Hybrid Intelligence (2020-)
Hybrid Intelligence (HI) is the combination of human and machine intelligence, expanding human intellect instead of replacing it. HI takes human expertise and intentionality into account when making meaningful decisions and perform appropriate actions, together with ethical, legal and societal values. Our goal is to design Hybrid Intelligent systems, an approach to Artificial Intelligence that puts humans at the centre, changing the course of the ongoing AI revolution. Within this project, I'm directly involved with the following PhD projects as daily supervisor: Alignment dialogues to understand people's support needs (1.14), Multimodal modeling of trust (3.13) and the following as external co-supervisor: AI for moral education (1.1), Knowledge representation for HI (1.26), Interactive dialogues for Logic-based AI (3.2), Justification in Human-AI teams (3.22). See the HI website for more details on these projects and publications.
AI*MAN Lab: Transparent & Traceable AI in Human-AI Teamwork (2020- )
In this interdisciplinary research line, in which the faculties of AE (Control and Simulation Section) and EEMCS (Intelligent Systems Department) cooperate, we will focus on human-AI teamwork. The main challenges of human-AI teamwork include obtaining mutual understanding among the teammates while making optimal decisions to realize the team's global objectives. Within this project, I'm interested in mutual trust among human and AI teammates. Both how explanations influence a human's trust in AI in different settings, and how AI can use trust to understand people in a teamwork context.
Modelling Trust (2020-2024)
AI systems are increasingly involved in decision making, either supporting people or autonomously. This also means that how much we trust these systems becomes increasingly important. Our trust in AI should be appropriate, not to much, and not too little. For any system to calibrate trust to be appropriate, it first needs to understand what trust is. In this project, we look at how we can formally capture trust and reason with it from an AI perspective, but also at how well these formalisms capture actual trust in human-AI interactions. Link to doctoral dissertation by Siddharth Mehrotra, associated with this project.
We are in this Together (2022-2024)
The goal of this short SIOP research project was to comprehensively investigate trust dynamics in human-AI teams, considering both interpersonal trust and team trust within a multidisciplinary framework. By integrating knowledge from Industrial and Organizational Psychology, Human Factors Engineering, Human-Computer Interaction, and Computer Science, we provide various empirical insights, develop a theoretical model, and present practical implications for designing and implementing trust reasoning in AI teammates.
CoreSAEP (2017-2020)
The aim of this project was to develop a new computational reasoning framework for Socially Adaptive Electronic Partners (SAEPs) that support people in their daily lives without people having to adapt their way of living to the software. This will require software that is flexible so that it can adapt to diverse and evolving rules of behavior (norms) of people in unforeseen circumstances. Within this project, I worked on the question of how we can formalize norms and values such that a SAEP could understand these and support people better.
VESP (2013-2017)
The Virtual E-coaching and Storytelling technology for Post-traumatic stress disorder (VESP) project looked at a home-therapy for PTSD patients where they can follow therapy at home. As this is challenging, we studied how a virtual agent could assist and motivate PTSD patients during therapy. The main focus lay on how the possibilities of the software can be used to provide personalized support and motivation. Link to doctoral dissertation associated with this project.
Aliz-e (2012-2013)
The Aliz-e project concerned a robot as companion and teacher for children with diabetes. In this project, I studied how emotional engagement could be modeled in the robot to support the interaction between robot and child. Link to Msc. thesis associated with this project.