Début de thèse : 2023
Fin de thèse : 2026
Date de soutenance prévue : –
Résumé
In modern manufacturing systems, there is a significant potential to adopt connected, adaptive systems to enhance efficiency and promote sustainability. A resilient and adaptive manufacturing ecosystem is essential to cope with increasing levels of sophistication and industrial and environmental requirements. In the view of the Industry of the Future, this demands the adoption of more flexible, adaptable, resilient, and sustainable technologies. Generally speaking, socio-technical systems are used to implement the Industry of the Future which integrates social and technical aspects. This involves deploying adaptive technologies that can quickly and flexibly respond to both endogenous dynamics and exogenous changes.
Multi-Agent Systems (MAS) are promising foundations in socio-technical systems to control manufacturing with their support for decentralization and flexibility. Agents are autonomous entities that make independent decisions and act to achieve their goals. However, their autonomy renders the control of manufacturing systems a challenge; therefore, the regulation of these systems becomes imperative.
In Normative MAS (NMAS), concepts such as norms and sanctions are used to regulate and enforce the behavior of autonomous agents according to the stated desired order. Norm represents the expected behavior of agents and is used to steer the system to the overall objectives. Sanctions are consequences of compliance or violation of the norm and can nudge agents to act conforming to the norms. Integrating these concepts in MAS allows a balance between the agent’s autonomy and system’s regulation.
In this context, the objective of the thesis is to design and develop models and mechanisms for socio-technical MAS able to self-adapt for regulating manufacturing systems for a trustworthy and sustainable Industry of the Future. The thesis focuses on proposing elements (e.g., models, mechanisms, languages) for general socio-technical MAS to achieve flexibility and adaptability in the regulated system. The applicability will be targeted on the manufacturing systems for a trustworthy and sustainable Industry of the Future perspective.
Mots clés
Multiagent Systems, Normative Systems, Responsible AI, Industry of the Future
Partenaires ou/et Financeurs
ANR-FAPESP NAIMAN Project
Objectifs de développement durable concernés
Publications
- As the complexity of software systems rises, the ability to provide explanations of system behavior has become a desirable property for any Artificial Intelligence based system, including autonomous multi-agent systems. While explainability is mainly explored to increase trust and understanding for end-users, it is also an interesting property from a software engineering perspective, supporting developers […]
- Explainability in Multi-Agent Systems (MAS) has emphasized the explanation of the behavior of individual autonomous agents. Since agents in MAS operate under an implicit or explicit organization, explainability must go beyond the individual agents and address the behavior of collectives of agents within an organization. We argue that explainability in MAS should account the different […]
- This paper introduces an anticipatory norm-compliant BDI agent that considers the future consequences of its own behaviour before committing to a goal in the context of a system regulated by norms. The agent simulates the future using explicit models of the environment, itself, and the normative system, checking for norm violations if its plans are […]
- Explainability is increasingly becoming an essential non functional requirement for supporting stakeholders to understand complex systems. In multi-agent systems (MAS), we have previously introduced a multi-level explainability framework to explain the behavior of individual agents. In that framework, explainability is investigated from a software engineering perspective and supports stakeholders playing different roles in the software […]
- In Multi-Agent Systems (MAS), the regulation of agents aims to define a balance between the control of the system and the agents' autonomy. The ability of a MAS to adapt its regulations at run-time is an important feature that enables it to be flexible to changing situations. There is no unique approach to designing such […]
- Despite inter-agent explainability being recognised as a potential enabler of useful dynamics for communication and cooperation in belief-desire-intention (BDI) multi-agent systems, research on explainability has been mostly focused on targeting humans. In this paper, we survey the existing literature on BDI explainability and identify how existing strategies align with the problem of engineering BDI agents […]
- In multi-agent systems (MAS), agents can be governed by regulations. Due to an ever-evolving set of exogenous or endogenous changes, the ability of MAS to adapt regulations becomes crucial. In the MAS literature, there is a lack of comprehensive works defining models to adapt regulations. We propose a general regulation adaptation model for MAS that […]
- Inter-agent explanations are an emerging approach to agent communication that enable agents to share their cognitive processes in order to reach mutual understanding. A key challenge is that agents are often heterogeneous, built on different paradigms and architectures, which makes their internal representations difficult to exchange directly. The Semantic Web offers key technologies, in the […]
- The increasing distribution of autonomous agents incorporating Artificial Intelligence technologies to operate (e.g., perceive, decide, interact, and act) in dynamic shared environments raises the challenge of ensuring their governance without limiting their autonomy. In multi-agent systems (MAS), regulation concepts and mechanisms, such as rules, norms, and sanctions, are usually integrated into what are called normative […]
- Regulating multi-agent system (MAS) to achieve a balance between the autonomy of agents and the control of the system is still a challenge. Regulation management in MAS has been conceptualized from various perspectives in the literature, whose intersections open up a wide range of design options. We propose a unified view on regulation management in […]
Actualités
- Du 25 au 29 mai 2026, l’Institut Fayol de Mines de Saint-Étienne a été largement représenté lors de la 25e édition de la International Conference on Autonomous Agents and Multiagent Systems 2026 (AAMAS 2026), organisée à Paphos. Référence internationale dans … Lire la Suite →
- Les 18 et 19 mars 2026, l’Institut Fayol a participé à la réunion annuelle du collège doctoral franco-allemand SeReCo, organisée cette année à Nuremberg. Financé par l’Université franco-allemande (UFA), le programme SeReCo (Semantics, Reasoning, and Coordination) vise à renforcer la coopération … Lire la Suite →
- L’Institut Fayol a été largement représenté lors de la 28e Conférence européenne sur l’intelligence artificielle (ECAI 2025), organisée du 25 au 30 octobre 2025 dans la ville historique de Bologne (Italie). Soutenu par l’European Association for Artificial Intelligence (EurAI) et … Lire la Suite →
- Du 27 juillet au 18 octobre 2025, Elena Yan, doctorante à l’Institut Fayol de Mines Saint-Étienne, a effectué un séjour de recherche de trois mois au Brésil, marqué par de riches collaborations et de belles réussites. Elle a principalement travaillé … Lire la Suite →
- Elena Yan, doctorante à l’Institut Fayol, membre du Laboratoire d’Informatique, de Modélisation et d’Optimisation des Systèmes (LIMOS) a participé du 29 septembre au 2 octobre 2025 à la conférence « Brazilian Symposium on Databases » et à la « Brazilian Conference on Intelligent Systems », qui … Lire la Suite →
- Ce 2 juillet 2025, la Journée de la Recherche de l’École Doctorale Sciences – Ingénierie – Santé (SIS) s’est tenue sur le campus Manufacture de l’Université Jean Monnet à Saint-Étienne. Cette rencontre annuelle constitue un temps fort pour la communauté doctorale, … Lire la Suite →
- Antoine Zimmermann, chercheur à l’Institut Henri Fayol de Mines Saint-Etienne, IMT et membre du laboratoire LIMOS, a organisé et participé à un workshop le 29 août à Dublin dans le cadre de l’action européenne COST sur les Graphes de Connaissances … Lire la Suite →
- Shervin Ahmadi, (doctorant au département Génie mathématique et industriel), Elena Yan (doctorante au département Informatique et systèmes intelligents) et Mariza Maliqi, (doctorante au département Génie mathématique et industriel) ont présenté leurs travaux de thèse lors du Colloque IMT 2024 dédié … Lire la Suite →