Chalmers Open Digital Repository

Welcome to Chalmers Open Digital Repository!

Here you can find:

Student theses and papers
Digital special collections, such as Chalmers modellkammare
Selected project reports

Research publications, reports and dissertations can be found in research.chalmers.se

Communities in Chalmers ODR

Select a community to browse its collections.

Now showing 1 - 2 of 2

Recent Submissions

Learning-Enhanced Nonlinear Model Predictive Control for Battery Thermal Management Systems
(2026) McCauley, Daniel Joseph; Kula, Lech Kazimierz
Battery thermal management (BTM) systems in electric vehicles are required to regulate the temperature of the battery powering the vehicle. Model predictive control (MPC) is an optimization-based control strategy that has proven useful in nonlinear control tasks across many different domains, and is therefore a promising candidate for BTM. However, battery thermal management systems are difficult to model due to nonlinearities, and simplified control models that do not fully capture the true dynamics are often employed, which can result in reduced control performance. In this thesis, an adaptive control framework is proposed for learning model residuals using a neural network. The learned residuals are used within the control model of the controller, resulting in a control model that adapts to the system. Specifically, the neural network is trained using two distinct loss functions, resulting in two distinct adaptive controllers. Both adaptive controllers are compared against a nominal controller relying solely on a physics-based model, on both matched and mismatched systems. The framework is initially tested on a benchmark reference tracking cascaded tank system, where it successfully learns the mismatch in dynamics and achieves improved closed-loop control performance. The framework is subsequently evaluated for both reference tracking and economic MPC formulations in BTM systems. For reference tracking, the adaptive controllers yielded mixed results, in some scenarios decreasing cost by up to 44 %, whereas in other scenarios increasing cost by up to 409 %. Similarly the root-mean-squared tracking error was reduced in some cases, and substantially increased in others. In economic MPC, the adaptive controller achieved cost reductions of 23 % to 35 % for all mismatched models, while incurring up to 11 % higher cost in a scenario with a matched model. Model adaptation via neural network residuals is therefore not automatically beneficial, as the approach is sensitive to the loss design, hyperparameters, and the training data. The proposed framework does improve performance in some scenarios, and enhancing its robustness and generalizability warrants further investigation.
Strictly-Local Multi-Agent Formation Control via BC-Anchored Reinforcement Learning
(2026) Cai, Yihuai
Multi-robot formation control requires a group of robots to coordinate under limited communication and local sensing in order to form desired geometric structures. Classical artificial-potential or spring-based controllers are interpretable and stable, but are difficult to turn directly into trainable closed-loop neural policies. In contrast, learning formation behavior directly with multi-agent reinforcement learning often suffers from symmetry-induced local optima, unstable reward shaping, and poor exploration. This thesis studies strict-local self-organization for multi-robot formation control, where each robot observes only local relative geometry, local edge-distance information, and its own role encoding, without access to global target vectors or centralized planning. We propose a controller-guided learning framework that combines DAgger behavior cloning with Multi-Agent Proximal Policy Optimization (MAPPO) refinement. A local spring controller is first constructed from the desired pairwise distances of the target template and used as the teacher policy. A graph neural network with recurrent memory is then trained on the closed-loop state distribution induced by the learned policy. Finally, MAPPO refines the policy using a formation-stress reward aligned with the teacher controller, while a frozen behavior-cloning policy serves as an MSE anchor to prevent destructive policy drift. The target shape is conveyed entirely through the desired pairwise distance on local communication edges, so a single policy can switch between formations without any global goal vector. Experiments demonstrate that the proposed method achieves stable formation on 10- robot multi-shape tasks, reaching succ@0.4d = 0.998 and succ@0.25d = 0.987 across triangular, hexagonal, circular, and rectangular-grid target formations. Using a single model per team size, trained on all of its target formations, the method retains partial scaling on the non-circular formations: succ@0.4d = 0.965 and succ@0.25d = 0.617 for the 21-robot system, and succ@0.4d = 0.525 and succ@0.25d = 0.254 for the 28-robot system. Large circular formations, however, remain unsolved at these larger team sizes, suggesting an empirical feasibility boundary of fixed-local formation control: the approach handles shapes that stay locally observable at the chosen communication scale, but struggles when the target geometry becomes globally sparse relative to the communication radius.
Prototype Based Segmentation of Bone Tissue Microscopy Images
(2026) Hellström, Matilda
Segmentation of microscopy images serves as a fundamental task within the field of biomedical research and clinical analysis. This thesis investigates whether pretrained self-supervised Vision Transformers, ViTs, can be used for prototype based similarity segmentation of unlabeled bone tissue microscopy images. The framework developed and presented utilizes pretrained DINOv2 backbones to extract feature embeddings from microscopy image patches. Positive and negative reference points are used to construct prototype embeddings, enabling similarity based segmentation within the learned feature space. To evaluate how model capacity influences the learned feature space and segmentation performance, all available DINOv2 backbone sizes were included in the experiments. Feature space visualizations and prototype transfer experiments further enabled evaluation of representation quality as well as the robustness and generalization capabilities of the proposed framework. In addition, the DINO heatmaps were used as input to a U-Net to investigate whether they could improve segmentation quality in supervised learning. The results show that pretrained ViTs extract feature representations in which tissue and background regions become partially separable within the learned feature space. PCA and UMAP visualizations indicate, together with clustering metrics, that structurally similar image patches tend to form clusters in the embedding space. The Giant backbone achieved the strongest segmentation performance with a mean dice score of 0.690 and an IoU of 0.534. Prototype transfer performed well within the same sample (mean dice score of 0.644), but performance decreased when transferring prototypes across samples (mean dice score of 0.542), indicating that the framework is sensitive to biological variability and domain shift. Providing a U-Net with the DINO output for refinement improved the dice scores while also reducing boundary alignment errors. The study demonstrates that pretrained self-supervised Vision Transformers can be used for prototype based segmentation of bone tissue microscopy images. Despite being trained on natural RGB images rather than microscopy data, the evaluated DINOv2 backbones produced feature representations that enabled segmentation of bone structures without any task specific training.
The Future of Digital Sales A User-Centered Approach to Develop an Online SaaS Purchasing Experience
(2026) Arvidsson, Måns; Niermann, Lucas
The Business to Business SaaS sales landscape is currently undergoing a transformation as customer behaviors shift away from traditional sales models. Due to its inherent complexity and traditionally lengthy manual purchasing processes, transitioning these customer journeys into a self-service digital environment introduces significant challenges to both providers and customers. To address these challenges, this study examines the specific needs and requirements of B2B SaaS customers. Utilizing a Research through Design approach, it proposes a usercentered solution grounded in usability and cognitive ergonomics theories. Developed for the Swedish SaaS provider Hogia, the study demonstrates how a complex digital purchasing process can be designed and integrated into a broader service system offering.
Utvärdering av en joystickstyrd robotarms noggrannhet och repeterbarhet Vid placering av acetabularkopp för total höftledsartroplastik
(2026) Bellander, Isabelle; Haque, Omeya; Jansson, Anton; Sahan, Bedirhan; Wrångemyr, Elsa
In total hip replacement surgery, the correct positioning and orientation of the acetabular cup, one of the components of the hip prosthesis, is crucial to avoid complications. Conventionally, the placement of the acetabular cup is performed manually by the surgeon, which places high demands on precision and experience; however, with technical aids such as robot-assisted surgery and navigation systems, it is possible to reduce the human factor at critical moments. Thus, the work investigates the position accuracy and repeatability of a joystick-controlled robot arm when steering towards a defined target point. Through experimental and virtual tests, the robot’s properties were simulated and analyzed. The results show that the joystick-controlled robot achieves position accuracy and repeatability within clinical error margins, with programmed movements providing the highest repeatability, while joystick control in combination with a navigation system is sufficiently reliable. The observed deviations are mainly attributed to geometric variations in the 3D-printed tool rather than the robot’s mechanics, which means that the accuracy can be improved through calibration. Future work should focus on improved calibration, more robust tool design, and further integration with clinical systems to enable safe and practical application in real-world surgical settings