Experience artificial intelligence.Touch, test, and understand it now.
Training module for machine learning and AI applications in technical practice
Experience the AI workflow
From data collection to real-time applications—all in one system
Computer Vision live
Automatically detect and classify workpieces and objects
Hands-on with real hardware
AI control unit, camera, and accessories for realistic scenarios
Comparison: Traditional vs. AI
Testing control algorithms against reinforcement learning
Digital support for maximum learning success – with the RXLea learning software
With the integrated learning software RXLea, the artificial intelligence project experiments become an interactive learning environment. RXLea guides learners step by step through real-world error scenarios and helps them understand technical concepts, systematically analyze errors, and implement practical solutions.
By combining practical hardware with a digital learning path, RXLea promotes independence and specifically strengthens Decision-making authority – in keeping with the Real Experience LearningInteractive exercises, multimedia content, and automatic result evaluation make learning efficient and motivating.
Digitally supported, experienced in real life.
Insights into our Product
Discover the unique features of our system in detail—modern, versatile, practical, and perfectly tailored to your needs.
Skills for the Practice
Numerous practical scenarios and realistic exercises promote not only technical knowledge but also independent decision-making. The skills acquired enhance confidence and efficiency in everyday work.
Train AI models independently
From data collection to application—a complete workflow in the hands of learners
Using computer vision in industrial settings
Identify workpieces, classify them, and make quality decisions
Compare control technology with AI
Testing classical control and reinforcement learning directly on the same hardware
Interpret data & evaluate results
Accurately interpret data from cameras, sensors, and AI analysis and draw conclusions
Identify errors & derive optimizations
Check model accuracy, improve training data, and optimize the application
Automate quality control
Apply AI-powered testing processes in a realistic production environment
Open system
Flexibly customizable: Can be modified at any time, with numerous interfaces and algorithms from common libraries
Different levels
Versatile—from playful introductions to career-related applications and even your own programming
Ready for the future?
Contact us to learn more and get started with your training!
REAL EXPERIENCE LEARNING
A compact training system brings artificial intelligence to life: learners work with real data, train models, and apply them in practical scenarios. Instead of abstract theory, they are tasked with independently understanding, training, and applying AI—step by step, with full control.
They take on the role of engineers in modern development and production environments. Using a camera, control unit, and graphical user interface, they collect data, classify objects, and verify the AI’s results. In the process, they learn how parameters, data volume, and data quality influence accuracy—and how models are optimized to make reliable decisions.
Afterward, learners observe the AI’s behavior in real time: objects are recognized, quality characteristics are checked, and decisions are automatically derived. They evaluate the impact of their inputs on classification and result quality—and practice critically questioning AI decisions. Errors can be deliberately induced to reveal the limits of the algorithms and foster a deep understanding of opportunities and risks.
RXLea features a modern, user-friendly interface that allows even beginners to get started quickly. Complex tasks are solved with just a few clicks, without a long learning curve.
With RXLea, learners can access content anytime, anywhere. Whether in the classroom, in the lab, or from home—this is how learning is integrated into everyday life.
Realistic simulations, hands-on experiments, and practical exercises make learning engaging and memorable. Theory comes to life and is applied in practice.
RXLea adapts to the needs of teachers and students. Content, modules, and difficulty levels can be customized to ensure the best learning outcomes.
Integrated analytics tools and assessment features help instructors stay on top of things. Learners benefit from direct feedback, clear goals, and additional motivational incentives through gamification methods.
RXLea relies on state-of-the-art technologies that are constantly being refined. This ensures you always stay up to date and benefit from regular updates and innovations.
Listen now & understand the app – our podcast
FAQ - Frequently Asked Questions
Modular and expandable
Can be combined with other AI training systems for flexible scenarios
Ready to use right away
Fully integrated system – ready to go right away
Project Overview
- Implement an AI workflow from data collection through training to real-time application
- Automatically detect and classify workpieces and derive quality decisions
- Flexibly adjust lighting, positioning, and training parameters
- Analyze and evaluate camera and classification data
- Compare control tasks using classical algorithms and machine learning
- Test models, identify sources of error, and optimize them in a targeted manner
Do you have any questions? Let’s talk!
© 2024 – 2026 Lucas-Nülle GmbH
A Practical Introduction to Machine Learning
Train AI models and apply them directly in real time
The training system covers the entire workflow of modern AI models. Learners train their own models using real data and deploy them directly in an application.
Machine learning is relevant. Getting started with training often isn’t.
Too much theory. Not enough practical understanding.
AI quickly becomes abstract
The inner workings of AI often remain invisible
Theory dominates the introduction
Programming is becoming a barrier to entry
The result: terms are learned, but the path from training data to a functioning AI model often remains unclear.
Our Solution: Machine Learning as a Continuous Learning Process
From data sets to real-time applications in a training system.
The system covers all phases of an AI project. Learners collect their own data, configure a neural network, train the model, and test the application directly within the system. This fosters a solid understanding of the possibilities and limitations of machine learning.
Learning Path
This is how learners develop their own AI applications
1. Create your own training data
Learners train their own models for image classification, for example for rock-paper-scissors or object recognition.
2. Configure model
The network structure and training parameters are configured via the graphical user interface. No programming knowledge is required.
3. Train the model
The AI system trains the model directly on the device. Results can be reviewed and adjusted immediately.
4. Test inference
The trained model is applied and evaluated directly, for example for quality control or object recognition.
One training system, multiple applications.
How Machine Learning Is Used
Quality control
Computer vision for visual quality inspection in manufacturing.
Object recognition
Object recognition for robotics applications.
Automation
Integrate AI models into PLC-controlled systems.
Your benefits
What the system does in training
Project-based learning approach
Three progressive learning projects ensure a strong practical focus and a motivating introduction to machine learning.
Complete AI workflow
Data collection, training, optimization, and real-time application come together in a coordinated learning environment.
Training on the Edge
The AI controller with NVIDIA Jetson Xavier NX enables computationally intensive training processes directly on the system.
No programming knowledge required
The graphical user interface lowers the barrier to entry and shifts the focus to understanding core AI concepts.
Open source if needed
Scripts and workflows remain visible. This facilitates the transition from application to understanding and further development.
Mobiles KI-Labor
The case also serves as an experimental station with a defined camera position and a reproducible test environment.
Experience machine learning firsthand
Apply and understand immediately
Learners work with real data, real hardware, and a complete application workflow. This makes AI not just something that is explained, but something that is visible, measurable, and comprehensible.
This is what AI training looks like in practice
Machine Learning in Action
From data collection to inference, all steps are logically interconnected.
Typical use cases
Three learning projects for immediate hands-on experience
A playful introduction with image recognition
The first step involves a motivating project such as Rock-Paper-Scissors. Learners create training data, train a model, and immediately experience how classification works.
Ideal for an easy introduction to datasets, features, and model behavior.
Visual quality inspection during manufacturing
In an industrial application scenario, students develop a model for visual quality control and apply AI directly to a real-world production context.
Practical applications for computer vision, automation, and industrial image processing.
Traffic sign recognition as a complex system
A more challenging project demonstrates how robust object recognition is achieved. It combines data collection, optimization, and real-time application.
Suitable for in-depth exploration of accuracy, generalization, and system behavior.
Incorporate machine learning into your training
We’ll show you exactly how the training system can be used in vocational schools, colleges, or continuing education programs.
Practical AI training
From the beginning to industrial applications
For vocational schools, colleges, and continuing education
From abstract AI to practical understanding
Find out how you can explain machine learning in an accessible way and integrate it step by step into existing training programs.
No-obligation • Personalized consultation • Specific use cases
REAL EXPERIENCE LEARNING
How is technical expertise developed?
Real Experience Learning makes technical content tangible. In the machine learning system, learners build understanding not only through theory, but also through their own data, real training steps, and directly observable results.
Learning with real data, hardware, and software
Train models and review results immediately
Learning paths with GUI, Python, and open source
Develop an understanding of the benefits and limitations of AI
Our Learning World
YOU GUIDE THE LEARNING
Every step, from data collection to real-time inference, is clearly presented in RXLea. No additional software or complex programming required.
Controlled trials
Data collection, training, and evaluation are guided step by step
Model training in the system
AI models are trained and tested directly in RXLea
Evaluate results immediately
Training data, classification, and results are displayed in a single interface
