** Fully funded PhD position in Explainable deep learning methods for human-human and human-robot interaction**

Department of Information Technology

Uppsala University

Interested candidates should contact Prof. Ginevra Castellano by email (ginevra.castellano@it.uu.se) by Friday 13^th of March at the latest to discuss the research project.

Include the following documents in the email:

-        A CV, including list of publications (if any) and the names of two reference persons

-        Transcript of grades

-        A cover letter of maximum one page describing the scientific issues in the project that interest you and how your past experiences fit into the project

Summary of project’s topic

Human-human interaction (HHI) relies on people’s ability to mutually understand each other, often by making use of multimodal implicit signals that are physiologically embedded in human behaviour and do not require the sender’s awareness. When we are engrossed in a conversation, we align with our partner: we unconsciously mimic each other, coordinate our behaviours and synchronize positive displays of emotion. This tremendously important skill, which spontaneously develops in HHI, is currently lacking in robots.

This project 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 of the complex, highly nonlinear deep neural networks, to develop new machine learning-based methods that (1) automatically analyse and predict emotional alignment in HHI, and (2) bootstrap emotional alignment in human-robot interaction.

More information about the project can be found here.

Requirements

The ideal PhD candidate is a student with an MSc in Computer Science, Machine Learning, Artificial Intelligence, Robotics or related field with a broad mathematical knowledge as well as technical and programming skills. The components to be studied build on a number of mathematical techniques and the methods development involved in the project will require good command of the related areas; central are mathematical optimization and probability theory. Experience and/or interest in the social sciences are also required. See further eligibility requirements here.

Further information

The project is a collaboration between the Uppsala Social Robotics Lab (Prof. Ginevra Castellano) and the MIDA (Methods for Image Data Analysis) group (Dr. Joakim Lindblad) at the Department of Information Technology, and the Uppsala Child and Baby Lab (Prof. Gustaf Gredebäck) at the Department of Psychology of Uppsala University.

The student will be part of the Uppsala Social Robotics Lab at the Division of Visual Information and Interaction of the Department of Information Technology, and contribute to lab’s projects on the topic of co-adaptation in human-robot interactions. The student will also join the Graduate school of the Centre for Interdisciplinary Mathematics (CIM).

The Uppsala Social Robotics Lab’s focus is on natural interaction with social artefacts such as robots and embodied virtual agents. This domain concerns bringing together multidisciplinary expertise to address new challenges in the area of social robotics, including mutual human-robot co-adaptation, multimodal multiparty natural interaction with social robots, multimodal human affect and social behaviour recognition, multimodal expression generation, robot learning from users, behaviour personalization, effects of embodiment (physical robot versus embodied virtual agent) and other fundamental aspects of human-robot interaction (HRI). State of the art robots are used, including the Pepper, Nao and Furhat robotic platforms.

The fully funded PhD position is for four years.

--

Dr. Ginevra Castellano

Professor

Director, Uppsala Social Robotics Lab

https://usr-lab.com

Department of Information Technology

Uppsala University

Box 337, 751 05 Uppsala, Sweden

Webpage: http://user.it.uu.se/~ginca820/