List of Topics

FAMER (Facilitating Multi-Party Engineering of Requirements)

Non-functional Requirements for Machine Learning (iNFoRM)

The overall objective of iNFoRM is to create a framework to define, decompose, express, monitor, and reason (make trade-offs) over NFRs for systems involving Machine Learning (ML), accounting for the uniqueness of ML solutions compared to typical software. 

<ol>
<li>Habibullah, Khan Mohammad, Gregory Gay, and Jennifer Horkoff. "A Framework for Managing Quality Requirements for Machine Learning-Based Software Systems."&nbsp;International Conference on the Quality of Information and Communications Technology. Cham: Springer Nature Switzerland, 2024. &nbsp;<a rel="noopener" href="https://link.springer.com/chapter/10.1007/978-3-031-70245-7_1" target="_blank" title="https://link.springer.com/chapter/10.1007/978-3-031-70245-7_1">https://link.springer.com/chapter/10.1007/978-3-031-70245-7_1</a></li>
<li>Habibullah, Khan Mohammad, et al. "Requirements and software engineering for automotive perception systems: an interview study."&nbsp;Requirements Engineering (2024): 1-24. <a rel="noopener" href="https://link.springer.com/article/10.1007/s00766-023-00410-1" target="_blank" title="https://link.springer.com/article/10.1007/s00766-023-00410-1">https://link.springer.com/article/10.1007/s00766-023-00410-1</a></li>
<li>Berglund, Lukas, et al. "Test maintenance for machine learning systems: A case study in the automotive industry."&nbsp;2023 IEEE Conference on Software Testing, Verification and Validation (ICST). IEEE, 2023. <a rel="noopener" href="https://ieeexplore.ieee.org/abstract/document/10132296" target="_blank" title="https://ieeexplore.ieee.org/abstract/document/10132296">https://ieeexplore.ieee.org/abstract/document/10132296</a></li>
</ol>

https://research.chalmers.se/en/project/12085

2025 – 2030
Software testing is a crucial component of the development process. It is also notoriously expensive. Although there is an initial cost associated with creating tests, much more cost is imposed by the need for test maintenance. Automated software tools can reduce the cost and improve the quality of test maintenance. However, despite its importance and cost, there has been little research on automation of test maintenance.

https://research.chalmers.se/en/project/9766

2020 – 2023
Software testing is invaluable in ensuring reliability. It is also difficult and expensive, with serious consequences. Automation is critical in controlling costs and focusing developers. A promising avenue of automation is search-based test generation - the framing of tasks such as input selection as optimization problems. Effective search-based generation relies on the selection of the right strategies to guide the search. Current approaches to search-based generation fail to match the effectiveness of human developers. 

<ol>
<li>Lönnfält, Albin, et al. "An intelligent test management system for optimizing decision making during software testing."&nbsp;Journal of Systems and Software 219 (2025): 112202.&nbsp; <a rel="noopener" href="https://www.sciencedirect.com/science/article/pii/S0164121224002462" target="_blank" title="https://www.sciencedirect.com/science/article/pii/S0164121224002462">https://www.sciencedirect.com/science/article/pii/S0164121224002462</a></li>
<li>Almulla, Hussein, and Gregory Gay. "Learning how to search: generating effective test cases through adaptive fitness function selection."&nbsp;Empirical Software Engineering 27.2 (2022): 38. <a rel="noopener" href="https://link.springer.com/article/10.1007/s10664-021-10048-8" target="_blank" title="https://link.springer.com/article/10.1007/s10664-021-10048-8">https://link.springer.com/article/10.1007/s10664-021-10048-8</a></li>
<li>
Kisso, George, and Farnaz Fotrousi. "Requirements conflicts detection: advancing with conversational ai."&nbsp;2024 IEEE 32nd International Requirements Engineering Conference Workshops (REW). IEEE, 2024. <a href="https://ieeexplore.ieee.org/abstract/document/10628668">https://ieeexplore.ieee.org/abstract/document/10628668</a>
</li>
<li>Kim, Jinhan, Robert Feldt, and Shin Yoo. "Guiding deep learning system testing using surprise adequacy." 2019 IEEE/ACM 41st International Conference on Software Engineering (ICSE). IEEE, 2019. <a href="https://research.chalmers.se/en/publication/513129">https://research.chalmers.se/en/publication/513129&nbsp;</a></li>
</ol>

SAICOM

In future generations of the open standard for radio networks, Open Radio Access Networks (O-RAN), data will be shared between many wireless devices. Artificial Intelligence (AI) in this environment will encounter new challenges due to (i) the limited computing power, bandwidth and energy resources of the devices, (ii) the distribution of software and data across many devices, and (iii) requirements for privacy and security. Current AI borrowed from robotics, computer vision or speech and text recognition is not designed to meet such challenges. This requires a new framework where AI and wireless networks develop in symbiosis. The aim of SAICOM is to contribute to the development of such a framework, with a focus on wireless software-defined networks and applications that depend on the reliability of the wireless connections. To achieve this ambitious goal, SAICOM introduces a research program with three main pillars: AI for the application layer and algorithms for O-RAN; AI for O-RAN software-based protocols that have a major impact on the application layer; and development of a complete AI software pipeline for AI over and within O-RAN. SAICOM aims to deliver breakthrough results directly that will benefit our partners (Ericsson, Hitachi-ABB, Volvo Cars, Electrolux, CEVT, AI Sweden and the City of Stockholm). Thus, SAICOM will contribute to the creation of new AI services for multiple applications, such as transportation, smart grids, smart buildings and smart cities.

<ol>
<li>Dona, Malsha Ashani Mahawatta, Christian Berger, and Yinan Yu. "AirDnD-Asynchronous In-Range Dynamic and Distributed Network Orchestration Framework."&nbsp;2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS). IEEE, 2023. <a href="https://ieeexplore.ieee.org/abstract/document/10272459">https://ieeexplore.ieee.org/abstract/document/10272459</a></li>
<li>Dona, Malsha Ashani Mahawatta, et al. "Tapping in a Remote Vehicle's onboard LLM to Complement the Ego Vehicle's Field-of-View." <a href="https://arxiv.org/abs/2408.10794">https://arxiv.org/abs/2408.10794</a></li>
<li>Habibullah, Khan Mohammad, et al. "Requirements and software engineering for automotive perception systems: an interview study."&nbsp;Requirements Engineering (2024): 1-24. <a rel="noopener" href="https://link.springer.com/article/10.1007/s00766-023-00410-1" target="_blank" title="https://link.springer.com/article/10.1007/s00766-023-00410-1">https://link.springer.com/article/10.1007/s00766-023-00410-1</a></li>
<li>Berglund, Lukas, et al. "Test maintenance for machine learning systems: A case study in the automotive industry."&nbsp;2023 IEEE Conference on Software Testing, Verification and Validation (ICST). IEEE, 2023.<a rel="noopener" href="https://ieeexplore.ieee.org/abstract/document/10132296" target="_blank" title="https://ieeexplore.ieee.org/abstract/document/10132296">https://ieeexplore.ieee.org/abstract/document/10132296</a></li>
</ol>

<ol>
<li>Ranim Khojah, Mazen Mohamad, Philipp Leitner, and Francisco Gomes de Oliveira Neto. 2024. Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice. Proc. ACM Softw. Eng. 1, FSE, Article 81 (July 2024), 22 pages. <a rel="noopener" href="https://doi.org/10.1145/3660788" target="_blank" title="https://doi.org/10.1145/3660788">https://doi.org/10.1145/3660788</a></li>
<li>Ranim Khojah, Francisco Gomes de Oliveira Neto, Mazen Mohamad, and Philipp Leitner. 2024. The Impact of Prompt Programming on Function-Level Code Generation. &nbsp;<a rel="noopener" href="https://arxiv.org/abs/2412.20545" target="_blank" title="https://arxiv.org/abs/2412.20545">https://arxiv.org/abs/2412.20545</a></li>
<li>Götharsson, Malte, et al. "Exploring the Role of Automation in Duplicate Bug Report Detection: An Industrial Case Study."&nbsp;Proceedings of the 5th ACM/IEEE International Conference on Automation of Software Test (AST 2024). 2024. <a href="https://dl.acm.org/doi/abs/10.1145/3644032.3644450">https://dl.acm.org/doi/abs/10.1145/3644032.3644450</a></li>
<li>Lemner, Ludvig, et al. "Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes."&nbsp;<a rel="noopener" href="https://arxiv.org/abs/2409.06416" target="_blank" title="https://arxiv.org/abs/2409.06416">arXiv preprint arXiv:2409.06416</a><a rel="noopener" href="https://arxiv.org/abs/2409.06416" target="_blank" title="https://arxiv.org/abs/2409.06416">&nbsp;(2024)</a>.</li>
<li>Fotrousi, Farnaz and Theocharis Tavantzis. "ReqGenie: GPT-Powered Conversational-AI for Requirements Elicitation." International Conference on Product-Focused Software Process Improvement. Cham: Springer Nature Switzerland, 2024. <a href="https://link.springer.com/chapter/10.1007/978-3-031-78386-9_25">https://link.springer.com/chapter/10.1007/978-3-031-78386-9_25</a></li>
<li>Juyeon Yoon, Robert Feldt, and Shin Yoo, “Intent-Driven Mobile GUI Testing with Autonomous Large Language Model Agents,” 2024 IEEE Conference on Software Testing, Verification, and Validation (ICST), Toronto, Canada, 2024.</li>
</ol>

<ol>
<li>Dona, Malsha Ashani Mahawatta, et al. "Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks." <a href="https://arxiv.org/abs/2408.01433">https://arxiv.org/abs/2408.01433</a></li>
<li>Dona, Malsha Ashani Mahawatta, et al. "LLMs Can Check Their Own Results to Mitigate Hallucinations in Traffic Understanding Tasks."&nbsp;IFIP International Conference on Testing Software and Systems. Cham: Springer Nature Switzerland, 2024. <a href="https://arxiv.org/abs/2409.12580">https://arxiv.org/abs/2409.12580</a></li>
</ol>

1. Khakurel, Jayden, Birgit Penzenstadler, Jari Porras, Antti Knutas, and Wenlu Zhang. "The rise of artificial intelligence under the lens of sustainability." Technologies 6, no. 4 (2018): 100.&nbsp;<a href="https://www.mdpi.com/2227-7080/6/4/100">https://www.mdpi.com/2227-7080/6/4/100</a>
&nbsp;

Lab members

Recent and upcoming events

Contact the AI Engineering Lab

AI Engineering Lab

EN Black Chalmers GU Centr Plate

Choose subject

Course syllabus for

Subject

Each academic year contains different courses

See programme page at universityadmissions.se

Educational area

Permissible substitutions of compulsory courses

To see your programme syllabus – select the academic year in which you started the programme.

[en: page.studyprogrammepage.syllabusesview.coursesdescription]

AI Engineering Lab

List of Topics

Software Engineering for AI

AI for Software Engineering

AI and Robotic Applications

AI for Automotive

Generative AI in Practice

AI Regulations and Guidelines

AI and Security

Human Topics in AI

AI Safety Engineering

AI and Sustainability