System engineering view on multi-agent technology for industrial applications: barriers and prospects

Abstract

For over a quarter of a century, multi-agent systems have been considered as one of the most promising technologies for conceptualization, software development and implementation of Artificial Intelligence (AI) solutions. Not so widely but multi-agent technology is also considered as a way of designing complex adaptive systems based on bio-inspired principles of selforganization and evolution. However, in practice, the industry rarely uses multi-agent technology, despite the appearance of new classes of applications for which it is the perfect match, for example, smart cyber-physical systems with digital twins of controlled objects. The paper analyzes the recent anticipations and real achievements in the practical use of multi-agent systems at the industry level. It also identifies the engineering problems that currently impede the extensive industrial implementation of multi-agent systems and technologies as well as the ways to overcome them. Finally, prospects for development of these technologies are evaluated up to the level of industrial implementation.

Implementation of digital twins in the process industry: A systematic literature review of enablers and barriers

“…Environmental issues are reduced through knowledge building. Although the current literature on DTs has not yet reached a mature state and there is a dearth of consolidated methodologies and tools for the development and implementation of DTs in the manufacturing industry Gorodetsky et al, 2020), the first real-world examples of DTs in industry are now emerging. In particular, the use of Industry 4.0 standards enables companies to lay the foundation for the successful development of DTs by implementing a robust and integrated data framework to exchange data between a physical asset and its DT .…”

Digital Twins: Review and Challenges

“…According to Gorodetsky [36], a new use of the MAS technology in Industry 4.0 is arising, consists of converting the already notorious DTs into smarts agents through an agentification method. In this way, the DTs would greatly improve their capabilities, and they would have by inheritance facility to negotiate and interact with other DTs of the same system.…”

Integrated Mobile Robotic Platform Model

“…Задача автономизации техники является сложной, многодисциплинарной и решается, как правило, для множества разных, но взаимосвязанных объектов (агентов), имеющих единую систему управления. При этом одним из аспектов автономизации является киберфизическая интеграция данных единой цифровой платформы с объектами техники, которые рассматриваются как агенты этой базовой мультиагентной системы [1]. Этот факт предполагает взаимодействие не только агентов техники друг с другом, но еще и с агентами других типов (физических, химических, биологических) [2].…”

“…Научно-образовательный центр (НОЦ) «Инженерия будущего» -это межрегиональное объединение вузов 6 субъектов Российской Федерации (Самарской, Пензенской, Тамбовской, Ульяновской, Астраханской областей, Республики Мордовия), призванное объединить науку и реальный сектор экономики 1 . Целью НОЦ является достижение мирового лидерства в научно-технологическом развитии и подготовке кадров по направлениям деятельности центра.…”