Research and innovation

Applied research for best-in-class applications in tomorrow’s world

We are driven by our passion for high-end software engineering. But our work extends way beyond state-of-the-art software development: we invest in research into innovative technologies and methods. Our agile, self-organised team of research scientists creates technologies that are reliably one step ahead and that lay the foundation for the future of digital innovations.

XITASO is therefore your partner for the entire research and developement value chain: from applied research to the development of mature innovative products and platforms.

International scientific excellence and close dialogue with the community are integral parts of our day-to-day research. They are the mainstays of our innovative strength and the secret of our achievement.

“We are pioneers of innovative cutting-edge technologies.”

Dr. Jan-Philipp Steghöfer - Ihr Experte für Forschung und Innovation
Dr. Jan-Philipp Steghöfer
Head of R&I
XITASO

Research and innovation for your success

Together with our partners from industry and science, we develop new domains and expand our expertise as part of interdisciplinary research projects:

  • We conduct joint research with industry partners on practical use cases to ensure the relevance and impact of our research
  • Together with research partners from science, we adapt the necessary fundamental technological and methodological knowledge to practical challenges
  • We align our research with sustainable technology trends in the market, which we identify together with our customers, partner organisations and associations

Because: Together we can shift the state of the art!

Main ImageHover Image
BSFZ Siegel
Certification

BSFZ

The BSFZ label certifies the R&D activities of companies that have received at least one positive decision from the Research Allowance Certification Office (BSFZ). This label attests in particular to the company’s internal R&D performance.

Research and innovation at XITASO – learn more about our the priorities of our research projects here:

AI for industrial applications – turning limited data into real value

AI for industrial applications often grapples with unbalanced data that contains relatively few error cases, causing many AI methods to fail. Our research and innovation is geared at generalised AI solutions that can work effectively in this environment, increasing value and avoiding costly test set-ups for data harvesting. Digital innovations play a vital roll here, especially in areas such as knowledge extraction, neurosymbolic AI and contrastive learning.

AI in healthcare and medical technology – clear focus on privacy and reliability 

Harnessing the full potential of AI in healthcare and medical technology will require infrastructure that prioritises data protection and trust. Our research is therefore focused on explainability, data security and the quantification of uncertainties. We embrace applied research and targeted technology development to craft solutions that people can trust and enjoy working with due to increased AI reliability.

Generative AI – trustworthy technological change  

The rise of generative AI (GenAI) is transforming how we use technology and presenting fresh opportunities for digital innovation. But unanswered questions that we are determined to address still remain. AI is unable to reach judgements based on human common sense, so the trustworthiness of generated content is absolutely crucial for us and our customers. Maintaining the security of stored information is another important aspect of our research and innovation. We also investigate the impact of GenAI on XITASO’s core business, namely software development.

Autonomous systems and robotics – ensuring their reliability and ease of use 

Autonomous systems and robots are increasingly integrated into our everyday lives – from delivery robots and automated trains to cars with self-driving capabilities. We conduct purposeful industrial research to investigate ways of improving the safety and efficiency of these technologies.
Our technology development underpins and expands the standards of software solutions from XITASO for autonomous systems, making them safe, reliable, scalable and user-friendly.

Cybersecurity and cryptographic agility – future-proof 

Our IT systems need to remain secure going forward as well. In a connected world, developing strong protection mechanisms to shield sensitive data from new threats and make systems resistant to cyber attacks is absolutely imperative. Digital innovations are essential here, as they enable fresh approaches to secure data processing and encryption. Cryptographic agility is a vital part of this. It ensures that systems can adapt to novel encryption methods if vulnerabilities are identified in current algorithms. With our applied research, we develop practical solutions to make software systems sustainably future proof.

Industry 4.0 and data spaces – improving industry efficiency 

What the Industrial Internet of Things (IoT) will bring to manufacturing and industrial processes is not just a change, but a revolution. It improves connectivity, creates digital twins of physical devices and systems and ensures the smooth data exchange along the entire supply chain.  Developing data spaces encourages this change by enabling the emergence of interoperable applications and leveraging technology development and efficiency within the industry.

Learn more about our research projects and partners here:

Our research team

XITASO Research Team

A selection of our publications

TitleTagsDate
Assessing Model Requirements for Explainable AI: A Template and Exemplary Case StudyADELeS2026
5(0) Shades of Wrong: Disentangling the Wrongness of AI Explanations2026
Exploring Prompts as Mixed Requirements and Solutions Artifacts2026
An Abstraction Is Worth a Thousand Vibes2026
AI-enhanced EEG analysis for clinical decision support in neurology – a mini-review2026
Cooperative perception with V2X: A Systematic Literature ReviewVALISENS2025
KI in der Software-EntwicklungBook2025
Using boundary objects and methodological island (BOMI) modeling in large-scale agile systems development.2025
R-LiViT: A LiDAR-Visual-Thermal Dataset Enabling Vulnerable Road User Focused Roadside PerceptionVALISENS2025
Human-Centered Explainable AI: Creating Explanations that Address Stakeholder Needs2025
Explaining Uncertainty: Exploring the Synergies of Explainable Artificial Intelligence and Uncertainty QuantificationKISPP2025
Challenges in AI Projects for Machinery and Plant Engineering2025
The Components of Collaborative Joint Perception and Prediction – A Conceptual FrameworkVALISENS2025
An Exploratory Study on the Engineering of Security Features2025
Natural Language Processing for Requirements Traceability2025
Towards Effective Complementary Security Analysis using Large Language ModelsAMiQuaSy2025
LGAR: Zero-Shot LLM-Guided Neural Ranking for Abstract Screening in Systematic Literature Reviews2025
Masked Autoencoder Self Pre-Training for Defect Detection in MicroelectronicsMaWiS-KI2025
No Data Left Behind: Exogenous Variables in Long-Term Forecasting of Nursing Staff CapacityKISPP2024
Facilitating skill-based robot programing using the Asset Administration Shell2024
Migrating Software Systems towards Post-Quantum-Cryptography – A Systematic Literature ReviewAMiQuaSy2024
Managing Security Evidence in Safety-Critical Organizations2024
Supporting Meta-model-based Language Evolution and Rapid Prototyping with Automated Grammar Transformation2024
Using Boundary Objects and Methodological Island (BOMI) Modeling in Large-Scale Agile Systems Development2024
A Closer Look at Length-niching Selection and Spatial Crossover in Variable-length Evolutionary Rule Set LearningADELeS2024
Length-niching Selection and Spatial Crossover in Variable-length Evolutionary Rule Set LearningADELeS2024
Systematizing Modeler Experience (MX) in Model-Driven Engineering Success Stories2024
Evaluating the Role of Security Assurance Cases in Agile Medical Device Development2024
Human Factors in Model-Driven Engineering: Future Research Goals and Initiatives for MDE2024
Tracking assets in source code with Security AnnotationsHITSSSE2024
Combining Requirements Enigneering Techniques for the Analysis of a Legacy System2024
Measuring Similarities in Model Structure of Metaheuristic Rule Set LearnersADELeS2024
Where Requirements and Agility Meet: No Man’s Land or a Land of Opportunity? 2024
Contrastive pretraining of regression tasks in reliability forecasting of automotive electronics.MaWiS-KI2023
Automated Extraction of Grammar Optimization Rule Configurations for Metamodel-Grammar Co-evolution2023
Composing Behaviour Trees for Rapid Application Development in Mobile Human-Robot-Collaboration2023
Creating Python-style Domain Specific Languages: A Semi-automated Approach and Intermediate Results2023
Exploiting Meta-Model Structures in the Generation of Xtext Editors.2023
Trustful Model-Based Information Exchange in Collaborative Engineering.2023
CASCADE: An Asset-driven Approach to Build Security Assurance Cases for Automotive Systems.2023
Blended modeling in commercial and open-source model-driven software engineering tools: A systematic study.2023
Processes, Methods, and Tools in Model-based Engineering — A Qualitative Multiple-Case Study2023
FeatRacer: Locating Features Through Assisted Traceability2023
Reliability-Based Aggregation of Heterogeneous Knowledge to Assist Operators in Manufacturing2022
Towards Conceptual and Procedural Models of Operator Knowledge in Industrial Information Models2022
A Closer Look at Sum-based Embedding Aggregation for Knowledge Graphs Containing Procedural Knowledge2022
Identifying security-related requirements in regulatory documents based on cross-project classification2022
Predicting thermal resistance of solder joints based on Scanning Acoustic Microscopy using Artificial Neural NetworksMaWiS-KI2022
CAD-based Grasp and Motion Planning for Process Automation in Fused Deposition ModellingADELeS2021
Knowledge Extraction via Decentralized Knowledge Graph Aggregation2021
Learning Classifier Systems for Self-Explaining Socio-Technical-SystemsADELeS2021
Interactive Knowledge-Guided LearningADELeS2020
Evaluating the Effect of User-Given Guiding Attention on the Learning ProcessADELeS2020
Opportunities and Limitations of Mixed Reality Holograms in Industrial Robotics2020
Towards Automated Parameter Optimization by Persisting Expert KnowledgeADELeS2019
partsival – Collision-based Particle and many-body Simulations on GPUs for Planetary Exploration Systems2018
Jan-Philipp_Management

Are you interested in a collaboration in the field of research and innovation, or do you have questions about our projects?

Then contact our Head of Research & Innovation and find out how we can help you in a no-obligation discussion.

Dr. Jan-Philipp Steghöfer
Tel. +49 821 885 882 374
jan-philipp.steghoefer@xitaso.com