European industry has been very competitive on the global markets by utilizing highly efficient Artificial Intelligence (AI) tools and massively producing high quality products. The advent for mass customization has been stressing the capability of modularization and flexibility of production processes through the incorporation of AI technologies. However, the communication between the different automation systems has not been yet accomplished efficiently since they lack interoperability and are restricted to their own system of coordination. The MAS4AI proposal proposes a system that allows the deployment and synchronization of different AI agents in manufacturing for autonomous modular production and human assistance. The MAS4AI system will be heavily driven by large industrial cases and will aim towards digitalising European industry with AI tools according to the Industry 4.0 paradigm. MAS4AI will develop its overall ambition by the means of four Scientific and Technological objectives namely: a) Multi-Agents-System (MAS) for distributing AI components in different hierarchy layers, customers and suppliers for realising refurbishment activities, b) AI agents using Knowledge-based Representation with Semantic Web Technologies, c) AI Agents for hierarchical planning of production processes, d) model-based Machine Learning (ML) AI agent. MAS4AI research and technological activity will be strongly driven by a set of industrial use cases which will be then used as demonstrators. The demonstrators involve important industrial sectors of high value added for Europe, namely AI technologies used for automotive, contract manufacturing, bicycle industry, bearings production and wood processing industry.

The digitalization of industry opens the path for mass customization but requires leveraging the existing manufacturing ecosystems and establishing a collaborative manufacturing environment. DIMOFAC project will enable the modularity, adaptability and responsiveness of a production line by the integration of Plug-and-Produce modules in a Closed-Loop Lifecycle Management System, for continuous production adaptation, optimization and improvement, in a fast and flexible manner. Reconfigurability is achieved by implementing a Digital Twin of each module and by deploying Digital Thread linking product and process dataflow, enabling seamless secure communication throughout the product lifecycle in factory and connecting it to the management systems in conformance to RAMI4.0. The DIMOFAC consortium is issued from the leading European open initiatives on smart manufacturing, leveraging know-how from past and running EU projects such as INTEGRADDE, COMMUNION, HIMALAIA, BRAINPORT, iM²AM, MIDIH, MARKET 4.0 and building upon a pre-existing network of open DIHs and competence centers such as SMART FACTORY KL, PICTIC, FFLOR, AFH, MANUHUB@WG. Partners will further extend their services and networks to leverage on the increased flexibility brought by modular production systems. Six industrial pilot lines, with multi-material manufacturing, additive manufacturing and assembly capabilities, will enable to demonstrate DIMOFAC Modular Factory Solution, with reconfiguration time reduction of production lines, up to 75% expected for interactive displays (SCHALTAG), 50% for cosmetic, aeronautic and additive manufacturing (ALBEA, EIRE COMPOSITES and SCULPTEO); 30% for shavers (PHILIPS) and industrial modules (VDL). A key result will be the network of open pilot lines, offering R&T and services supporting process validation and implementation in EU SMEs, Midcaps and large organisations in different sectors, spreading knowledge, awareness and adoption of DIMOFAC Modular Factory Solution.

Human robot collaboration (HRC) has evolved to address the need for flexible production, presenting however drawbacks such as: Inability to cover all applications, Low performance/quality of collaboration and Complexity. SHERLOCK aims to introduce the latest safe robotic technologies in production environments, enhancing them with smart mechatronics and AI based cognition, creating efficient HRC stations that are designed to be safe and guarantee the acceptance/wellbeing of operators. SHERLOCK’s objectives are driven by production requirements involving: 1. Soft Robotics Collaborative Production Station: Starting from a human safety basis: - AURA a high payload collaborative manipulator - Smart exoskeletons with adjustable operation - Safe mobile dual arm manipulators 2. Human - centred interaction, collaboration and awareness by developing - Interfaces inspiring trust/familiarity, allowing seamless HR interaction - Methods for assessing user impact of HRC systems - Design principles/standards to maintain operator psychological safety/wellbeing in HRC - Production setups for people with special restrictions exploiting the robot’s cognition 3. AI enabled cognition for autonomous HRC applications: enabling robots to understand their environment, reason over it and adapt by: -Multi-level perception for process and environment assessment - Safe workspace monitoring systems - Autonomous planning and coordination of human robot tasks - Interactive learning, adapting to operator and simplifying teaching of new tasks 4. Modules for design and certification of Safe HRC applications: - Automated Risk Assessment tools within design/simulation packages - VR/AR tools for validating collaborative operations - reducing certification time - Software tools for Formal on-line safety assessment - AR/VR training methods specialized for HRC SHERLOCK will demonstrate its result in 4 sectors: elevators, industrial modules, aeronautics structures and machine tools production.