AIDOaRt - AI-augmented automation for efficient DevOps, a model-based framework for continuous development At RunTime in cyber-physical systems
Divisions:
Research Groups:
Industrial Software Engineering
Software Testing Laboratory
Status:
Start date:
End date:
Many companies are investing significant resources in software development, but the use of Artificial Intelligence (AI) in development and design techniques is still immature. AIDOaRt focuses on supporting the continuous development of embedded systems with artificial intelligence. Built-in systems are all the systems of built-in micro-computers that control our cars, trains, planes and telephones, almost everything in our environment. With AI, the project must be able to support development at all stages, as well as operation, improvement and maintenance of the products. There is thus a strong industrial interest in the project's solutions, as development is made more efficient and cheaper, and in the end they will also benefit the consumer level, in the form of better, cheaper, safer and more sustainable products.
The project aims to support development teams during the automated continuous development of embedded computers using integrated AI-enhanced solutions. The overall AIDOaRT infrastructure must work together with existing data sources, but we must also ensure that systems are designed responsibly and contribute to our confidence in their behavior. AIDOaRT aims to contribute to companies where continuous distribution and operation is the core business. The project's framework will be validated in concrete industrial cases involving complex embedded systems, in Sweden's cases including trains, construction machinery, etc.
AIDOaRt is coordinated by MDH and has a total turnover of € 24.4 million and employs 80 full-time equivalents with academic and industrial researchers, project managers and other staff in our 32 organizations. MDH's total cost for the project is SEK 26.5 million and we have almost 8 full-time equivalent researchers and project managers involved. The funding comes partly from ECSEL-JU and the European Commission, and partly from VINNOVA. Our Swedish partners are Alstom, VCE, RISE and Westermo.
Artificial Intelligence Methods for Optimization of the Software Testing Process With Practical Examples and Exercises (Jul 2022) Sahar Tahvili, Leo Hatvani
Early validation of heterogeneous battery systems in the railway domain (May 2022) Johan Bergelin, Antonio Cicchetti The 16th IEEE Systems Conference 2022 (Syscon 2022)
Machine Learning Testing in an ADAS Case Study Using Simulation-Integrated Bio-Inspired Search-Based Testing (Mar 2022) Mahshid Helali Moghadam, Markus Borg , Mehrdad Saadatmand , Seyed Jalaleddin Mousavirad , Markus Bohlin, Björn Lisper
Using NLP tools to detect ambiguities in system requirements - A comparison study (Mar 2022) Aleksandar Bajceta, Miguel Leon Ortiz, Wasif Afzal, Pernilla Lindberg , Markus Bohlin 5th Workshop on Natural Language Processing for Requirements Engineering @ REFSQ (NLP4RE)
Machine Learning Techniques for Software Vulnerability Prediction: A comparative study (Mar 2022) Gul Jabeen, Sabit Rahim , Wasif Afzal, Dawar Khan , Aftab Ahmed Khan , Zahid Hussain , Tehmina Bibi Applied Intelligence (APIN)
Software Test Results Exploration and Visualization with Continuous Integration and Nightly Testing (Feb 2022) Per Erik Strandberg, Wasif Afzal, Daniel Sundmark International Journal on Software Tools for Technology Transfer (STTT)
