Intro

ASRLab conducts research on the engineering, verification, validation, and dependability of autonomous and intelligent systems.

Our work brings together software engineering, robotics, artificial intelligence, digital twins, and experimental validation to develop methods and tools for building systems that can be systematically tested, evaluated, and trusted.

Research at ASRLab spans both fundamental and applied challenges, with a strong focus on transferring research outcomes into real-world engineering and industrial environments.

1. Autonomous Systems

ASRLab investigates the development and evaluation of autonomous and cyber-physical systems, with applications in robotics, intelligent vehicles, and industrial automation.

Our research addresses how autonomous systems can operate reliably under complex and changing conditions, combining software engineering, control, simulation, and experimental validation.

2. Verification & Validation

Verification and validation are at the core of ASRLab’s research.

We develop approaches for simulation-based testing, fault injection, hardware-in-the-loop experimentation, and systematic validation of autonomous and software-intensive systems.

Our goal is to provide measurable evidence that systems behave as expected before they are deployed in real operational environments.

3. Software Testing & Quality

ASRLab develops methods and platforms for improving the quality, robustness, and reliability of software systems.

Research topics include automated software testing, mutation testing, test optimisation, performance evaluation, fault injection, and AI-assisted testing.

A major focus is the automation of the software testing lifecycle through intelligent tools that support requirements analysis, test generation, optimisation, execution, reporting, and closure.

4. Digital Twin Engineering

ASRLab explores digital twins as engineering and validation environments for complex industrial and cyber-physical systems.

Our research combines system models, simulation, real-world data, and physical experimentation to support scenario-based testing, verification, and continuous system evaluation.

Digital twins are also used to investigate how software, planning strategies, and operational scenarios can be evaluated before they are transferred to physical systems.

5. Trustworthy AI & AI-Assisted Engineering

ASRLab investigates how artificial intelligence can be both used as an engineering tool and systematically evaluated as part of intelligent systems.

Research includes trustworthy AI, AI quality evaluation, AI-assisted software testing, and the use of large language models in software and product development.

A particular focus is on integrating AI into engineering workflows while maintaining traceability, reliability, and systematic validation.

6. Dependability & Reliability

ASRLab studies how the performance, reliability, and dependability of software-intensive and autonomous systems can be measured and improved.

Our work includes reliability estimation, dependability modelling, fault-tolerant systems, robustness evaluation, and analysis of system behaviour under faults and unexpected conditions.

These methods support the development of systems that remain predictable and dependable throughout their operational lifecycle.