEEE Int. Conf. Metaverse Comput., Netw., Appl., MetaCom, pp. 253–258, Institute of Electrical and Electronics Engineers Inc., 2024, ISBN: 979-833151599-7 (ISBN).
Abstract | Links | BibTeX | Tags: Adversarial machine learning, AGI (Artificial General Intelligence), Artificial general intelligence, Artificial general intelligences, Autonomous decision, Autonomous Decision-Making, Data assimilation, Data integration, Decisions makings, Digital Twin Technology, Emotion Recognition, Generative adversarial networks, Generative AI large model, Generative AI Large Models, Large models, Metaverse, Metaverses, Model Acceleration, Model Compression, Multi agent systems, Multi-agent systems, Multi-modal data, Multi-Modal Data Integration, Multiagent systems (MASs), Reinforcement Learning, Reinforcement learnings, Spatio-temporal data
@inproceedings{ding_enhancing_2024,
title = {Enhancing Computational Processing Performance for Generative AI Large Models with Autonomous Decision-Making in Metaverse Applications},
author = {P. Ding and J. Liu and M. Sun and L. Li and H. Liu},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85211489063&doi=10.1109%2fMetaCom62920.2024.00048&partnerID=40&md5=ae085a7d90b12c9090f5bf7a274bc7ce},
doi = {10.1109/MetaCom62920.2024.00048},
isbn = {979-833151599-7 (ISBN)},
year = {2024},
date = {2024-01-01},
booktitle = {Proc. - IEEE Int. Conf. Metaverse Comput., Netw., Appl., MetaCom},
pages = {253–258},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {We explore how to enhance the computational processing performance for generative AI large models with autonomous decision-making in metaverse applications. We first introduce the relationship between AI large models and the Metaverse. We elaborate on the application scenarios of generative AI large models in Metaverse, including real-time weather simulation, embodied intelligence of agents, dynamic environment interaction, and user emotion recognition. We then propose the method of Multi-Dimensional Optimization Generation Framework (MDOGF) to improve computational processing performance. The experiment results show great improvement in computational processing performance. © 2024 IEEE.},
keywords = {Adversarial machine learning, AGI (Artificial General Intelligence), Artificial general intelligence, Artificial general intelligences, Autonomous decision, Autonomous Decision-Making, Data assimilation, Data integration, Decisions makings, Digital Twin Technology, Emotion Recognition, Generative adversarial networks, Generative AI large model, Generative AI Large Models, Large models, Metaverse, Metaverses, Model Acceleration, Model Compression, Multi agent systems, Multi-agent systems, Multi-modal data, Multi-Modal Data Integration, Multiagent systems (MASs), Reinforcement Learning, Reinforcement learnings, Spatio-temporal data},
pubstate = {published},
tppubtype = {inproceedings}
}
We explore how to enhance the computational processing performance for generative AI large models with autonomous decision-making in metaverse applications. We first introduce the relationship between AI large models and the Metaverse. We elaborate on the application scenarios of generative AI large models in Metaverse, including real-time weather simulation, embodied intelligence of agents, dynamic environment interaction, and user emotion recognition. We then propose the method of Multi-Dimensional Optimization Generation Framework (MDOGF) to improve computational processing performance. The experiment results show great improvement in computational processing performance. © 2024 IEEE.
Bojić, L.; Ðapić, V.
The Interplay of Social and Robotics Theories in AGI Alignment: Navigating the Digital City Through Simulation-based Multi-Agent Systems Proceedings Article
In: N., Zdravkovic; University, Belgrade Tadeusa Koscuska 63 Belgrade Metropolitan; D., Domazet; University, Tadeusa Koscuska 63 Belgrade Belgrade Metropolitan; S., Lopez-Pernas; of Eastern Finland, Yliopistokatu-2 Joensuu University; M.A., Conde; de Vegazana S/N University of Leon, Leon Campus; P., Vijayakumar (Ed.): CEUR Workshop Proc., pp. 58–63, CEUR-WS, 2024, ISBN: 16130073 (ISSN).
Abstract | Links | BibTeX | Tags: Artificial general intelligence, Artificial general intelligences, Autonomous agents, Decision making, Decision theory, Decisions makings, Human values, Intelligent Agents, Language Model, Large language model, large language models, Multi agent systems, Philosophical aspects, Robotic theory, Robotics, Robotics Theories, Simulation based approaches, Simulation platform, Simulation-Based Approach, Smart city, Social Theories, Social theory, Theoretical framework, Virtual cities, Virtual Reality
@inproceedings{bojic_interplay_2024,
title = {The Interplay of Social and Robotics Theories in AGI Alignment: Navigating the Digital City Through Simulation-based Multi-Agent Systems},
author = {L. Bojić and V. Ðapić},
editor = {Zdravkovic N. and Belgrade Tadeusa Koscuska 63 Belgrade Metropolitan University and Domazet D. and Tadeusa Koscuska 63 Belgrade Belgrade Metropolitan University and Lopez-Pernas S. and Yliopistokatu-2 Joensuu University of Eastern Finland and Conde M.A. and Leon Campus de Vegazana S/N University of Leon and Vijayakumar P.},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85193478708&partnerID=40&md5=6a9fd04d5bbf8b876ba508bef1c09076},
isbn = {16130073 (ISSN)},
year = {2024},
date = {2024-01-01},
booktitle = {CEUR Workshop Proc.},
volume = {3676},
pages = {58–63},
publisher = {CEUR-WS},
abstract = {This study delves into the task of aligning Artificial General Intelligence (AGI) and Large Language Models (LLMs) to societal and ethical norms by using theoretical frameworks derived from social science and robotics. The expansive adoption of AGI technologies magnifies the importance of aligning AGI with human values and ethical boundaries. This paper presents an innovative simulation-based approach, engaging autonomous’digital citizens’ within a multi-agent system simulation in a virtual city environment. The virtual city serves as a platform to examine systematic interactions and decision-making, leveraging various theories, notably, Social Simulation Theory, Theory of Reasoned Action, Multi-Agent System Theory, and Situated Action Theory. The aim of establishing this digital landscape is to create a fluid platform that enables our AI agents to engage in interactions and enact independent decisions, thereby recreating life-like situations. The LLMs, embodying the personas in this digital city, operate as the leading agents demonstrating substantial levels of autonomy. Despite the promising advantages of this approach, limitations primarily lie in the unpredictability of real-world social structures. This work aims to promote a deeper understanding of AGI dynamics and contribute to its future development, prioritizing the integration of diverse societal perspectives in the process. © 2024 Copyright for this paper by its authors.},
keywords = {Artificial general intelligence, Artificial general intelligences, Autonomous agents, Decision making, Decision theory, Decisions makings, Human values, Intelligent Agents, Language Model, Large language model, large language models, Multi agent systems, Philosophical aspects, Robotic theory, Robotics, Robotics Theories, Simulation based approaches, Simulation platform, Simulation-Based Approach, Smart city, Social Theories, Social theory, Theoretical framework, Virtual cities, Virtual Reality},
pubstate = {published},
tppubtype = {inproceedings}
}
This study delves into the task of aligning Artificial General Intelligence (AGI) and Large Language Models (LLMs) to societal and ethical norms by using theoretical frameworks derived from social science and robotics. The expansive adoption of AGI technologies magnifies the importance of aligning AGI with human values and ethical boundaries. This paper presents an innovative simulation-based approach, engaging autonomous’digital citizens’ within a multi-agent system simulation in a virtual city environment. The virtual city serves as a platform to examine systematic interactions and decision-making, leveraging various theories, notably, Social Simulation Theory, Theory of Reasoned Action, Multi-Agent System Theory, and Situated Action Theory. The aim of establishing this digital landscape is to create a fluid platform that enables our AI agents to engage in interactions and enact independent decisions, thereby recreating life-like situations. The LLMs, embodying the personas in this digital city, operate as the leading agents demonstrating substantial levels of autonomy. Despite the promising advantages of this approach, limitations primarily lie in the unpredictability of real-world social structures. This work aims to promote a deeper understanding of AGI dynamics and contribute to its future development, prioritizing the integration of diverse societal perspectives in the process. © 2024 Copyright for this paper by its authors.
2023
Park, J.; Choi, J.; Kim, S. -L.; Bennis, M.
Enabling the Wireless Metaverse via Semantic Multiverse Communication Proceedings Article
In: Annu. IEEE Commun.Soc. Conf. Sens., Mesh Ad Hoc Commun. Netw. workshops, pp. 85–90, IEEE Computer Society, 2023, ISBN: 21555486 (ISSN); 979-835030052-9 (ISBN).
Abstract | Links | BibTeX | Tags: Deep learning, Extended reality (XR), Federated learning, Fertilizers, Learn+, Learning systems, Metaverse, Metaverses, Modal analysis, Multi agent systems, Multi-agent reinforcement learning, Multi-modal data, Reinforcement Learning, Semantic communication, Semantics, Signal encoding, Signaling game, Split learning, Symbolic artificial intelligence
@inproceedings{park_enabling_2023,
title = {Enabling the Wireless Metaverse via Semantic Multiverse Communication},
author = {J. Park and J. Choi and S. -L. Kim and M. Bennis},
url = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85177465286&doi=10.1109%2fSECON58729.2023.10287438&partnerID=40&md5=b052572fb2f78ce0694c7ae5726c8daf},
doi = {10.1109/SECON58729.2023.10287438},
isbn = {21555486 (ISSN); 979-835030052-9 (ISBN)},
year = {2023},
date = {2023-01-01},
booktitle = {Annu. IEEE Commun.Soc. Conf. Sens., Mesh Ad Hoc Commun. Netw. workshops},
volume = {2023-September},
pages = {85–90},
publisher = {IEEE Computer Society},
abstract = {Metaverse over wireless networks is an emerging use case of the sixth generation (6G) wireless systems, posing unprecedented challenges in terms of its multi-modal data transmissions with stringent latency and reliability requirements. Towards enabling this wireless metaverse, in this article we propose a novel semantic communication (SC) framework by decomposing the metaverse into human/machine agent-specific semantic multiverses (SMs). An SM stored at each agent comprises a semantic encoder and a generator, leveraging recent advances in generative artificial intelligence (AI). To improve communication efficiency, the encoder learns the semantic representations (SRs) of multi-modal data, while the generator learns how to manipulate them for locally rendering scenes and interactions in the metaverse. Since these learned SMs are biased towards local environments, their success hinges on synchronizing heterogeneous SMs in the background while communicating SRs in the foreground, turning the wireless metaverse problem into the problem of semantic multiverse communication (SMC). Based on this SMC architecture, we propose several promising algorithmic and analytic tools for modeling and designing SMC, ranging from distributed learning and multi-agent reinforcement learning (MARL) to signaling games and symbolic AI. © 2023 IEEE.},
keywords = {Deep learning, Extended reality (XR), Federated learning, Fertilizers, Learn+, Learning systems, Metaverse, Metaverses, Modal analysis, Multi agent systems, Multi-agent reinforcement learning, Multi-modal data, Reinforcement Learning, Semantic communication, Semantics, Signal encoding, Signaling game, Split learning, Symbolic artificial intelligence},
pubstate = {published},
tppubtype = {inproceedings}
}
Metaverse over wireless networks is an emerging use case of the sixth generation (6G) wireless systems, posing unprecedented challenges in terms of its multi-modal data transmissions with stringent latency and reliability requirements. Towards enabling this wireless metaverse, in this article we propose a novel semantic communication (SC) framework by decomposing the metaverse into human/machine agent-specific semantic multiverses (SMs). An SM stored at each agent comprises a semantic encoder and a generator, leveraging recent advances in generative artificial intelligence (AI). To improve communication efficiency, the encoder learns the semantic representations (SRs) of multi-modal data, while the generator learns how to manipulate them for locally rendering scenes and interactions in the metaverse. Since these learned SMs are biased towards local environments, their success hinges on synchronizing heterogeneous SMs in the background while communicating SRs in the foreground, turning the wireless metaverse problem into the problem of semantic multiverse communication (SMC). Based on this SMC architecture, we propose several promising algorithmic and analytic tools for modeling and designing SMC, ranging from distributed learning and multi-agent reinforcement learning (MARL) to signaling games and symbolic AI. © 2023 IEEE.
2022
Cossentino, Massimo; Lopes, Salvatore; Sabatucci, Luca
Automatically-Generated Agent Organizations for Flexible Workflow Enactment Proceedings Article
In: Agents and Artificial Intelligence: 13th International Conference, ICAART 2021, Virtual Event, February 4– 6, 2021, Revised Selected Papers, pp. 70–84, Springer International Publishing Cham, 2022.
Abstract | Links | BibTeX | Tags: Agent organisations, Business Process, Dynamic workflow, Multi agent systems, Workflow management
@inproceedings{cossentinoAutomaticallyGeneratedAgentOrganizations2022,
title = {Automatically-Generated Agent Organizations for Flexible Workflow Enactment},
author = { Massimo Cossentino and Salvatore Lopes and Luca Sabatucci},
doi = {10.1007/978-3-031-10161-8_4},
year = {2022},
date = {2022-01-01},
booktitle = {Agents and Artificial Intelligence: 13th International Conference, ICAART 2021, Virtual Event, February 4– 6, 2021, Revised Selected Papers},
pages = {70--84},
publisher = {Springer International Publishing Cham},
abstract = {The use of multi-agent systems for the implementation and management of data-intensive workflows is generally considered a particularly interesting solution. We propose an approach that exploits the definition of processes described with the BPMN language for the automatic generation of agent organisations. To demonstrate the use of our approach, we chose the JaCaMo agent framework for its inherent support of agent organisations described with the MOISE meta-model. The resulting agent organization is built for adapting to different execution context, by self-modifying its structural and functional specification for continuing to fulfil the BP goal. textcopyright 2022, Springer Nature Switzerland AG.},
keywords = {Agent organisations, Business Process, Dynamic workflow, Multi agent systems, Workflow management},
pubstate = {published},
tppubtype = {inproceedings}
}
The use of multi-agent systems for the implementation and management of data-intensive workflows is generally considered a particularly interesting solution. We propose an approach that exploits the definition of processes described with the BPMN language for the automatic generation of agent organisations. To demonstrate the use of our approach, we chose the JaCaMo agent framework for its inherent support of agent organisations described with the MOISE meta-model. The resulting agent organization is built for adapting to different execution context, by self-modifying its structural and functional specification for continuing to fulfil the BP goal. textcopyright 2022, Springer Nature Switzerland AG.
Cossentino, Massimo; Lopes, Salvatore; Sabatucci, Luca
Automatically-Generated Agent Organizations for Flexible Workflow Enactment Proceedings Article
In: Agents and Artificial Intelligence: 13th International Conference, ICAART 2021, Virtual Event, February 4–6, 2021, Revised Selected Papers, pp. 70–84, Springer International Publishing Cham, 2022.
Abstract | Links | BibTeX | Tags: Agent organisations, Business Process, Dynamic workflow, Multi agent systems, Workflow management
@inproceedings{cossentino_automatically-generated_2022,
title = {Automatically-Generated Agent Organizations for Flexible Workflow Enactment},
author = {Massimo Cossentino and Salvatore Lopes and Luca Sabatucci},
doi = {10.1007/978-3-031-10161-8_4},
year = {2022},
date = {2022-01-01},
booktitle = {Agents and Artificial Intelligence: 13th International Conference, ICAART 2021, Virtual Event, February 4–6, 2021, Revised Selected Papers},
pages = {70–84},
publisher = {Springer International Publishing Cham},
abstract = {The use of multi-agent systems for the implementation and management of data-intensive workflows is generally considered a particularly interesting solution. We propose an approach that exploits the definition of processes described with the BPMN language for the automatic generation of agent organisations. To demonstrate the use of our approach, we chose the JaCaMo agent framework for its inherent support of agent organisations described with the MOISE meta-model. The resulting agent organization is built for adapting to different execution context, by self-modifying its structural and functional specification for continuing to fulfil the BP goal. © 2022, Springer Nature Switzerland AG.},
keywords = {Agent organisations, Business Process, Dynamic workflow, Multi agent systems, Workflow management},
pubstate = {published},
tppubtype = {inproceedings}
}
The use of multi-agent systems for the implementation and management of data-intensive workflows is generally considered a particularly interesting solution. We propose an approach that exploits the definition of processes described with the BPMN language for the automatic generation of agent organisations. To demonstrate the use of our approach, we chose the JaCaMo agent framework for its inherent support of agent organisations described with the MOISE meta-model. The resulting agent organization is built for adapting to different execution context, by self-modifying its structural and functional specification for continuing to fulfil the BP goal. © 2022, Springer Nature Switzerland AG.
2021
Cossentino, Massimo; Lopes, Salvatore; Sabatucci, Luca
Automatic Definition of MOISE Organizations for Adaptive Workflows. Proceedings Article
In: ICAART (1), pp. 125–136, 2021.
Abstract | Links | BibTeX | Tags: Agent organisations, Dynamic workflow, Metamodeling, Multi agent systems
@inproceedings{cossentinoAutomaticDefinitionMOISE2021,
title = {Automatic Definition of MOISE Organizations for Adaptive Workflows.},
author = { Massimo Cossentino and Salvatore Lopes and Luca Sabatucci},
doi = {10.5220/0010319201250136},
year = {2021},
date = {2021-01-01},
booktitle = {ICAART (1)},
pages = {125--136},
abstract = {The enactment of dynamic workflows may take advantage of the multi-agent system paradigm. The approach presented in this paper allows exploiting a high-level BPMN process definition to generate an agent organisation that can enact the workflow using different strategies. These are implemented as organisational schemes representing alternative goal decomposition trees. The availability of several equivalent solutions enables the optimisation and adaptation features of the approach. The mapping of the initial workflow to organisations starts with the automatic generation of goals from the BPMN, and it exploits a metamodeling approach to generate MOISE organisation definition. textcopyright 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved},
keywords = {Agent organisations, Dynamic workflow, Metamodeling, Multi agent systems},
pubstate = {published},
tppubtype = {inproceedings}
}
The enactment of dynamic workflows may take advantage of the multi-agent system paradigm. The approach presented in this paper allows exploiting a high-level BPMN process definition to generate an agent organisation that can enact the workflow using different strategies. These are implemented as organisational schemes representing alternative goal decomposition trees. The availability of several equivalent solutions enables the optimisation and adaptation features of the approach. The mapping of the initial workflow to organisations starts with the automatic generation of goals from the BPMN, and it exploits a metamodeling approach to generate MOISE organisation definition. textcopyright 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved
Cossentino, Massimo; Lopes, Salvatore; Sabatucci, Luca
Automatic Definition of MOISE Organizations for Adaptive Workflows. Proceedings Article
In: ICAART (1), pp. 125–136, 2021.
Abstract | Links | BibTeX | Tags: Agent organisations, Dynamic workflow, Metamodeling, Multi agent systems
@inproceedings{cossentino_automatic_2021,
title = {Automatic Definition of MOISE Organizations for Adaptive Workflows.},
author = {Massimo Cossentino and Salvatore Lopes and Luca Sabatucci},
doi = {10.5220/0010319201250136},
year = {2021},
date = {2021-01-01},
booktitle = {ICAART (1)},
pages = {125–136},
abstract = {The enactment of dynamic workflows may take advantage of the multi-agent system paradigm. The approach presented in this paper allows exploiting a high-level BPMN process definition to generate an agent organisation that can enact the workflow using different strategies. These are implemented as organisational schemes representing alternative goal decomposition trees. The availability of several equivalent solutions enables the optimisation and adaptation features of the approach. The mapping of the initial workflow to organisations starts with the automatic generation of goals from the BPMN, and it exploits a metamodeling approach to generate MOISE organisation definition. © 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved},
keywords = {Agent organisations, Dynamic workflow, Metamodeling, Multi agent systems},
pubstate = {published},
tppubtype = {inproceedings}
}
The enactment of dynamic workflows may take advantage of the multi-agent system paradigm. The approach presented in this paper allows exploiting a high-level BPMN process definition to generate an agent organisation that can enact the workflow using different strategies. These are implemented as organisational schemes representing alternative goal decomposition trees. The availability of several equivalent solutions enables the optimisation and adaptation features of the approach. The mapping of the initial workflow to organisations starts with the automatic generation of goals from the BPMN, and it exploits a metamodeling approach to generate MOISE organisation definition. © 2021 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved
2020
Cossentino, Massimo; Lopes, Salvatore; Sabatucci, Luca
A Tool for the Automatic Generation of MOISE Organisations From BPMN. Proceedings Article
In: WOA, pp. 69, 2020.
Abstract | BibTeX | Tags: BPMN, Business Process, Multi agent systems, Self-Adaptive Systems
@inproceedings{cossentinoToolAutomaticGeneration2020,
title = {A Tool for the Automatic Generation of MOISE Organisations From BPMN.},
author = { Massimo Cossentino and Salvatore Lopes and Luca Sabatucci},
year = {2020},
date = {2020-01-01},
booktitle = {WOA},
volume = {1613},
pages = {69},
abstract = {Multi-agent systems proved successful in enacting business processes because of their inner properties (distribution of tasks, collaboration and coordination among agents). MAS adoption in enacting processes becomes even more interesting if they exhibit adaptation capabilities. The proposed approach consists in the automatic generation of a MOISE organisation from the BPMN specification of a business process. This organisation is conceived to support adaptation because of the possibility to adapt its configuration at runtime according to emerging needs. Here, we focus on the tool for processing BPMN specification and generating MOISE organization code.},
keywords = {BPMN, Business Process, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
Multi-agent systems proved successful in enacting business processes because of their inner properties (distribution of tasks, collaboration and coordination among agents). MAS adoption in enacting processes becomes even more interesting if they exhibit adaptation capabilities. The proposed approach consists in the automatic generation of a MOISE organisation from the BPMN specification of a business process. This organisation is conceived to support adaptation because of the possibility to adapt its configuration at runtime according to emerging needs. Here, we focus on the tool for processing BPMN specification and generating MOISE organization code.
Cossentino, Massimo; Lopes, Salvatore; Sabatucci, Luca
A Tool for the Automatic Generation of MOISE Organisations From BPMN. Proceedings Article
In: WOA, pp. 69, 2020.
Abstract | Links | BibTeX | Tags: BPMN, Business Process, Multi agent systems, Self-Adaptive Systems
@inproceedings{cossentino_tool_2020,
title = {A Tool for the Automatic Generation of MOISE Organisations From BPMN.},
author = {Massimo Cossentino and Salvatore Lopes and Luca Sabatucci},
url = {https://ceur-ws.org/Vol-2706/paper11.pdf},
year = {2020},
date = {2020-01-01},
booktitle = {WOA},
volume = {1613},
pages = {69},
abstract = {Multi-agent systems proved successful in enacting business processes because of their inner properties (distribution of tasks, collaboration and coordination among agents). MAS adoption in enacting processes becomes even more interesting if they exhibit adaptation capabilities. The proposed approach consists in the automatic generation of a MOISE organisation from the BPMN specification of a business process. This organisation is conceived to support adaptation because of the possibility to adapt its configuration at runtime according to emerging needs. Here, we focus on the tool for processing BPMN specification and generating MOISE organization code.},
keywords = {BPMN, Business Process, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
Multi-agent systems proved successful in enacting business processes because of their inner properties (distribution of tasks, collaboration and coordination among agents). MAS adoption in enacting processes becomes even more interesting if they exhibit adaptation capabilities. The proposed approach consists in the automatic generation of a MOISE organisation from the BPMN specification of a business process. This organisation is conceived to support adaptation because of the possibility to adapt its configuration at runtime according to emerging needs. Here, we focus on the tool for processing BPMN specification and generating MOISE organization code.
2019
Cossentino, Massimo; Sabatucci, Luca; Lopes, Salvatore
Partial and Full Goal Satisfaction in the MUSA Middleware Proceedings Article
In: Multi-Agent Systems: 16th European Conference, EUMAS 2018, Bergen, Norway, December 6– 7, 2018, Revised Selected Papers 16, pp. 15–29, Springer International Publishing, 2019.
Abstract | Links | BibTeX | Tags: Multi agent systems, Partial goal satisfaction, Self-Adaptive Systems
@inproceedings{cossentinoPartialFullGoal2019,
title = {Partial and Full Goal Satisfaction in the MUSA Middleware},
author = { Massimo Cossentino and Luca Sabatucci and Salvatore Lopes},
doi = {10.1007/978-3-030-14174-5_2},
year = {2019},
date = {2019-01-01},
booktitle = {Multi-Agent Systems: 16th European Conference, EUMAS 2018, Bergen, Norway, December 6– 7, 2018, Revised Selected Papers 16},
pages = {15--29},
publisher = {Springer International Publishing},
abstract = {Classical goal-based reasoning frameworks for agents sup- pose goals are either achieved fully or not achieved at all: unless achieved completely, the agents have failed to address them. This behavior is dif- ferent from how people do and therefore is far from real-world scenarios: in every moment a goal has reached a certain level of satisfaction. This work proposes to extend the classical boolean definition of goal achievement by adopting a novel approach, the Distance to Goal Satis- faction, a metric to measure the distance to the full satisfaction of a logic formula. In this paper we defined and implemented this metric; subsequently, we extended MUSA, a self-adaptive middleware used to engineer a het- erogeneous range of applications. This extension allows solving real sit- uations in which the full achievement represented a limitation.},
keywords = {Multi agent systems, Partial goal satisfaction, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
Classical goal-based reasoning frameworks for agents sup- pose goals are either achieved fully or not achieved at all: unless achieved completely, the agents have failed to address them. This behavior is dif- ferent from how people do and therefore is far from real-world scenarios: in every moment a goal has reached a certain level of satisfaction. This work proposes to extend the classical boolean definition of goal achievement by adopting a novel approach, the Distance to Goal Satis- faction, a metric to measure the distance to the full satisfaction of a logic formula. In this paper we defined and implemented this metric; subsequently, we extended MUSA, a self-adaptive middleware used to engineer a het- erogeneous range of applications. This extension allows solving real sit- uations in which the full achievement represented a limitation.
Cossentino, Massimo; Sabatucci, Luca; Lopes, Salvatore
Partial and full goal satisfaction in the MUSA middleware Proceedings Article
In: Multi-Agent Systems: 16th European Conference, EUMAS 2018, Bergen, Norway, December 6–7, 2018, Revised Selected Papers 16, pp. 15–29, Springer International Publishing, 2019.
Abstract | Links | BibTeX | Tags: Multi agent systems, Partial goal satisfaction, Self-Adaptive Systems
@inproceedings{cossentino_partial_2019,
title = {Partial and full goal satisfaction in the MUSA middleware},
author = {Massimo Cossentino and Luca Sabatucci and Salvatore Lopes},
doi = {10.1007/978-3-030-14174-5_2},
year = {2019},
date = {2019-01-01},
booktitle = {Multi-Agent Systems: 16th European Conference, EUMAS 2018, Bergen, Norway, December 6–7, 2018, Revised Selected Papers 16},
pages = {15–29},
publisher = {Springer International Publishing},
abstract = {Classical goal-based reasoning frameworks for agents sup- pose goals are either achieved fully or not achieved at all: unless achieved completely, the agents have failed to address them. This behavior is dif- ferent from how people do and therefore is far from real-world scenarios: in every moment a goal has reached a certain level of satisfaction. This work proposes to extend the classical boolean definition of goal achievement by adopting a novel approach, the Distance to Goal Satis- faction, a metric to measure the distance to the full satisfaction of a logic formula. In this paper we defined and implemented this metric; subsequently, we extended MUSA, a self-adaptive middleware used to engineer a het- erogeneous range of applications. This extension allows solving real sit- uations in which the full achievement represented a limitation.},
keywords = {Multi agent systems, Partial goal satisfaction, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
Classical goal-based reasoning frameworks for agents sup- pose goals are either achieved fully or not achieved at all: unless achieved completely, the agents have failed to address them. This behavior is dif- ferent from how people do and therefore is far from real-world scenarios: in every moment a goal has reached a certain level of satisfaction. This work proposes to extend the classical boolean definition of goal achievement by adopting a novel approach, the Distance to Goal Satis- faction, a metric to measure the distance to the full satisfaction of a logic formula. In this paper we defined and implemented this metric; subsequently, we extended MUSA, a self-adaptive middleware used to engineer a het- erogeneous range of applications. This extension allows solving real sit- uations in which the full achievement represented a limitation.
2018
Sabatucci, Luca; Lopes, Salvatore; Cossentino, Massimo
MUSA 2.0: A Distributed and Scalable Middleware for User-Driven Service Adaptation Proceedings Article
In: Intelligent Interactive Multimedia Systems and Services 2017 10, pp. 492–501, Springer International Publishing, 2018.
Abstract | Links | BibTeX | Tags: Middleware, Multi agent systems, Self-Adaptive Systems
@inproceedings{sabatucciMUSADistributedScalable2018,
title = {MUSA 2.0: A Distributed and Scalable Middleware for User-Driven Service Adaptation},
author = { Luca Sabatucci and Salvatore Lopes and Massimo Cossentino},
doi = {10.1007/978-3-319-59480-4_49},
year = {2018},
date = {2018-01-01},
booktitle = {Intelligent Interactive Multimedia Systems and Services 2017 10},
pages = {492--501},
publisher = {Springer International Publishing},
abstract = {MUSA is an agent-based middleware for user-driven self-adaptation. It is based on the separation of concerns between user's goals and system's capabilities. This work analyses some architectural problems of the current implementation and illustrates a new architecture based on the agents and artifacts paradigm. textcopyright Springer International Publishing AG 2018.},
keywords = {Middleware, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
MUSA is an agent-based middleware for user-driven self-adaptation. It is based on the separation of concerns between user's goals and system's capabilities. This work analyses some architectural problems of the current implementation and illustrates a new architecture based on the agents and artifacts paradigm. textcopyright Springer International Publishing AG 2018.
Sabatucci, Luca; Lopes, Salvatore; Cossentino, Massimo
MUSA 2.0: A distributed and scalable middleware for user-driven service adaptation Proceedings Article
In: Intelligent Interactive Multimedia Systems and Services 2017 10, pp. 492–501, Springer International Publishing, 2018.
Abstract | Links | BibTeX | Tags: Middleware, Multi agent systems, Self-Adaptive Systems
@inproceedings{sabatucci_musa_2018,
title = {MUSA 2.0: A distributed and scalable middleware for user-driven service adaptation},
author = {Luca Sabatucci and Salvatore Lopes and Massimo Cossentino},
doi = {10.1007/978-3-319-59480-4_49},
year = {2018},
date = {2018-01-01},
booktitle = {Intelligent Interactive Multimedia Systems and Services 2017 10},
pages = {492–501},
publisher = {Springer International Publishing},
abstract = {MUSA is an agent-based middleware for user-driven self-adaptation. It is based on the separation of concerns between user’s goals and system’s capabilities. This work analyses some architectural problems of the current implementation and illustrates a new architecture based on the agents and artifacts paradigm. © Springer International Publishing AG 2018.},
keywords = {Middleware, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
MUSA is an agent-based middleware for user-driven self-adaptation. It is based on the separation of concerns between user’s goals and system’s capabilities. This work analyses some architectural problems of the current implementation and illustrates a new architecture based on the agents and artifacts paradigm. © Springer International Publishing AG 2018.
2017
Cossentino, Massimo; Sabatucci, Luca; Seidita, Valeria
Towards an Approach for Engineering Complex Systems: Agents and Agility. Proceedings Article
In: WOA, pp. 1–6, 2017.
Abstract | BibTeX | Tags: Agile Development, Cyber-Physical Systems, Multi agent systems, Self-Adaptive Systems
@inproceedings{cossentinoApproachEngineeringComplex2017,
title = {Towards an Approach for Engineering Complex Systems: Agents and Agility.},
author = { Massimo Cossentino and Luca Sabatucci and Valeria Seidita},
year = {2017},
date = {2017-01-01},
booktitle = {WOA},
pages = {1--6},
abstract = {The way in which we use and conceive modern software systems is changing. Humans/users are becoming more and more immersed in today complex systems operation, systems interact in a dynamic fashion with the users and with changing and dynamic environments. New design paradigms are necessary. In this paper we propose a first insight to engineering complex physical systems by employing agility and a framework for self-adaptive service composition.},
keywords = {Agile Development, Cyber-Physical Systems, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
The way in which we use and conceive modern software systems is changing. Humans/users are becoming more and more immersed in today complex systems operation, systems interact in a dynamic fashion with the users and with changing and dynamic environments. New design paradigms are necessary. In this paper we propose a first insight to engineering complex physical systems by employing agility and a framework for self-adaptive service composition.
Cossentino, Massimo; Sabatucci, Luca; Seidita, Valeria
Towards an Approach for Engineering Complex Systems: Agents and Agility. Proceedings Article
In: WOA, pp. 1–6, 2017.
Abstract | Links | BibTeX | Tags: Agile Development, Cyber-Physical Systems, Multi agent systems, Self-Adaptive Systems
@inproceedings{cossentino_towards_2017,
title = {Towards an Approach for Engineering Complex Systems: Agents and Agility.},
author = {Massimo Cossentino and Luca Sabatucci and Valeria Seidita},
url = {https://ceur-ws.org/Vol-1867/w1.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {WOA},
pages = {1–6},
abstract = {The way in which we use and conceive modern software systems is changing. Humans/users are becoming more and more immersed in today complex systems operation, systems interact in a dynamic fashion with the users and with changing and dynamic environments. New design paradigms are necessary. In this paper we propose a first insight to engineering complex physical systems by employing agility and a framework for self-adaptive service composition.},
keywords = {Agile Development, Cyber-Physical Systems, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
The way in which we use and conceive modern software systems is changing. Humans/users are becoming more and more immersed in today complex systems operation, systems interact in a dynamic fashion with the users and with changing and dynamic environments. New design paradigms are necessary. In this paper we propose a first insight to engineering complex physical systems by employing agility and a framework for self-adaptive service composition.
2015
Cossentino, Massimo; Lodato, Carmelo; Lopes, Salvatore; Sabatucci, Luca
MUSA: A Middleware for User-driven Service Adaptation. Proceedings Article
In: WOA, pp. 1–10, 2015.
Abstract | BibTeX | Tags: Automatic service composition, Middleware, Multi agent systems, Self-Adaptive Systems
@inproceedings{cossentinoMUSAMiddlewareUserdriven2015,
title = {MUSA: A Middleware for User-driven Service Adaptation.},
author = { Massimo Cossentino and Carmelo Lodato and Salvatore Lopes and Luca Sabatucci},
year = {2015},
date = {2015-01-01},
booktitle = {WOA},
pages = {1--10},
abstract = {One of the current challenges of Service Oriented Engineering is to provide instruments for dealing with dynamic and unpredictable environments and changing user requirements. Traditional approaches based on static workflows provide little support for adapting at runtime the flow of activities. MUSA (Middleware for User-driven Service Adaptation) is a holonic multi-agent system for the self-adaptive composition and orchestration of services in a distributed environment.},
keywords = {Automatic service composition, Middleware, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
One of the current challenges of Service Oriented Engineering is to provide instruments for dealing with dynamic and unpredictable environments and changing user requirements. Traditional approaches based on static workflows provide little support for adapting at runtime the flow of activities. MUSA (Middleware for User-driven Service Adaptation) is a holonic multi-agent system for the self-adaptive composition and orchestration of services in a distributed environment.
Cossentino, Massimo; Lodato, Carmelo; Lopes, Salvatore; Sabatucci, Luca
MUSA: a Middleware for User-driven Service Adaptation. Proceedings Article
In: WOA, pp. 1–10, 2015.
Abstract | Links | BibTeX | Tags: Automatic service composition, Middleware, Multi agent systems, Self-Adaptive Systems
@inproceedings{cossentino_musa_2015,
title = {MUSA: a Middleware for User-driven Service Adaptation.},
author = {Massimo Cossentino and Carmelo Lodato and Salvatore Lopes and Luca Sabatucci},
url = {https://ceur-ws.org/Vol-1382/paper1.pdf},
year = {2015},
date = {2015-01-01},
booktitle = {WOA},
pages = {1–10},
abstract = {One of the current challenges of Service Oriented Engineering is to provide instruments for dealing with dynamic and unpredictable environments and changing user requirements. Traditional approaches based on static workflows provide little support for adapting at runtime the flow of activities. MUSA (Middleware for User-driven Service Adaptation) is a holonic multi-agent system for the self-adaptive composition and orchestration of services in a distributed environment.},
keywords = {Automatic service composition, Middleware, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
One of the current challenges of Service Oriented Engineering is to provide instruments for dealing with dynamic and unpredictable environments and changing user requirements. Traditional approaches based on static workflows provide little support for adapting at runtime the flow of activities. MUSA (Middleware for User-driven Service Adaptation) is a holonic multi-agent system for the self-adaptive composition and orchestration of services in a distributed environment.
2014
Cossentino, Massimo; Nogare, Daniele Dalle; Giancarlo, Raffaele; Lodato, Carmelo; Lopes, Salvatore; Ribino, Patrizia; Sabatucci, Luca; Seidita, Valeria
GIMT: A Tool for Ontology and Goal Modeling in BDI Multi-Agent Design Proceedings Article
In: WOA 2014, Catania, Italy, Sept. 25-26, CEUR, 2014.
Abstract | BibTeX | Tags: Design Process, Multi agent systems, Semantic layer
@inproceedings{cossentinoGIMTToolOntology2014,
title = {GIMT: A Tool for Ontology and Goal Modeling in BDI Multi-Agent Design},
author = { Massimo Cossentino and Daniele Dalle Nogare and Raffaele Giancarlo and Carmelo Lodato and Salvatore Lopes and Patrizia Ribino and Luca Sabatucci and Valeria Seidita},
year = {2014},
date = {2014-01-01},
booktitle = {WOA 2014, Catania, Italy, Sept. 25-26},
volume = {1260},
publisher = {CEUR},
abstract = {Designing and developing BDI multi-agent systems would be facilitated by rising up the level of abstraction to use and by a methodological approach for managing it. To this aim it is common the integration of goal oriented analysis techniques with the design and implementation phases. In this fashion, our experience is that the use of an ontology in the early stages of the process is a great support for subsequent phases: goal modeling, agent design and implementation. However, we are aware that building and maintaining an ontology has to be supported by appropriate tools. This paper proposes GIMT (Goal Identification and Modeling Tool) as a further step towards the creation of a complete methodological approach for developing multi-agent systems to be implemented in the JACAMO framework. GIMT is a CASE tool for supporting ontology building and goal modeling. Besides the advantages offered by an automatic tool, the other novelty of this research is in the mapping between metamodeling based on Model Driven Engineering (MDE) and Domain Specific Modeling Languages (DSMLs) with the Eclipse plug-in development environment.},
keywords = {Design Process, Multi agent systems, Semantic layer},
pubstate = {published},
tppubtype = {inproceedings}
}
Designing and developing BDI multi-agent systems would be facilitated by rising up the level of abstraction to use and by a methodological approach for managing it. To this aim it is common the integration of goal oriented analysis techniques with the design and implementation phases. In this fashion, our experience is that the use of an ontology in the early stages of the process is a great support for subsequent phases: goal modeling, agent design and implementation. However, we are aware that building and maintaining an ontology has to be supported by appropriate tools. This paper proposes GIMT (Goal Identification and Modeling Tool) as a further step towards the creation of a complete methodological approach for developing multi-agent systems to be implemented in the JACAMO framework. GIMT is a CASE tool for supporting ontology building and goal modeling. Besides the advantages offered by an automatic tool, the other novelty of this research is in the mapping between metamodeling based on Model Driven Engineering (MDE) and Domain Specific Modeling Languages (DSMLs) with the Eclipse plug-in development environment.
Cossentino, Massimo; Nogare, Daniele Dalle; Giancarlo, Raffaele; Lodato, Carmelo; Lopes, Salvatore; Ribino, Patrizia; Sabatucci, Luca; Seidita, Valeria
GIMT: A tool for ontology and goal modeling in BDI Multi-Agent Design Proceedings Article
In: WOA 2014, Catania, Italy, Sept. 25-26, CEUR, 2014.
Abstract | Links | BibTeX | Tags: Design Process, Multi agent systems, Semantic layer
@inproceedings{cossentino_gimt_2014,
title = {GIMT: A tool for ontology and goal modeling in BDI Multi-Agent Design},
author = {Massimo Cossentino and Daniele Dalle Nogare and Raffaele Giancarlo and Carmelo Lodato and Salvatore Lopes and Patrizia Ribino and Luca Sabatucci and Valeria Seidita},
url = {https://www.semanticscholar.org/paper/GIMT%3A-A-Tool-for-Ontology-and-Goal-Modeling-in-BDI-Cossentino-Nogare/de04bfabc91ab877465a62719d7f38c5c7c94742},
year = {2014},
date = {2014-01-01},
booktitle = {WOA 2014, Catania, Italy, Sept. 25-26},
volume = {1260},
publisher = {CEUR},
abstract = {Designing and developing BDI multi-agent systems would be facilitated by rising up the level of abstraction to use and by a methodological approach for managing it. To this aim it is common the integration of goal oriented analysis techniques with the design and implementation phases. In this fashion, our experience is that the use of an ontology in the early stages of the process is a great support for subsequent phases: goal modeling, agent design and implementation. However, we are aware that building and maintaining an ontology has to be supported by appropriate tools. This paper proposes GIMT (Goal Identification and Modeling Tool) as a further step towards the creation of a complete methodological approach for developing multi-agent systems to be implemented in the JACAMO framework. GIMT is a CASE tool for supporting ontology building and goal modeling. Besides the advantages offered by an automatic tool, the other novelty of this research is in the mapping between metamodeling based on Model Driven Engineering (MDE) and Domain Specific Modeling Languages (DSMLs) with the Eclipse plug-in development environment.},
keywords = {Design Process, Multi agent systems, Semantic layer},
pubstate = {published},
tppubtype = {inproceedings}
}
Designing and developing BDI multi-agent systems would be facilitated by rising up the level of abstraction to use and by a methodological approach for managing it. To this aim it is common the integration of goal oriented analysis techniques with the design and implementation phases. In this fashion, our experience is that the use of an ontology in the early stages of the process is a great support for subsequent phases: goal modeling, agent design and implementation. However, we are aware that building and maintaining an ontology has to be supported by appropriate tools. This paper proposes GIMT (Goal Identification and Modeling Tool) as a further step towards the creation of a complete methodological approach for developing multi-agent systems to be implemented in the JACAMO framework. GIMT is a CASE tool for supporting ontology building and goal modeling. Besides the advantages offered by an automatic tool, the other novelty of this research is in the mapping between metamodeling based on Model Driven Engineering (MDE) and Domain Specific Modeling Languages (DSMLs) with the Eclipse plug-in development environment.
2013
Ribino, Patrizia; Cossentino, Massimo; Lodato, Carmelo; Lopes, Salvatore; Sabatucci, Luca; Seidita, Valeria
Ontology and Goal Model in Designing BDI Multi-Agent Systems. Proceedings Article
In: WOA@ AI* IA, pp. 66–72, 2013.
Abstract | BibTeX | Tags: Goal-Model, Goal-Oriented Approach, Multi agent systems, Semantic layer
@inproceedings{ribinoOntologyGoalModel2013,
title = {Ontology and Goal Model in Designing BDI Multi-Agent Systems.},
author = { Patrizia Ribino and Massimo Cossentino and Carmelo Lodato and Salvatore Lopes and Luca Sabatucci and Valeria Seidita},
year = {2013},
date = {2013-01-01},
booktitle = {WOA@ AI* IA},
volume = {1099},
pages = {66--72},
abstract = {Nowadays several methodological approaches exist, each of them tightly tied up with the implementation platform supporting it. In this paper we propose an intermediate step toward the definition of a methodological approach for supporting the JACAMO framework. This paper resumes a previous work, focused on modeling BDI organizations, and we now address the requirements analysis phase. In particular, we propose the use of an ontological model and a goal model for representing requirements and the domain formalization respectively. The two portions of design process are connected by a heuristic process that allows to extract goals from the ontological model. The resulting models are also used for completing each other and for enhancing the problem description that is considered an input to our process. In the paper we use the well-known case study of the conference management system for illustrating the proposed portion of process.},
keywords = {Goal-Model, Goal-Oriented Approach, Multi agent systems, Semantic layer},
pubstate = {published},
tppubtype = {inproceedings}
}
Nowadays several methodological approaches exist, each of them tightly tied up with the implementation platform supporting it. In this paper we propose an intermediate step toward the definition of a methodological approach for supporting the JACAMO framework. This paper resumes a previous work, focused on modeling BDI organizations, and we now address the requirements analysis phase. In particular, we propose the use of an ontological model and a goal model for representing requirements and the domain formalization respectively. The two portions of design process are connected by a heuristic process that allows to extract goals from the ontological model. The resulting models are also used for completing each other and for enhancing the problem description that is considered an input to our process. In the paper we use the well-known case study of the conference management system for illustrating the proposed portion of process.
Sabatucci, Luca; Ribino, Patrizia; Lodato, Carmelo; Lopes, Salvatore; Cossentino, Massimo
Goalspec: A Goal Specification Language Supporting Adaptivity and Evolution Proceedings Article
In: Engineering Multi-Agent Systems: First International Workshop, EMAS 2013, St. Paul, MN, USA, May 6-7, 2013, Revised Selected Papers 1, pp. 235–254, Springer Berlin Heidelberg, 2013.
Abstract | Links | BibTeX | Tags: Goal-Oriented Approach, Multi agent systems, Self-Adaptive Systems
@inproceedings{sabatucciGoalspecGoalSpecification2013,
title = {Goalspec: A Goal Specification Language Supporting Adaptivity and Evolution},
author = { Luca Sabatucci and Patrizia Ribino and Carmelo Lodato and Salvatore Lopes and Massimo Cossentino},
doi = {10.1007/978-3-642-45343-4_13},
year = {2013},
date = {2013-01-01},
booktitle = {Engineering Multi-Agent Systems: First International Workshop, EMAS 2013, St. Paul, MN, USA, May 6-7, 2013, Revised Selected Papers 1},
pages = {235--254},
publisher = {Springer Berlin Heidelberg},
abstract = {The characteristic of being autonomous and proactive makes the agents able to explore a wide solution space, that dynamically changes or contains uncertainty. We propose a language for describing system goals that may be injected at run-time into the system. The novelty of our approach consists in decoupling the business goals (what is expected) and their implementation (how to address the desired behavior). Indeed relieving the tension between 'what' and 'how' provides more degrees of freedom to the system. On the occurrence, agents of our system may exploit their features (mainly autonomy and proactivity, but also learning and planning) for getting benefits from a wider solution space. The result is that the system behavior may adapt to the current operating conditions. Moreover, the injection mechanism contributes to reduce the effort in evolving the system. This paper focuses on the goal specification language that is the base for enabling both adaptivity and evolution.},
keywords = {Goal-Oriented Approach, Multi agent systems, Self-Adaptive Systems},
pubstate = {published},
tppubtype = {inproceedings}
}
The characteristic of being autonomous and proactive makes the agents able to explore a wide solution space, that dynamically changes or contains uncertainty. We propose a language for describing system goals that may be injected at run-time into the system. The novelty of our approach consists in decoupling the business goals (what is expected) and their implementation (how to address the desired behavior). Indeed relieving the tension between 'what' and 'how' provides more degrees of freedom to the system. On the occurrence, agents of our system may exploit their features (mainly autonomy and proactivity, but also learning and planning) for getting benefits from a wider solution space. The result is that the system behavior may adapt to the current operating conditions. Moreover, the injection mechanism contributes to reduce the effort in evolving the system. This paper focuses on the goal specification language that is the base for enabling both adaptivity and evolution.
Sabatucci, Luca; Cossentino, Massimo; Lodato, Carmelo; Lopes, Salvatore; Seidita, Valeria
A Possible Approach for Implementing Self-Awareness in JASON. Proceedings Article
In: EUMAS, pp. 68–81, 2013.
Abstract | BibTeX | Tags: Multi agent systems, Self-Adaptive Systems, Self-Awareness
@inproceedings{sabatucciPossibleApproachImplementing2013,
title = {A Possible Approach for Implementing Self-Awareness in JASON.},
author = { Luca Sabatucci and Massimo Cossentino and Carmelo Lodato and Salvatore Lopes and Valeria Seidita},
year = {2013},
date = {2013-01-01},
booktitle = {EUMAS},
volume = {13},
pages = {68--81},
abstract = {In Philosophy, the term awareness is often associated to theories of consciousness and self-referential behavior. In computer science, the awareness is a topic of increasing relevance in both Software Engineering and Artificial Intelligence, being closely related to autonomy and proactiveness. We can distinguish two orders of awareness: the first order is the awareness of the environment also known as context-awareness; conversely, self-awareness is a higher order awareness (knowledge about one's own mental states). Nowadays, many agent oriented languages offer native instruments to implement context-awareness. However, self-awareness is not adequately supported and it requires further considerations. This paper focuses on implementation techniques, based on JASON, for creating software agents able to dynamically reason about their knowledge of the environment, as well as on their missions, capabilities and current execution state.},
keywords = {Multi agent systems, Self-Adaptive Systems, Self-Awareness},
pubstate = {published},
tppubtype = {inproceedings}
}
In Philosophy, the term awareness is often associated to theories of consciousness and self-referential behavior. In computer science, the awareness is a topic of increasing relevance in both Software Engineering and Artificial Intelligence, being closely related to autonomy and proactiveness. We can distinguish two orders of awareness: the first order is the awareness of the environment also known as context-awareness; conversely, self-awareness is a higher order awareness (knowledge about one's own mental states). Nowadays, many agent oriented languages offer native instruments to implement context-awareness. However, self-awareness is not adequately supported and it requires further considerations. This paper focuses on implementation techniques, based on JASON, for creating software agents able to dynamically reason about their knowledge of the environment, as well as on their missions, capabilities and current execution state.