Skip to content


The learning modules will be implemented in the VET schools over the effective duration of the project, around two and a half years. The VET teachers will receive the Teaching Units (TUs) from the Universities team and implement them with a group of students aged 16 and above. VET teachers will apply a minimum of 2 hours per week on average to this task. The University team will provide technical support through on-demand development meetings, and the TUs will be improved based on feedback from the VET teachers and students. At the end of the implementation period, the VET students and teachers will provide feedback on the TUs, and the University team will integrate agreed modifications and deliver the final version of the TUs. Three main case studies have been considered:

Case study 1

Computer Vision Learning Module

The specific objective of this module is to develop TUs and resources in the field of computer vision. They will be created by the Computer Vision lab of the University of Ljubljana and tested by the Solski Center Velenje, both in Slovenia. Computer Vision (CV) is an important field of Artificial Intelligence, which uses images as input and extracts information from them to make decisions based on their content. Understanding CV methods, concepts, and their pros and cons is important for new generations to successfully adopt them in everyday life and adapt them to new needs.

The TUs will be presented in the form of hands-on activities interlinked with examples of applicability in a wider context, and will be based on Python, PyTorch, OpenCV, Orange, and related tools. Specifically, three learning modules (LM) on CV will be created, and they will cover essential concepts for students to understand the field.

CVLM1 will focus on capturing and curating unbiased and properly distributed data, a crucial step in ensuring the fairness and accuracy of algorithms. The TUs will outline the protocol for collecting, organizing, labelling, and maintaining image datasets to eliminate possible biases. CVLM2 will delve into the important steps of detection and segmentation, which are crucial in most CV systems. This modulewill cover both steps based on the data from CVLM1. CVLM3 will cover tracking and recognition, where the teaching units will show how additional temporal information in a sequence of images can be utilized in tracking scenarios, and how recognition can be applied to people, objects, soft-biometrics modalities, gestures, among others.

Case study 2

Robotics Learning Module

The second case study aims to develop and test robotics teaching units. They will be leaded by the University of A Coruña team and Rodolfo Ucha VET school, both in Spain. The goal is developing TUs that show students how AI provides robots with the ability to adapt and increase their applicability to different tasks and environments.

The TUs will be based on standard methods, tools, and software, including AI frameworks and 3D simulators, with an emphasis on open-source options. The TUs will be organized into three learning modules (LM) again.

RLM1 will introduce students to the basics of autonomous robotics, including types of robots, sensors, and actuators. The RLM2 will cover classical ways of controlling a robot, as well as concepts of control and the relation between perception and control. The third module (CVLM3) will introduce general concepts of machine learning and provide opportunities to develop an intelligent controller for a robot.

The TUs will be designed to provide students with practical experience in applying AI to robotics, with the goal of preparing them for careers in fields that require knowledge and skills related to robotics and AI. It has been agreed to focus the TUs in two main application areas of autonomous robotics of high relevance due to their applicability in real companies and industry: mobile robotics and robotic manipulator. Consequently, the three learning modules will include specific challenges to be solved with these two types of robots.

Case study 3

Ambient Intelligence Learning Module

This case study aims to develop and test TUs in the field of Ambient Intelligence (AmI). They will be devel-oped by the ISLAB group at University of Minho and deployed by the VET school at Caldas das Taipas, both in Portugal. The TUs will cover key concepts related to sensing, actuation and control in intelligent environments, and the ethical im-plications and responsibilities involved in designing context-sensitive solutions. The TUs will be interlinked, providing examples of applicability in a wider context.
As in the previous cases, the TUs will be organized into three learning modules (LM).

The first one (AmILM1) will focus on sensing, covering different sensor classes and types. Additionally, it will introduce Intelligent Environments, including concepts such as Internet of Everything, Internet of Things, and People’s Internet. The second module (AmILM2) will provide an overview of Ambient Intelligence, including pervasive computing, ubiquitous computing, affective computing, usable computing, and intelligent interfaces. It will also cover Ambient Intelligence architecture, perception, reasoning, decision-making, acting, and learning. Finally, AmILM3 will explore various applications of Ambient Intelligence, such as smart cities and assisted living environments, while also addressing safety and ethics concerns such as privacy, data protection, identification, and the legal framework. The TUs will be designed to be inter-linked and applicable in a wider context, using Python, PyTorch, soft senses, and some basic sensors.

These modules will contribute to developing new knowledge on the labour market in sectors such as Industry 5.0 and Smart Environments, as well as enhancing VET students’ digital skills and fostering innovation.