This Work in Progress paper introduces the design of an innovative educational system that leverages Artificial Intelligence (AI) to address challenges in physics education. The primary objective is to create a system that dynamically adapts to the individual needs and preferences of students while maintaining user-friendliness for teachers, allowing them to tailor their teaching methods. The emphasis is on fostering motivation and engagement, achieved through the implementation of a gamified virtual environment and a strong focus on personalization. Our aim is to develop a system capable of autonomously generating learning activities and constructing effective learning paths, all under the supervision and interaction of teachers. The generation of learning activities is guided by educational taxonomies that delineate and categorize the cognitive processes involved in these activities. The proposed educational system seeks to address challenges identified by Physics Education Research (PER), which offers valuable insights into how individuals learn physics and provides strategies to enhance the overall quality of physics education. Our specific focus revolves around two crucial aspects: concentrating on the conceptual understanding of physics concepts and processes, and fostering knowledge integration and coherence across various physics topics. These aspects are deemed essential for cultivating enduring knowledge and facilitating practical applications in the field of physics.

In this paper, we propose to share our positive experience about the organization of the yearly European Defence Challenge, from the design to the execution. After a preliminary phase during which the students can follow various webinars, this challenge operates with the following two steps: during the first one, student teams submit a one-page note about a given topic related to the Defence domain. The proposals are evaluated by different experts in the field. Then, some student teams are selected to move on to the second phase of the challenge during which they develop their ideas in a 10-page proposal. Additional events punctuate the challenge, from a webinar at the beginning of the second phase to the award ceremony with invited speakers having different backgrounds, from industry to economics passing by politics. This challenge is hence a good way for students to define their professional plans by discovering a domain, its activities and its stakeholders. This is also a good opportunity to strengthen the synergies between the higher-education institutions and companies and more generally to facilitate the interactions between the actors of an ecosystem.

The fast pace of technological evolution, pushed by the Industry 4.0 and accelerated by the COVID-19, is in contrast with the slow change of the education institutions. Indeed, they struggle to promptly update their programs to be aligned with the labour market needs. In such a dynamic environment, a rethinking of the education design process is fundamental to support schools, universities and learning centres through a faster digitalization of their services. The emerging perspectives in curriculum design propose the use of data to develop and deliver better courses to students taking advantage of technological evolution. In this paper, we attempt to present a framework for using data as a support of education design, with a focus on textual data. The aim is to delineate a framework to exploit Natural Language Processing (NLP) and Named Entity Recognition (NER) techniques in data-driven strategies for designing courses. To support these techniques, we disclose a map of the most relevant concepts that can aid education design and can be mined with NLP.

In this work we tackle the problem of planning grasps for an underactuated gripper which enable it to retrieve target objects from a cluttered environment. Furthermore, we investigate how additional manipulation capabilities of the gripping device, provided by active surfaces on the inside of the fingers, can lead to performance improvement in the grasp execution process. To this end, we employ a simple strategy, in which the target object is `pulled-in' towards the palm during grasping which results in firm enveloping grasps. We show the effectiveness of the suggested methods by means of experiments conducted in a real-world scenario.

Since the introduction of the first prototypes of robotic end-effectors showing manipulation capabilities, much research focused on the design and control of robot hand and grippers. While many studies focus on enhancing the sensing capabilities and motion agility, a less explored topic is the engineering of the surfaces that enable the hand to contact the object. In this paper we present the prototype of the Velvet Fingers smart gripper, a novel concept of end-effector combining the simple mechanics and control of under-actuated devices together with high manipulation possibilities, usually offered only by dexterous robotic hands. This enhancement is obtained thanks to active surfaces, i.e. engineered contact surfaces able to emulate different levels of friction and to apply tangential thrusts to the contacted object. Through the paper particular attention is dedicated to the mechanical implementation, sense drive and control electronics of the device; some analysis on the control algorithms are reported. Finally, the capabilities of the prototype are showed through preliminary grasps and manipulation experiments.

Industrial grippers are often used for grasping, while in-hand re-orientation and positioning are dealt with by other means. Contact surface engineering has been recently proposed as a possible mean to introduce dexterity in simple grippers, as in the Velvet Fingers smart gripper, a novel concept of end-effector combining simple under-actuated mechanics and high manipulation possibilities, thanks to conveyors which are built in the finger pads. This paper undergoes the modeling and control of the active conveyors of the Velvet Fingers gripper which are rendered able to emulate different levels of friction and to apply tangential thrusts to the contacted objects. Through the paper particular attention is dedicated to the mechanical implementation, sense drive and control electronics of the device. The capabilities of the prototype are showed in some grasping and manipulation experiments.

The design of grasping and manipulation systems is one of the most investigated topics in recent robotic and automation engineering. It is a process that has to take into account many development possibilities and to face different trade offs, as that between application possibilities and design complexity. In this work we present the design of a novel end-effector that merges the essential mechanics and control simplicity of underactuated devices, together with the high levels of manipulability usually featured in dexterous robotic hands. To obtain this enhancement, the proposed gripper considers the possibility offered by active surfaces, i.e. engineered contact surfaces able to simulate different levels of friction and to apply tangential thrust to the contacted object. The actual dexterity enhancement is evaluated by an analytical manipulability analysis and some examples of in hand manipulations and grasps are taken into account. A mechanical solution is presented, which implements the proposed idea through the adoption of one DoF active surfaces mounted on the fingers. The proposed solution presents a manipulability index one order of magnitude higher than common grippers.