Chalmers Open Digital Repository

Välkommen till Chalmers öppna digitala arkiv!

Här hittar du:

Studentarbeten utgivna på lärosätet, såväl kandidatarbeten som examensarbeten på grund- och masternivå
Digitala specialsamlingar, som t ex Chalmers modellkammare
Utvalda projektrapporter

Forskningspublikationer, rapporter och avhandlingar hittar du i research.chalmers.se

Enheter i Chalmers ODR

Välj en enhet för att se alla samlingar.

Visar 1 - 2 av 2

Senast publicerade

Integration of a field tested PEMFC into a research test bench, calculating theoretical operating solutions for the cooling system
(2026) Yaushev, Arthur
Analysis of the product compositions of hydrotreated bio-oils
(2026) Trapp, Sofie
LLM-Assisted Requirements Decomposition in Automotive Software Engineering - A Case Study at Volvo Cars
(2026) Nam Hoàng, Nhât; Rååd, Melker
Requirements decomposition in automotive software engineering is a complex and context-dependent activity that requires architectural understanding, abstraction level judgement, and domain expertise. Although Large Language Models (LLMs) have shown potential in several software engineering tasks, their use for requirements decomposition in safety-critical automotive contexts remains insufficiently understood. This thesis investigates how LLM-based assistants can support requirements decom position in automotive software engineering through a case study at Volvo Cars. The study follows a Design Science Research methodology combining semi-structured interviews, iterative artefact development, and industrial evaluation with domain experts. The resulting human-in-the-loop artefact combines contextual grounding through standards, historical decompositions, and system-structure information with hierarchy guidance, structured prompt orchestration, and schema-constrained generation. The artefact was evaluated through benchmark-based assessments, contextual evaluations using participant-selected requirements, and qualitative feedback sessions with automotive domain experts. The results suggest that LLM-based assistants can support requirements decomposition by reducing cognitive effort, improving contextual awareness, and providing alternative decomposition perspectives during refinement. The evaluation further indicates that contextual grounding, hierarchy guidance, and structured orchestration positively influenced expert-perceived out put quality and reviewability. At the same time, important limitations remain related to abstraction-level consistency, incomplete contextual understanding, and the need for expert validation in safety-critical engineering contexts. The findings suggest that LLM-based decomposition assistants are most useful as decision-support tools within human-in-the-loop workflows rather than as autonomous requirement generation systems.
Self-supervised Representation Learning for LiDAR Point Clouds - A Design Science Study of a Self-Supervised Model for Perception in Autonomous Driving
(2026) Kronberg, Mariam; Eriksson, Ylva
Autonomous driving systems are large, complex software systems where accurate environmental perception is foundational to safe navigation. Perception systems often rely heavily on supervised deep learning models trained on large volumes of manually annotated datasets, resulting in performance heavily tied to the quality of the annotations. Self-supervised learning (SSL) offers a promising alternative by deriving supervisory signals directly from raw, unlabeled data, yet its application to LiDAR point clouds of autonomous driving data remains largely underexplored. We investigate whether a JEPA-based architecture, adapted to operate on LiDAR data, can learn high-quality representations without manual labels, and what that implies for the autonomous driving system during its evolution. We examine the meaning for software quality as well as the impact on the engineering process of building and updating the system. Through an iterative design process, we find that our SSL model substantially outperforms a fully supervised baseline in low label-budget regimes, and that fine-tuning the pre-trained backbone recovers nearly identical detection performance under the full label budget. Our results suggest that SSL pre-training is a viable architectural strategy for reducing annotation dependency and improving maintainability through backbone reuse, though these benefits come with meaningful upfront engineering complexity that should be weighed in practice.
Software-Engineered Human-AIAnnotation Systems for Safety-Critical Perception Pipelines
(2026) Lin, Qiqi; Kokum Mutludogan, Sezin
AI-assisted annotation systems are increasingly used to support perception data generation for autonomous and ML-enabled systems. While modern AI models can improve annotation efficiency and detection coverage, integrating multiple AI components into human-in-the-loop workflows also introduces architectural tradeoffs related to functional correctness, performance efficiency, maintainability, human cognitive workload, and usability. Existing research often focuses primarily on model-level accuracy, while the broader impact of workflow orchestration and human-AI interaction remains less explored. This thesis investigates how different architectural design patterns influence the behavior and quality attributes of AI-assisted annotation systems. Building upon architectural design patterns for ML-enabled systems, six human-AI annotation variants were designed and evaluated, including sequential, parallel, single-model, and VLM-assisted workflows. A modular annotation platform integrating YOLO11n, OWL-ViT, VLM-based prompt generation, and human validation was developed following a design science research approach. The evaluation combined controlled annotation experiments and a complementary user study. Functional correctness, maintainability, performance efficiency, annotation consistency, human intervention effort, and cognitive workload were analyzed across architectural variants using both quantitative metrics and qualitative feedback from participants. The results demonstrated that no single architectural variant optimized all evaluated quality attributes simultaneously. The Parallel variant improved detection diversity and recall but increased cognitive workload and interaction complexity. The Sequential variant reduced cognitive effort and improved usability through simplified validation-oriented interaction, although it introduced stronger dependency propagation and orchestration complexity. The findings further showed that increasing architectural complexity or adding additional AI components does not automatically improve overall effectiveness. Overall, the thesis highlights that evaluating ML-enabled human-AI systems requires considering not only predictive performance, but also maintainability, interaction design, human oversight, and long-term sustainability. The findings provide practical architectural recommendations for future AI-assisted perception annotation systems.