You are here


The AIPlan4EU project will bring AI planning as a first-class citizen in the European AI On-Demand (AI4EU) Platform by developing a uniform, user-centered framework to access the existing planning technology and by devising concrete guidelines for innovators and practitioners on how to use this technology. To do so, we will consider use-cases from diverse application areas that will drive the design and the development of the framework, and include several available planning systems as engines that can be selected to solve practical problems. We will develop a general and planner-agnostic API that will both be served by the AI4EU platform and be available as a resource to be integrated into the users' systems. The framework will be validated on use-cases both from within the consortium and recruited by means of cascade funding; moreover, standard interfaces between the framework and common industrial technologies will be developed and made available.

VALU3S focuses on verification and validation (V&V) of cyber-physical automated systems. VALU3S will investigate methods, tools and concepts that are not only suitable for the evaluation of automated systems but also improve the time and cost of the verification and validation process. Thus, overall, VALU3S aims to design, implement and evaluate state-of-the-art V&V methods and tools that reduce the time and cost needed to verify and validate automated systems with respect to safety, cybersecurity and privacy (SCP) requirements.

The HUBCAP project aims at establishing a cloud-based center of innovation and collaboration among companies, research institutes and competence centers to help SMEs try and adopt Model-Based Design (MBD) technology. It builds on seven established Digital Innovation Hubs (DIHs) in seven European countries, each embedded in its regional innovation ecosystem, offering complementary technical expertise, experimental capabilities, and specialist knowledge in Cyber-Physical Systems (CPS) application domains.

Design and development of a robotic manipulator.

  • Recognizing objects within boxes, planning movements to pick the object and to position it in the proper electroplating bar;
  • Proper integration with the external production (E.g. the MAIS project);
  • Facilitate the learning for new objects, thus reducing the cost for adaptation;

Final clients are coating companies operating complex and heterogeneous coating tasks.

Unmanned Air Vehicles (UAVs) are used to help in search and rescue of people lost in natural environments. UAV-Retina project aims at creating automatic drone platforms that can capture infrared, thermal and visible images from aerial views. Platforms scan accurately the zone of interest optimizing their paths, in order to save energy. By analysing the acquired data they can detect and locate targets, if present.

In AWARD, the ES unit is responsible for the intra-logistic planning of a warehouse using Automated Guided Vehicles and by coordinating the last mile deliveries using drones.

Self-learning planning algorithms, based on academic knowledge and machine learning Techniques

Hybrid architecture;

This project is part of a key workstream activity of the company financing this activity which aims at changing the paradigm of underwater inspections and interventions via a fleet of next-generation drones and advanced ancillary equipments.

Within this project the ES unit will design and develop the Autonomous Reasoning Engine for the subsea robotic platform of the company:

A joint scientific study, funded by Bosch, will investigate the application of safety contracts and safety assessment techniques based on formal methods to the design process of Bosch with the goal of demonstrating their usefulness and suitability in the automotive domain.

Modeling, verification and safety analysis of critical, highly integrated systems.

The Mechanical Automation Integration System is an ambitious project aimed at the development of a platform for the automatic control of electroplating plants. We discovered that for this project, the combination of the planning and the scheduling sub-problems was intractable for existing domain-independent planers.  In the project we developed a very efficient domain-dependent planner in which we coded the knowledge gained from extensive discussions with domain experts.