Pieter Wolfert obtained his Master’s degree in Artificial Intelligence in 2018 at Radboud University, Nijmegen - The Netherlands. He wrote his thesis on ‘Online engagement prediction in child-robot interaction’ at Tilburg University, where he was part of the European funded L2TOR project. In his thesis he used machine learning techniques to design a data driven model that would be capable of capturing the engagement of children with a robot in a child-robot tutoring task. Currently he is a PhD student at Ghent University supervised by Prof. Tony Belpaeme, where his focus is on social robotics and machine learning (co-supervisor Prof. Francis wyffels). As a PhD student he is a member of IDLab, a research group embedded in Ghent University and imec. He is funded by FWO.
At this moment, my focus is on improving the evaluation methods that are used within the field of co-speech gesture generation. Nowadays, co-speech gestures for embodied conversational agents (say virtual agents and robots) are generated using models that are trained on human motion data. These models rely on machine learning, and objective metrics are used in both the training phase and evaluation phase of these models. When we want to use the generated nonverbal behaviour of these models in virtual agents and social robots, it is crucial to have user tests with human participants, and to not just rely on the outcomes of objective metrics. For this evaluation phase, we rely on subjective methods, as nonverbal behavior is inherently subjective. Improving subjective evaluation strategies will lead to improved generation of nonverbal behaviour, such that these generation models can be used to drive nonverbal behaviour in virtual agents and social robots.