Luigi Gargioni
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Luigi Gargioni has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Daniela Fogli
Department of Information Engineering, University of Brescia, Brescia, Italy
10 shared publications - Pietro Baroni
DII, University of Brescia, Italy
4 shared publications - Angela Locoro
Department of Economics and Management, Universitá degli Studi di Brescia, Contrada Santa Chiara, 50, 25122 Brescia, Italy
2 shared publications - Barbara Rita Barricelli
University of Brescia
1 shared publication - Elena Margherita Nava
Department of Information Engineering, University of Brescia, Brescia, Italy
1 shared publication - Rachid Alami
LAAS-CNRS
1 shared publication
Latest Publications
- 28 October 2026
- Published by Springer Nature in Intelligent Service Robotics
- Vol. 19 (6) , 103
A digital twin-enabled environment for end-user development of robot tasks
- 28 October 2026
- Published by Springer Nature in Intelligent Service Robotics
- Vol. 19 (6) , 103
A digital twin-enabled environment for end-user development of robot tasks
- Open Access
- 3 September 2026
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 18 (7) , 94
A Hybrid LLM/Model-Based Architecture for Flexible and Adaptive Robot Coaching
Human-Robot Interaction (HRI) presents significant challenges in accurately assessing situations, adapting robotic behavior to human intentions, ensuring explainability, pertinence, and acceptability, and effectively managing uncertainty. Traditional model-based approaches provide reliability but struggle with human unpredictability, often approximating human behavior through specific models that fail to encompass all possible scenarios. Conversely, statistical approaches, such as Large Language Models (LLMs), offer greater adaptability but lack deterministic guarantees. This paper introduces a hybrid architecture that integrates structured methodologies with the flexibility of LLMs to enhance robotic coaching in dynamic environments. The proposed architecture leverages deterministic modules for critical constraints and safety guarantees while employing LLMs for contextual understanding, natural language interaction, and adaptation to unpredictable human behaviors. Through a healthcare robotic coach scenario implementation and the conduction of a user study, we aim to demonstrate how this balanced approach enables effective monitoring of task execution, dynamic adaptation to human states, and seamless verbal interaction while maintaining system reliability. By bridging deterministic and statistics-based techniques, the proposed architecture aims to advance HRI toward safer, more transparent, flexible, and adaptive interactions.
- 3 September 2026
- Published by Springer Nature in International Journal of Social Robotics
- Vol. 18 (7) , 94
Open AccessA Hybrid LLM/Model-Based Architecture for Flexible and Adaptive Robot Coaching
Human-Robot Interaction (HRI) presents significant challenges in accurately assessing situations, adapting robotic behavior to human intentions, ensuring explainability, pertinence, and acceptability, and effectively managing uncertainty. Traditional model-based approaches provide reliability but struggle with human unpredictability, often approximating human behavior through specific models that fail to encompass all possible scenarios. Conversely, statistical approaches, such as Large Language Models (LLMs), offer greater adaptability but lack deterministic guarantees. This paper introduces a hybrid architecture that integrates structured methodologies with the flexibility of LLMs to enhance robotic coaching in dynamic environments. The proposed architecture leverages deterministic modules for critical constraints and safety guarantees while employing LLMs for contextual understanding, natural language interaction, and adaptation to unpredictable human behaviors. Through a healthcare robotic coach scenario implementation and the conduction of a user study, we aim to demonstrate how this balanced approach enables effective monitoring of task execution, dynamic adaptation to human states, and seamless verbal interaction while maintaining system reliability. By bridging deterministic and statistics-based techniques, the proposed architecture aims to advance HRI toward safer, more transparent, flexible, and adaptive interactions.
- Open Access
- 30 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Journal on Responsible Computing
- Vol. 2 (3) , 1-26
Preparation of Personalized Medicines through Collaborative Robots: A Hybrid Approach to the End-User Development of Robot Programs
Galenic formulations are personalized medicines prepared by pharmacists in their laborato ries. They are produced in small batches considering single patients’ characteristics, such as age, gender, allergies, and the like, thus contributing to responsible health. The production process is performed manually with the support of mechanic machines. This activity is time-consuming, prone to errors, and subject to quality variations. In this paper, we propose the integration of collaborative robots into the galenic formulation process to obtain several advantages, such as increased productivity, reduced variability, improved accuracy, and minimized risks associated with human error. Additionally, the use of robots can alleviate the physical burden on human operators, allowing them to focus on higher-level tasks that require critical thinking and decision-making. To achieve this goal, a software application, called PRAISE (Pharmaceutical Robotic and AI System for End users), has been developed; it is meant to support end users (i.e., pharmacists) in defining robot programs suitable to the case at hand. This application is conceived as an End-User Development (EUD) environment, which implements a hybrid interaction approach based on a natural language interface leveraging Large Language Models and a graphical interface to check and possibly revise the user-created robot programs. A user study carried out with nine pharmacists demonstrates the validity of the approach.
- 30 September 2025
- Published by Association for Computing Machinery (ACM) in ACM Journal on Responsible Computing
- Vol. 2 (3) , 1-26
Open AccessPreparation of Personalized Medicines through Collaborative Robots: A Hybrid Approach to the End-User Development of Robot Programs
Galenic formulations are personalized medicines prepared by pharmacists in their laborato ries. They are produced in small batches considering single patients’ characteristics, such as age, gender, allergies, and the like, thus contributing to responsible health. The production process is performed manually with the support of mechanic machines. This activity is time-consuming, prone to errors, and subject to quality variations. In this paper, we propose the integration of collaborative robots into the galenic formulation process to obtain several advantages, such as increased productivity, reduced variability, improved accuracy, and minimized risks associated with human error. Additionally, the use of robots can alleviate the physical burden on human operators, allowing them to focus on higher-level tasks that require critical thinking and decision-making. To achieve this goal, a software application, called PRAISE (Pharmaceutical Robotic and AI System for End users), has been developed; it is meant to support end users (i.e., pharmacists) in defining robot programs suitable to the case at hand. This application is conceived as an End-User Development (EUD) environment, which implements a hybrid interaction approach based on a natural language interface leveraging Large Language Models and a graphical interface to check and possibly revise the user-created robot programs. A user study carried out with nine pharmacists demonstrates the validity of the approach.
- 1 September 2025
- Published by Springer Nature
- p. 208-222
Empowering Worker-Robot Collaboration: Leveraging LLMs for Extracting and Visualizing Robot Task Metrics
- 1 September 2025
- Published by Springer Nature
- p. 208-222
Empowering Worker-Robot Collaboration: Leveraging LLMs for Extracting and Visualizing Robot Task Metrics
- Open Access
- 1 August 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (8) , 349
AI-Supported EUD for Data Visualization: An Exploratory Case Study
Data visualization is a key activity in data-driven decision making and is gaining momentum in many organizational contexts. However, the role and contribution of both end-user development (EUD) and artificial intelligence (AI) technologies for data visualization and analytics are still not clear or systematically studied. This work investigates how effectively AI-supported EUD tools may assist visual analytics tasks in organizations. An exploratory case study with eight interviews with key informants allowed a deep understanding of data analysis and visualization practices in a large Italian company. It aimed at identifying the various professional roles and competencies necessary in the business context, understanding the data sources and data formats exploited in daily activities, and formulating suitable hypotheses to guide the design of AI-supported EUD tools for data analysis and visualization. In particular, the results of interviews with key informants yielded the development of a prototype of an LLM-based EUD environment, which was then used with selected target users to collect their opinions and expectations about this type of intervention in their work practice and organization. All the data collected during the exploratory case study finally led to defining a set of design guidelines for AI-supported EUD for data visualization.
- 1 August 2025
- Published by MDPI AG in Future Internet
- Vol. 17 (8) , 349
Open AccessAI-Supported EUD for Data Visualization: An Exploratory Case Study
Data visualization is a key activity in data-driven decision making and is gaining momentum in many organizational contexts. However, the role and contribution of both end-user development (EUD) and artificial intelligence (AI) technologies for data visualization and analytics are still not clear or systematically studied. This work investigates how effectively AI-supported EUD tools may assist visual analytics tasks in organizations. An exploratory case study with eight interviews with key informants allowed a deep understanding of data analysis and visualization practices in a large Italian company. It aimed at identifying the various professional roles and competencies necessary in the business context, understanding the data sources and data formats exploited in daily activities, and formulating suitable hypotheses to guide the design of AI-supported EUD tools for data analysis and visualization. In particular, the results of interviews with key informants yielded the development of a prototype of an LLM-based EUD environment, which was then used with selected target users to collect their opinions and expectations about this type of intervention in their work practice and organization. All the data collected during the exploratory case study finally led to defining a set of design guidelines for AI-supported EUD for data visualization.
- Open Access
- 30 June 2025
- Published by MDPI AG in Information
- Vol. 16 (7) , 559
Exploring the Adoption of Collaborative Robots for the Preparation of Galenic Formulations
Galenic preparations are patient-centered medicines prepared by pharmacists or veterinarians, which allow personalizing dosages, overcoming allergy problems, reducing costs, and dealing with rare diseases. However, the current manual production process of galenic preparations poses several challenges to human workers. This paper proposes the use of collaborative robots to help pharmacists carry out the most tiresome, precise, error-prone, and time-consuming tasks. In particular, an end-user development (EUD) environment called PRAISE (pharmaceutical robotic and AI system for end users) has been designed to support pharmacists in programming the tasks to be performed by a collaborative robot. The EUD environment integrates artificial intelligence (AI) features based on large language models but ensures that end users always have complete control over the generated output, that is, a robot program. The paper focuses on the application of a human-centered methodology adopted to design PRAISE by involving representative end users (experts in the pharmaceutical sector) from system ideation to its evaluation. Design implications related to AI-enabled EUD for collaborative robots are the main findings of the paper.
- 30 June 2025
- Published by MDPI AG in Information
- Vol. 16 (7) , 559
Open AccessExploring the Adoption of Collaborative Robots for the Preparation of Galenic Formulations
Galenic preparations are patient-centered medicines prepared by pharmacists or veterinarians, which allow personalizing dosages, overcoming allergy problems, reducing costs, and dealing with rare diseases. However, the current manual production process of galenic preparations poses several challenges to human workers. This paper proposes the use of collaborative robots to help pharmacists carry out the most tiresome, precise, error-prone, and time-consuming tasks. In particular, an end-user development (EUD) environment called PRAISE (pharmaceutical robotic and AI system for end users) has been designed to support pharmacists in programming the tasks to be performed by a collaborative robot. The EUD environment integrates artificial intelligence (AI) features based on large language models but ensures that end users always have complete control over the generated output, that is, a robot program. The paper focuses on the application of a human-centered methodology adopted to design PRAISE by involving representative end users (experts in the pharmaceutical sector) from system ideation to its evaluation. Design implications related to AI-enabled EUD for collaborative robots are the main findings of the paper.
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Emerging approaches to human-robot collaboration in healthcare
Collaborative robots can enhance productivity and efficiency in healthcare. This PhD project aims to investigate new methods and tools for effective interaction with these robots, focusing on programming techniques accessible to domain experts without a background in computer science or robotics. Automating repetitive tasks can allow healthcare professionals to dedicate more attention to critical procedures. For instance, this technology can enhance therapy efficiency and personalized medicine preparation, benefiting patient outcomes. The research will investigate the use of Large Language Models to simplify and optimize robot task programming, reducing the need for technical expertise.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessEmerging approaches to human-robot collaboration in healthcare
Collaborative robots can enhance productivity and efficiency in healthcare. This PhD project aims to investigate new methods and tools for effective interaction with these robots, focusing on programming techniques accessible to domain experts without a background in computer science or robotics. Automating repetitive tasks can allow healthcare professionals to dedicate more attention to critical procedures. For instance, this technology can enhance therapy efficiency and personalized medicine preparation, benefiting patient outcomes. The research will investigate the use of Large Language Models to simplify and optimize robot task programming, reducing the need for technical expertise.
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Towards the Unification of Computational Thinking and EUDability: Two Cases from Healthcare
This paper presents a study about the mapping of the EUDability of End-User Development (EUD) tools with the Computational Thinking (CT) skills of users. This mapping provides an approach to evaluate the suitability of a EUD environment in supporting people performing their daily work while managing and exploiting EUD tools. EUDability is a construct encompassing different dimensions that need to be assessed through a careful scrutiny by human-computer interaction experts, while CT skills should mirror those dimensions from the point of view of assessing the level of ability of users in managing problems with a computational thinking attitude. Moving from the healthcare domain, we present two cases: a tool for geriatric professionals supporting them in the preparation of cognitive exercises for elderly patients; and a tool for pharmacists, which empowers them to create robot programs related to the preparation of personalized medications. These cases have been exploited to show how to unify the EUDability assessment with the CT skills assessment. In particular, the application of the EUDability evaluation method for each tool, as well as the administration of the Computational Thinking Scale to domain experts are shown. The results of the two assessments are reported and discussed, together with the limitations of the present study. The results show the goodness of fit of the proposed EUD tools in the healthcare domain.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-9
Open AccessTowards the Unification of Computational Thinking and EUDability: Two Cases from Healthcare
This paper presents a study about the mapping of the EUDability of End-User Development (EUD) tools with the Computational Thinking (CT) skills of users. This mapping provides an approach to evaluate the suitability of a EUD environment in supporting people performing their daily work while managing and exploiting EUD tools. EUDability is a construct encompassing different dimensions that need to be assessed through a careful scrutiny by human-computer interaction experts, while CT skills should mirror those dimensions from the point of view of assessing the level of ability of users in managing problems with a computational thinking attitude. Moving from the healthcare domain, we present two cases: a tool for geriatric professionals supporting them in the preparation of cognitive exercises for elderly patients; and a tool for pharmacists, which empowers them to create robot programs related to the preparation of personalized medications. These cases have been exploited to show how to unify the EUDability assessment with the CT skills assessment. In particular, the application of the EUDability evaluation method for each tool, as well as the administration of the Computational Thinking Scale to domain experts are shown. The results of the two assessments are reported and discussed, together with the limitations of the present study. The results show the goodness of fit of the proposed EUD tools in the healthcare domain.
- Open Access
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 478-482
Integrating ChatGPT with Blockly for End-User Development of Robot Tasks
This paper presents an End-User Development environment for collaborative robot programming, which integrates Open AI ChatGPT with Google Blockly. Within this environment, a user, who is neither expert in robotics nor in computer programming, can define the items characterizing the application domain (e.g., objects, actions, and locations) and define pick-and-place tasks involving these items. Task definition can be achieved with a combination of natural language and block-based interaction, which exploits the computational capabilities of ChatGPT and the graphical interaction features offered by Blockly, to check the correctness of generated robot programs and modify them through direct manipulation.
- 11 March 2024
- Published by Association for Computing Machinery (ACM)
- p. 478-482
Open AccessIntegrating ChatGPT with Blockly for End-User Development of Robot Tasks
This paper presents an End-User Development environment for collaborative robot programming, which integrates Open AI ChatGPT with Google Blockly. Within this environment, a user, who is neither expert in robotics nor in computer programming, can define the items characterizing the application domain (e.g., objects, actions, and locations) and define pick-and-place tasks involving these items. Task definition can be achieved with a combination of natural language and block-based interaction, which exploits the computational capabilities of ChatGPT and the graphical interaction features offered by Blockly, to check the correctness of generated robot programs and modify them through direct manipulation.