Home / Project / Details
📊 Projekt

KI@MINT

Brandenburgische Technische Universität Cottbus-Senftenberg

KI@MINT

Institution: Brandenburgische Technische Universität Cottbus-Senftenberg Category: Project
Website: https://www.b-tu.de/universitaet/ueber-uns/qualitaet-von-lehre-und-studium/innovative-lehrprojekte/kimint

Short Description

The KI@MINT project at BTU Cottbus-Senftenberg develops practice-oriented teaching offerings to qualify students in Artificial Intelligence. Target groups are students in MINT disciplines as well as professionally qualified individuals. The main benefit for universities lies in creating sustainable, competence-oriented learning environments that enable the application of AI in real engineering contexts through teaching laboratories, an AI learning factory, and digital tools.

General Description

-

Thematic Classification

Subject Areas

  • Computer Science
  • Mechanical Engineering
  • Civil Engineering
  • Production Economics
  • Applied Mathematics
  • Technology in Science and Philosophy
  • Fluorescence Microscopy
  • Automation Technology
  • Neurology (implicit through medical image analysis)
  • Physics (implicit through sensor technology and 3D printing)

Research Fields

  • Artificial Intelligence (AI)
  • Image analysis with weak AI
  • Neural networks
  • Object detection (e.g., with YOLO)
  • AI-based image recognition
  • AI in production economics (learning factory)
  • AI in engineering sciences (civil engineering)
  • Drone control with AI
  • Sensor platforms and AI
  • 3D printing and AI
  • AI for automated processes in Industry 4.0
  • AI for search and rescue operations (e.g., in drowning incidents)
  • AI for medical image analysis (CT, MRI, X-ray images)
  • AI for skin detection (carcinomas)
  • AI for eye detection (cataracts)
  • AI for non-contact temperature measurement
  • AI for material recognition (e.g., screws and nuts)
  • AI for fluorescence microscopy (plastid clusters)
  • AI for process optimization in learning factories
  • AI for flight path planning and image-based localization
  • AI for processing large data sets
  • AI for adaptive neural domain refinement (time-dependent differential equations)

Specializations

  • KI Apprenticeship Lab with drones, sensor platforms, and 3D printers
  • Practice-oriented teaching concept with KI learning factory for production and economic challenges
  • KI competencies in engineering (e.g., civil engineering)
  • Image analysis with weak KI (neural networks, image recognition)
  • KI-based object detection in industrial and medical applications (e.g., skin detection, eye detection, temperature measurement)
  • KI methods in automation technology (e.g., component differentiation)
  • Development of teaching and learning formats with didactic support and educational technological assistance
  • Strengthening KI competencies among study applicants and professionally qualified individuals
  • Use of KI software (e.g., TensorFlow) and technological platforms (e.g., Jupiter Notebooks, HAWKI)
  • Practical delivery of KI fundamentals and applications in MINT programs

Keywords

  • KI@MINT - Artificial Intelligence - Apprenticeship Lab - Practice-Oriented - Engineering - Image Analysis - Learning Factory - Didactics - Digital Platform - Self-Learning Course

Funding

Funding Provider: -
Funding Program: Bundesministerium für Bildung und Forschung
Funding Reference: BMBF-01ZZ2201
Funding Period: 01.22 - 12.25
Project Volume: Nicht verfügbar

Team & Partners

Project Leadership

Prof. Dr. Peer Schmidt (BTU Cottbus-Senftenberg)

Involved Persons

  • Dr. Claudia Börner (Project Management TP 1)
  • Boguslaw Malys (Project Management TP 1)
  • Prof. Michael Breuss (Project Management TP 2)
  • Prof. Douglas Cunningham (Project Management TP 2)
  • Prof. Ulrich Berger (Project Management TP 3)
  • Dr. Marc Gebauer (Project Management TP 3)
  • Prof. Armin Fügenschuh (Project Management TP 4)
  • Prof. Achim Bleicher (Project Management TP 4)
  • Prof. Christian Hentschel (Project Management TP 5)
  • Prof. Silke Michalk (Project Management TP 6)
  • Heike Bartholomäus (Project Management TP 6)
  • Stefan Gohrenz (Bachelor's Program Mechanical Engineering, Bachelor's Thesis within TP 2)
  • Johannes Höna (Master's Program Artificial Intelligence Technology, Master's Thesis within TP 2)
  • Alexander Howel (Bachelor's Program Computer Science, Bachelor's Thesis within TP 2)
  • Patrick Ebert (Bachelor's Program Computer Science, Bachelor's Thesis within TP 2)
  • Dustin Scharf (Bachelor's Program Computer Science, Bachelor's Thesis within TP 2)
  • Slavomíra Schneidereit (Master's Program Mechanical Engineering, Master's Thesis within TP 2)
  • T. Schneidereit (Author Publication within TP 2)
  • S. Gohrenz (Author Publication within TP 2)
  • M. Khan Mohammadi

Affiliated Institutions

-

External Partners

  • Polnische Hochschule (im Rahmen eines KI-Workshops mit polnischen Studierenden)
  • EUNICE-University (Teilnahme an der EUNICE Staff Week)
  • Zentrum der brandenburgischen Hochschulen für Digitale Transformation (ZDT) (Kooperation bei Tagungen und Projekten)
  • Bund-Länder-Initiative "KI in der Hochschulbildung" (Kooperation im Rahmen der Veranstaltung "KI-Lunch")

Project Contents

Goals

  • Development and testing of contemporary, innovative study programs for practice-oriented qualification of specialists in the AI-driven workforce
  • Strengthening AI competencies among students through practice-oriented teaching and learning formats, particularly in engineering and production economics
  • Establishment and utilization of a sustainable AI training lab with technical platforms (drones, sensors, 3D printers) and AI software (e.g., TensorFlow)
  • Promotion of accessibility and enthusiasm for AI topics among prospective students, school pupils, and professionally qualified individuals
  • Development and implementation of didactically sound, competence-oriented teaching concepts with a focus on image analysis, algorithms, and application in real-world problem scenarios

Work Packages

  • TP 1: Innovative teaching and learning formats – didactic support and educational technology assistance
  • TP 2: KI Apprenticeship Lab – Algorithms, technologies, and methods: essential and sustainable
  • TP 3: Practice-oriented teaching concept with a KI Learning Factory
  • TP 4: KI competencies for practice-oriented problem solving in engineering
  • TP 5: Image analysis using weak KI
  • TP 6: Strengthening KI competencies in study and qualification offerings

Methods

  • Practice-oriented teaching and learning methods
  • Didactic support and educational technology assistance
  • Establishment of a KI apprenticeship lab with drones, sensor platforms, and 3D printers
  • Use of KI software (e.g. TensorFlow) for controlling technical systems
  • Development of learning pathways for internships and independent implementation in small groups
  • Practice-oriented teaching concept with a KI learning factory (multi-stage production facility)
  • Integration of KI elements into classical teaching modules on production economics
  • Introduction event followed by micro-projects from engineering
  • Application of KI algorithms and data processing in engineering problems
  • Image analysis using weak KI (neural networks) for image recognition
  • Practical approach to creating and preprocessing training and test data
  • Training and evaluation of neural networks
  • Raising awareness of risks and applications of KI in everyday life
  • Practice-oriented case studies (e.g. skin detector, eye detection, temperature measurement, material differentiation)
  • Development and adaptation of courses for various target groups (students, professionals, applicants)
  • Target group analysis and needs assessment
  • Promotion of permeability and enthusiasm for K

Expected Outcomes

  • Development and testing of contemporary, innovative study programs for the practice-oriented qualification of specialists in the AI-driven working world
  • Establishment of a sustainable AI training lab with drones, sensor platforms, and 3D printers, as well as provision of AI software (e.g., TensorFlow)
  • Creation of an AI learning factory for the practice-oriented transfer of AI solutions in production-economic challenges
  • Implementation of a practice-oriented teaching module in engineering featuring micro-projects for applying AI algorithms and data analysis
  • Development of a course on image analysis with weak AI, including practical application of neural networks for image recognition and data evaluation
  • Strengthening of AI competencies in study and qualification offerings for various target groups (students, professionally qualified individuals, working professionals)
  • Increasing permeability and enthusiasm for MINT study programs through targeted outreach and awareness-raising regarding AI modules
  • Development and implementation of didactic concepts, teaching and learning methods, and digital platforms to support the AI learning process
  • Quality assurance and evaluation processes to ensure the effectiveness and continuous improvement of teaching offerings
  • Institutionalization of project outcomes through transfer measures and integration into the regular teaching activities at BTU Cottbus

Contact

Contact Person: Prof. Dr. Peer Schmidt
Email: vp-lehre@b-tu.de
Project Website: https://www.b-tu.de/universitaet/ueber-uns/qualitaet-von-lehre-und-studium/innovative-lehrprojekte/kimint

Recorded: 2026-01-11
Source: https://www.b-tu.de/universitaet/ueber-uns/qualitaet-von-lehre-und-studium/innovative-lehrprojekte/kimint

Visit Website