Abstract This paper presents an integrated approach combining in-person teaching with digital assessments in a mechanical engineering course, leveraging a blended learning environment to enhance both physical and remote instructions. The primary focus is on addressing challenges associated with digital exams, such as hardware and software limitations, connectivity issues, and the risk of cheating. To mitigate these barriers for digital exams, the paper proposes creating unique exam tasks based on student IDs and employing semi-automatic grading of computer drawings using Python scripts, which streamline the assessment process while ensuring accuracy and fairness. Traditional assessment methods typically involve written exams, computer-based tests, practical labs, oral exams, and project-based assessments. These methods require students to attend exams in person, with activities strictly monitored to prevent cheating. However, this approach highlights the need to transition from traditional methods to digital assessments, focusing on knowledge application rather than simply recalling the information. In order to show the possibility of such a transition, a Computer-Aided Design (CAD) course is employed as a case study, where theoretical knowledge is assessed through digital quizzes and practical skills via design challenges and final exams. By creating unique tasks based on student IDs, the course ensures exam integrity and fairness and still allows students to work on the assigned problem on their own computer device and on their own time schedule. Additionally, a semi-automatic system compares the volumetric properties of student-generated 3D models with reference solutions using Python scripts. This approach significantly reduces manual grading workload while maintaining high assessment standards. The course structure aligns learning activities with desired outcomes through the Constructive Alignment of Biggs et. al. Weekly quizzes handled via Moodle automatically grade the theoretical knowledge of the students, while biweekly tutorials and practical sessions support the transition from theory to practical application. Design challenges, graded and contributing to the final exam score, motivate students and provide continuous feedback and assessment. This dynamic learning environment not only engages students but also enhances the retention of theoretical knowledge and its practical application through digital tools. In conclusion, this paper showcases the successful integration of digital assessment methodologies in mechanical engineering education. By addressing and overcoming challenges early, and aligning learning activities with outcomes, the blended learning approach enhances the educational experience. The strategic use of unique exam tasks and semi-automatic grading systems not only ensures fair and accurate assessments but also prepares students for the demands of the digital age in their professional careers.

The Artificial Intelligence community has long pursued personalized education. Over the past decades, efforts have ranged from automated advisors to Intelligent Tutoring Systems, all aimed at tailoring learning experiences to students' individual needs and interests. Unfortunately, many of these endeavors remained largely theoretical or proposed solutions challenging to implement in real-world scenarios. However, we are now in the era of Large Language Models (LLMs) like ChatGPT, Mistral, or Claude, which exhibit promising capabilities with significant potential to impact personalized education. For instance, ChatGPT 4 can assist students in using the Socratic method in their learning process. Despite the immense possibilities these technologies offer, limited significant results are showcasing the impact of LLMs in educational settings. Therefore, this paper aims to present tools and strategies based on LLMs to address personalized education within online collaborative learning settings. To do so, we propose RAGs (Retrieval-Augmented Generation) agents that could be added to online collaborative learning platforms: a) the Oracle agent, capable of answering questions related to topics and materials uploaded to the platform.; b) the Summary agent, which can summarize and present content based on students' profiles.; c) the Socratic agent, guiding students in learning topics through close interaction.; d) the Forum agent, analyzing students' forum posts to identify challenging topics and suggest ways to overcome difficulties or foster peer collaboration.; e) the Assessment agent, presenting personalized challenges based on students' needs. f) the Proactive agent, analyzing student activity and suggesting learning paths as needed. Importantly, each RAG agent can leverage historical student data to personalize the learning experience effectively. To assess the effectiveness of this personalized approach, we plan to evaluate the use of RAGs in online collaborative learning platforms compared to previous online learning courses conducted in previous years.

This paper reveals various approaches undertaken over more than two decades of teaching undergraduate programming classes at different Higher Education Institutions, in order to improve student activation and participation in class and consequently teaching and learning effectiveness. While new technologies and the ubiquity of smartphones and internet access has brought new tools to the classroom and opened new didactic approaches, lessons learned from this personal long-term study show that neither technology itself nor any single new and often hyped didactic approach ensured sustained improvement of student activation. Rather it needs an integrated yet open approach towards a participative learning space supported but not created by new tools, technology and innovative teaching methods.

Desert ants Cataglyphis spec. monitor inclination and distance covered through force-based sensing in their legs. To transfer this mechanism to legged robots, artificial neural networks are used to determine the inclination angle of an experimental ramp from the motor data of the legs of a commercial hexapod walking robot. It is possible to determine the inclination angle of the ramp based on the motor data of the robot legs read out during a run. The result is independent of the weight and orientation of the robot on the ramp and hence robust enough to serve as an independent odometer.