To Örebro University

As district heating networks evolve to meet climate-neutral objectives, optimizing their control under heterogeneous building characteristics and dynamic environmental conditions remains a significant challenge. Traditional control strategies often lack the adaptability necessary to account for building-specific dynamics and to ensure real-time adherence to operational safety constraints. In this work, we present an integrated machine learning-based framework that combines an adaptive context-aware transformer model with deep reinforcement learning to address these limitations. The proposed approach introduces an adaptive context-aware transformer as a predictive environment within a Deep Q-Network (DQN) framework, enabling data-driven, building-specific control of district heating systems. Utilizing real-world data from 148 residential buildings across Sweden and Finland, the model incorporates contextual embeddings and temporal features to predict indoor temperature trajectories with high accuracy, achieving root mean square error values between 0.18-0.24 degrees C for Swedish buildings and 0.26-0.32 degrees C for Finnish buildings. The DQN agent leverages these predictions to optimize heating control while ensuring compliance with operational safety limits and preserving occupant comfort. Experimental results demonstrate significant energy savings, with mid-rise buildings achieving up to 14.85% reduction in energy consumption, and peak seasonal savings exceeding 20% during spring months. This integrated approach illustrates the potential for substantial energy optimization and reliable indoor climate management in future district heating networks.

This study investigates the efficiency and safety outcomes of implementing different adaptive coordination models for automated vehicle (AV) fleets, managed by a centralized coordinator that dynamically responds to human-controlled vehicle behavior. The simulated scenarios replicate an underground mining environment characterized by narrow tunnels with limited connectivity. To address the unique challenges of such settings, we propose a novel metric — Path Overlap Density (POD) — to predict efficiency and potentially the safety performance of AV fleets. The study also explores the impact of map features on AV fleets performance. The results demonstrate that both AV fleet coordination strategies and underground tunnel network characteristics significantly influence overall system performance. While map features are critical for optimizing efficiency, adaptive coordination strategies are essential for ensuring safe operations. 

Transformer-based models have gained increasing popularity for time-series prediction; however, in specific applications such as residential heating systems, static contextual data of buildings is crucial to effectively capture and learn complex environmental dynamics. This paper presents a novel transformer-based model that adapts the contextual meta-data of residential buildings, generalizing across diverse environments. The model integrates temporal data with adaptive embedding of building-specific contextual meta-data such as geographic locations and building characteristics to dynamically learn and adapt to the variations. These adaptive context embeddings allow the model to comprehensively understand how different buildings respond to environmental changes over time. Initial results show improved accuracy and reliability in indoor temperature predictions of residential buildings, demonstrating the model’s potential to optimize district heating systems across a diverse array of residential buildings. This proposed model provides a basis for developing proactive heat management systems in buildings.

This study investigates the complexities of Mixed Traffic with Fleets of Automated Vehicles (MTF-AVs) in underground mining environments characterized by confined spaces, limited visibility, and strict navigation requirements. The research focuses on integrating human-controlled vehicles into coordinated AV fleets, addressing the unpredictable interactions that arise from human behaviour. The ORU coordination framework, originally designed for a fully autonomous system, is adapted for mixed traffic scenarios to evaluate the impact of human behaviour on system efficiency and safety. Through a series of simulations, the study explores how fleet coordination algorithms adapt to human driver behaviour. These simulations demonstrate that human error and rule violations significantly reduce performance, increasing safety risks and decreasing efficiency. Findings emphasize the need for advanced coordination algorithms that dynamically adapt to unpredictable human behaviour in MTF-AVs. Such algorithms would optimize interactions between automated and human-controlled vehicles, enhancing both safety and efficiency in these complex and dynamic environments. Future research will further explore the influence of human behaviour on the coordination system and develop advanced coordination algorithms with methods to evaluate these interactions effectively.

Human-robot collaboration follows rigid processes, in order to ensure safe interactions. In case of deviations from predetermined tasks, typically, processes come to a halt. This position paper proposes a conceptual framework for intention recognition and communication, enabling a higher granularity of understanding of intentions to facilitate more efficient and safe human-robot collaboration, especially in events of deviations from expected behaviour.

This work highlights the challenge of labeling data with single-label categories, as there may be ambiguity in the assigned labels. This ambiguity arises when a data sample, which can be influenced by previous affective events is labeled with a single-label category (known as priming). Label distribution learning (LDL) is proposed as an approach to contend with the ambiguity among labels. This approach has been relatively unexplored in the field of affective computing. In this work, an experiment is designed to explore the benefits of employing LDL using specifically the SEED and SEED-V datasets. In these datasets, different emotions are induced by exposing participants to a sequence of stimuli (videoclip watching). However, these datasets provide single labels, where each data point corresponds to one affective state or emotion. Due to the lack of label distributions within existing benchmarks, label enhancement serves as a preparatory step, whose goal is to compute label distributions from the feature space and single labels before training a label distribution learning model. Experimental results show that the LDL approach reduces confusion with respect to the emotion induced in the previous trial. Distribution learning is an approach that can help to further improve the prediction of affect, which to date remains a difficult and ambiguous concept to label.

This paper presents a novel approach for predicting average indoor temperature in residential buildings, utilizing contextual factors of the rise of the building and geographical location. The proposed approach employs advanced deep learning architectures, such as Long Short-Term Memory (LSTM) and Transformers, to create generalized predictive models applicable to a range of residential buildings. The models are trained using historical data from 18 residential buildings over a period of 6 to 10 years, where the buildings are located in different climate zones. Testing is done on nine different data sets representing three different locations and three different types of buildings. The study demonstrates that incorporating the context of building rise significantly improves the models' predictive performance. Specifically, the transformer-based models show improvements in R2 of 4%-27% in a 6 h prediction horizon. The proposed approach explicitly using context information significantly improves the accuracy of predicting, making learnt models a good starting point for optimizing district heating distribution.

This paper examines the significance of the priming effect in designing and developing models for recognizing of affective states. Using a public dataset, often considered a benchmark in automatic stress recognition, the significance of the priming effect is explicated. Two experimental setups confirm the importance of task ordering in this problem. The results demonstrate the statistical significance of the model’s confusion when the subject has previously experienced stress and illustrate the importance for the Affective Computing community to develop methods to mitigate the priming effect where the order of tasks impacts how data should be modelled.

Energy optimization plays a vital role in decreasing the carbon footprint of residential buildings. In this paper, we present a prediction model of indoor temperature in residential buildings in three different case studies in different towns in Sweden. To predict the indoor temperature accurately, a dataset based on several years of data collection (up to 7 years) has been used. This paper applies both the traditional LSTM model as well as the more recent transformer model. The latter has been used because of its ability to perform a mechanism of self-attention that shows particular promise in multivariate sensor data. In addition to these algorithms, the data set is also modified based on contextual information and compared against an approach where no contextual information is used. Contextual information in this case takes into account the physical location of specific apartment units within the full residence and builds individual models based on the location of the unit. The results demonstrate that transformers are better suited for task of prediction, and that transformers combined with contextual information, provide a suitable approach for energy consumption prediction.