Research

Children’s Intuitive Theory of AI

This project, funded by the Marianne and Marcus Wallenberg Foundation (2023-2026), will explore trustworthy robots for preschoolers.

Creating Robots for Children, with Children

This Jacobs Foundation Research Fellowship (2023 - 2025) project is concerned with participatory design and automation of robots for/with children, aiming to minimise disparities in which kind of children get to benefit from socially assistive robots.

Co-Designing a Social Robot Facilitator to Boost Community Engagement with Type 2 Diabetes Prevention

This project, co-funded by the Uppsala Diabetes Research Centre and the Uppsala University Psychosocial Care Programme (U-CARE) (2022-2026) explores community-situated co-design and evaluation of a social robot based system designed to increase engagement with Type 2 Diabetes prevention within socioeconomically disadvantaged areas of Uppsala.

SymAware (Symbolic logic framework for situational awareness in mixed autonomy)

SymAware will be focused on human-in-the-loop design and automation methods for ethical and trustworthy awareness in human-robot interaction. The project is funded by Horizon Europe (2022-2025).

Robot-assisted diagnosis of women’s depression around childbirth

This project, funded by Uppsala University’s Centre for Women’s Mental Health during their Reproductive Lifespan (WoMHeR) (2021-2025), explores the use of social robots for screening of perinatal depression in women.

Deep Learning for Emotional Alignment in Human-Robot Interaction (ELECTRA)

ELECTRA aims to develop computational models for analysis of synchrony and alignment in human-human and human-robot interaction. This project is funded by the Swedish Research Council (2021-2024).

Explainable deep learning methods for human-human and human-robot interaction

This project, funded by Uppsala University’s Centre for Interdisciplinary Mathematics (2020-2024), aims at building on advances in deep learning, and in particular on the field of Explainable Artificial Intelligence (XAI), which offers approaches to increase the interpretability and explainability of the complex, highly nonlinear deep neural networks, to develop new machine learning-based methods that: (1) automatically analyse and predict alignment in human-human interaction (HHI), (2) visualize and provide interpretation of regions of focus, as well as the type of used information (e.g., face expression, eye movement, body position, etc.), in network’s decision/prediction making to aid understanding of the alignment in HHI.

The ethics and social consequences of AI & caring robots. Learning trust, empathy and accountability

It is likely that robots will soon be providing us with health and social care at different stages of our lives. For this to work, the robots must be able to build trusting relationships with people and act in a manner that is ethically acceptable. One important aspect of these relational intra-actions, and a challenge for researchers working with human-machine interaction,is therefore to program robots to behave sympathetically and accessibly. The project, funded by the Marianne and Marcus Wallenberg Foundation, is a collaboration with social science researchers at Linköping University (2020-2024).