About the project

Objective
The project envisions a mobile cyber-physical system where people carrying mobile sensors (e.g., smartphones, smartcards) generate large amounts of trajectory data to sense and monitor human interactions with physical and social environments. The project aims to develop a causal artificial intelligence (AI) methodology to analyze and model human mobility behaviour dynamics (decision-making) using individual travel trajectory data and develop the causal diagrams of human mobility behaviour under disturbances that could help design effective strategies for sustainable and resilient urban mobility systems. The research challenges are learning the complex ‘hidden’ human decision-making mechanism from pervasive ‘observed’ trajectories and developing effective, scalable causal AI models and algorithms.

Background
The ever-changing mobility landscape and climate change continue challenging existing operating models and the responsiveness of city planners, policymakers, and regulators. City authorities have growing investment needs that require more focused operations and management strategies that align mobility portfolios to societal goals. The project targets the root cause of traffic (human) and novel analytic techniques to learn and predict human mobility behaviour dynamics from pervasive mobile sensing data that can help cities meet both sustainability challenges (through predicting congestion, emissions, and energy consumption) and improve urban resilience to disruptive events (such as infrastructure failures, natural disasters, or pandemics).

The human mobility area witnessed active developments in two broad but separate fields: transport and computer science. They work with different data, use different methods, and answer different but overlapping questions, i.e., mobility behaviour modelling using ‘small’ data in transport and mobility pattern analysis using ‘big’ data in computer science. A solid bridge between these is beneficial and needed but is still an open challenge. Mobile sensing and information technology have enabled us to collect much mobility trajectory data from human decision-makers. The predictive AI techniques show the potential to learn and predict human mobility using these trajectory data efficiently. However, they continually run up against the limits of what they observe (correlations, not causal relationships), thus hindering any serious applicability for preparedness and response policies for cities without understanding the causal mobility dynamics.

cAIMBER will bridge the two human mobility research streams in Transport Science and Computer Science. Also, it will develop the causal AI methodology, merging the RL and Causal Inference research fields. Integrating interdisciplinary expertise and techniques will derive generalizable insights about human behaviour dynamics that contribute to the scientific communities’ theoretical conceptualization of travel choices and decision-making mechanisms. Practically, cAIMBER conducts extensive empirical analysis using a comprehensive dataset covering different types of system disturbances for seven years. The accumulated knowledge of human mobility under these situational contexts would help city planners and service operators to make more informed decisions for sustainable and resilient travel.

Crossdisciplinary collaboration
The researchers in the team represent the KTH School of Architecture and Built Environment (ABE), Civil and Architectural Engineering Department, Transport Planning Division and KTH School of Engineering Science (SCI), Mathematics Department, Mathematics for Data and AI Division. Strategic research partners at KTH iMobility Lab and MIT Transit Lab support the project.

Watch the recorded presentation at the Digitalize in Stockholm 2023 event:

About the project

Objective
Digital humans and AI are becoming an integrated part of society. Modern chatbots such as GPT3 (Generative Pre-trained Transformer 3) have shown a remarkable capability of generating human-like responses and may even be prompted to act sarcastic, depressed or shy. To bring such systems into an embodied agent, such as a digital human, the agent’s body motion should reflect the same psychological inner state. This is, however, lacking in modern synthesis systems of non-verbal behaviours, which only generate generic motion based on a neutral speaker.

In this project, we propose to enhance virtual agents’ state of the art by giving them a psychological inner state that colours their nonverbal behaviour. We term these agents artificial actors – virtual digital humans that can take directions and produce expressive and convincing acting behaviour, much like a real actor takes instructions from a director. This means that it should be possible to instruct a character not only what to do or talk about but also how these actions should be performed (e.g. as a shy person with social phobia).

The project includes

• A) recording a large database of acted behaviours containing a range of psychological states
• B) developing probabilistic generative methods to synthesize gestures from such high-level traits and,
• C) developing a psychological, cognitive model guiding the synthesis.

We will specifically create a virtual agent simulating a therapy patient and evaluate its performance with therapists or therapists in training.

Background
To be announced

Crossdisciplinary collaboration
The researchers in the team represent the School of Electrical Engineering and Computer Science, KTH and the Psychology Department at Stockholm University.

About the project

Objective
This project aims to combine magnetic resonance elastography (MRE) and advanced diffusion magnetic resonance imaging (dMRI) to develop the next generation of MRE methods to improve the biomechanical characterization of brain tissue.

More specifically, A) we will propose computational models that consider the diffusion processes to estimate biomechanical properties of the brain at a sub-voxel level and B) we will use advanced dMRI data to predict biomechanical properties without the expensive equipment required by MRE.

We will apply these new methods to data we are acquiring from Parkinson’s disease (PD) and cancer patients and healthy subjects and test their potential to improve the diagnosis and treatment of patients and to characterize biomechanical changes during ageing.

Background
Neurological disorders affect millions of persons worldwide. While MRI is crucial in clinical diagnostics, it is largely limited to morphological features. Understanding how the mechanical properties of tissues change due to disease can give valuable information for improving their early detection and diagnosis. A promising tool for non-invasively estimating these mechanical properties through magnetic resonance imaging (MRI) is Magnetic Resonance Elastography (MRE). The current MRE methods generate limited mechanical information about the brain tissue at a relatively low image resolution. The proposed methods will provide a better mechanical characterization of tissues for improved diagnosis. Moreover, using additional MRI modalities, we can better understand the mechanism behind the changes in mechanical properties due to diseases. This can eventually lead to better treatments for patients. MRE for the brain is only available in a few sites worldwide. In Autumn 2022, the KTH-owned MRI scanner became the first one in Sweden capable of performing MRE examinations in the brain.

Crossdisciplinary collaboration
In this project, we are establishing a new cross-disciplinary and complementary collaboration:

• Lisa Prahl Wittberg, Prof. in Multiphase flows / Fluid mechanics at the Department of Engineering Mechanics at KTH, is an expert in developing computational models to understand better the underlying processes of complex fluids in the human body.
• Rodrigo Moreno, Assoc. Prof. in Biomedical Imaging at KTH is an expert in using advanced AI applied to medical images. His group is currently involved in all projects in Sweden that use MRE for the brain.
• Christian Gasser, Prof. in tissue mechanics at KTH Mechanical Engineering, provides his expertise in the constitutive modelling of tissues needed in the project.
• Christoffer Olsson, a postdoc recruited for the previous phase of the project, will remain one of the key persons for developing the methods in this project.
• The data of this project is being collected in collaboration with Assoc. Prof. Armita Golkar from Stockholm Univ (SU), and Prof. Per Svenningsson, Assoc. Prof. Grégoria Kalpouzos and Assoc. Prof. Anna Falck Delgado from Karolinska Institute (KI).

About the project

Objective
The aim of this project is to analyse the environmental impacts of increased digitalization and the use of Information and Communication Technologies. The project can include both method development and case studies. The impacts will be analysed using life cycle assessment and life cycle thinking. Case studies can vary on different scales and include specific devices, applications and sectoral assessments. Initially, the focus will be on climate impacts and energy use, but it may also be broadened to a larger spectrum of environmental impacts. Assessments will include the direct impacts of ICT but also different types of indirect impacts, including rebound effects.

Background
The ICT sector has an environmental footprint. The future development of this footprint is debated, and it is important that the discussions have a scientific basis. Digitalisation may be a tool for reducing environmental impacts. By improving efficiencies and dematerialising products and services, new ICT applications can reduce the footprints of other sectors. More studies are, however, needed in order to understand when this actually leads to decreased impacts and when there is a risk for indirect rebound effects that increase use and footprints. Environmental life cycle assessment is a standardised method for assessing potential environmental impacts of products, services and functions “from the cradle to the grave”, i.e. from the extraction of raw materials via production and uses to waste management. It is used for analysing the environmental footprints, i.e. the direct impacts, of ICT. It can also be used for analysing different types of indirect effects.

Partner Postdocs
After working in the industry on large-scale refrigeration and heat pump systems and as an entrepreneur with solar pumps, Shoaib Azizi undertook a master’s program in Sustainable Energy Engineering at KTH. He moved to Umeå in northern Sweden for a multi-disciplinary PhD project on energy-efficient renovation of buildings. His PhD included research on the opportunities for digital tools to improve management and energy efficiency in buildings. He defended his thesis “A multi-method Assessment to Support Energy Efficiency Decisions in Existing Residential and Academic Buildings” in September 2021. Now Shoaib is a Digital Futures Postdoc researcher in digitalization and climate impacts at the Department of Sustainable Development, Environmental Science and Engineering (SEED) at KTH. His research involves lifecycle assessment methodology to understand various aspects of digitalization and its impacts on the environment.

Anna Furberg defended her PhD thesis in 2020 at Chalmers University of Technology. Her thesis, titled “Environmental, Resource and Health Assessments of Hard Materials and Material Substitution: The Cases of Cemented Carbide and Polycrystalline Diamond”, involved Life Cycle Assessment (LCA) case studies and method development. After her thesis, she worked at the Norwegian Institute for Sustainability Research, NORSUS, on various LCA projects and, in several cases, as the project leader. In 2022, she was awarded the SETAC Europe Young Scientist Life Cycle Assessment Award, which recognizes exceptional achievements by a young scientist in the field of LCA. Anna has a Digital Futures Postdoc position in digitalization and climate impacts at the Department of Sustainable Development, Environmental Science and Engineering (SEED) at KTH.

Supervisor
Göran Finnveden is a Professor of Environmental Strategic Analysis at the Department of Sustainable Development, Environmental Sciences and Engineering at KTH. He is also the director of the Mistra Sustainable Consumption research program. His research is focused on sustainable consumption and life cycle assessment, and other sustainability assessment tools. The research includes method development and case studies in different areas, including the environmental impacts of ICT.

About the project

Objective
The main objective of this project is to improve the productivity of two packaging lines within the SweOps Steriles function, as measured by Overall Equipment Effectiveness (OEE) and competence in line staffing. We aim to achieve the objective by enabling next-best-action decision support for front-line operators.

Background
Modern pharmaceutical packaging lines are complex systems with multiple intricate physical and digital components. Operators gain domain expertise through extended exposure and interaction with the systems. They see, touch, and listen to the operating parts of the system. With time, they develop deep procedural knowledge and reach the level where they can predict when the physical systems need maintenance. How do they do this? This is the basic question of the project SMART: Smart Predictive Maintenance for the Pharmaceutical Industry, a collaboration between AstraZeneca and KTH.

Our approach deploys three pillars: 1) sensor networks in manufacturing, 2) machine learning predictive models, and 3) interactive immersive and contextual visualizations. We will observe and interview expert operators to acquire their procedural knowledge and focus on the sensing and machine learning tools to produce a rich sensor-based predictive model that we visualize peripherally in the plant and immersively to the operators. The project aims to enhance the operators’ abilities to perform predictive maintenance and expedite the transfer of these skills to novice operators via novel digital tools.

Partner Postdoc
Tianzhi Li

Main supervisor
Lihui Wang, Professor and Chair of Sustainable Manufacturing at KTH

Co-supervisors
Jan Kronqvist, Assistant Professor at KTH
Ming Xiao, Associate Professor, Division of ISE at KTH EECS
Mario Romero, Associate professor at KTH EECS School, Division of Computational Science and Technology

Watch the recorded presentation at the Digitalize in Stockholm 2023 event:

Background and summary of fellowship
Behaviour Trees (BTs) represent a hierarchical way of combining low-level controllers for different tasks into high-level controllers for more complex tasks. The key advantages of BTs have been shown to include the following:

• Recursive structure: The BT is a rooted tree and at every edge of that tree, the interface between the parent and the subtree is the same, centred around a return status of either Success, Failure or Running.
• Modularity: Due to the recursive structure, a complex subtree can be seen as a single leaf, and vice versa. This enables the encapsulation of complexity.
• Transparency: The recursive structure of BTs makes them human-readable. You can always look at a BT and see why it is executing a particular behaviour. This fact in combination with the modularity described above enables a user to understand complex BTs by analyzing one subtree at a time.
• An efficient tool for human system design: BTs were created by computer game programmers to make their life easier when creating complex AI designs. Modularity is a well-known tool to handle complexity, and transparency is vital in any human design.
• An efficient tool for automated design. The modular recursive structure simplifies automated design.
• A structure that enables formal analysis of safety and convergence. Formal analysis of convergence and region of attraction is enabled by the modular recursive structure.

In this project, we will use the properties of BTs listed above to synthesize controllers that combine the efficiency of reinforcement learning with formal performance guarantees such as safety and convergence to a designated goal area.

Background and summary of fellowship
Reinforcement Learning (RL) is concerned with learning efficient control policies for systems with unknown dynamics and reward functions. RL plays an increasingly important role in a large spectrum of application domains including online platforms (recommender systems and search engines), robotics, and self-driving vehicles. Over the last decade, RL algorithms, combined with modern function approximators such as deep neural networks, have shown unprecedented performance and have been able to solve very complex sequential decision tasks better than humans. Yet, these algorithms are lacking robustness, and are most often extremely data inefficient.

This research project aims at contributing to the theoretical foundations for the design of data-efficient and robust RL algorithms. To this aim, we develop a fundamental two-step process:

1. We characterize information-theoretical limits for the performance of RL algorithms (in terms of sample complexity, i.e., data efficiency)
2. We leverage these limits to guide the design of optimal RL algorithms, algorithms approaching the fundamental performance limits