"Robots can help improve our emotional well-being"

"As a researcher, it's been fascinating to see the progress that Artificial Intelligence (AI) has made in the last 10 years. Fifteen years ago, it was difficult to imagine that AI would be as advanced as it is today," said Agata Lapedriza, a member of the Faculty of Computer Science, Multimedia and Telecommunications at the Universitat Oberta de Catalunya (UOC) and leader of AIWELL (AI for Human Well-being), a research group attached to the UOC's eHealth Center that conducts research on artificial intelligence focused on health and well-being. AIWELL evolved from the SUNAI (Scene Understanding and Artificial Intelligence Lab) research group, which was active for 10 years at the UOC. The group is made up of 16 members (5 faculty members, 7 doctoral students, 1 Postdoc and 4 intern master’s degree students).

AIWELL's lines of research include areas such as computer vision – giving machines the ability to "see" –, natural language processing, people-centred perception, deep learning, explainable artificial intelligence and trust and ethics in AI (fairness in AI).

Although they may seem like different disciplines, in reality "they're all connected," said Lapedriza, who is also a researcher affiliated with the MIT Media Lab in Boston, where she carries out part of her work. One of the applications of computer vision to health is the recognition of emotions, "a very complex task for a machine, but which is an essential capability for machines that have to interact with people, such as robots or virtual assistants". It is hoped that in the future this technology can be applied to make communication between robots and humans smoother, and that, for example, robots will be better able to assist people or detect when they need help and send a warning. The work of Lapedriza and her team focuses on improving the computational models used by robots to perceive emotions, personality traits, intentions, and so on. 

"We can apply our research to the detection of stress or the creation of technologies that help us improve our well-being. One of our projects studies the design of robots that help improve emotional well-being. Robots could provide information on positive psychology and teach techniques to better manage your emotions," explained the researcher.

In the field of social robotics, AIWELL collaborates with the Hospital Sant Joan de Déu. One of the projects is to develop a robotic car to reduce the stress of children who have to undergo an operation in the hospital. It’s a smart car that interacts with the children during the journey to the operating theatre and helps them to relax. The research also involved MIT, Hyundai (which made this promotional video) and Affective.

Explainability and fairness in artificial intelligence

Another line of research is the explainability of artificial intelligence in the field of medical imaging. "It's essential to make sure that a diagnosis made by a machine is reliable and, therefore, it must be able to give explanations of why it has reached a certain conclusion. Explainability is very important to know whether or not we are to believe a diagnosis," said the researcher.

In this field, AIWELL works in collaboration with Hospital Vall d'Hebron, an initiative promoted by David Masip, an AIWELL researcher and member of the Faculty of Computer Science, Multimedia and Telecommunications. In addition, the group is in the process of establishing new alliances with other healthcare organizations to work in new areas of research, for example early detection of mental illness and patient follow-up through the analysis of behavioural data related to technology. "Changes in the way a person interacts with technology can be indicators of the onset of a mental health problem. For example, if we talk less on the phone and stay at home more, this could be a sign that we're isolating ourselves, and isolation may be indicative of the onset of depression," explained Lapedriza.

Addressing the criticism that artificial intelligence often receives of having unethical biases and behaviours, the UOC researcher responds that there is a certain distrust because the media and science fiction films and books often show "the bad side of AI". "They show the cases where AI systems are unreliable. It's true that there are bias problems, and there are currently many measures to discover and mitigate these biases. However, we mustn't lose sight of the fact that there are a large number of situations in which AI works and is very useful." In addition, she said, "there's a technical ignorance of how these AI systems work and what exactly they do, and this understandably generates mistrust."

To counteract the possible bias in the technology, initiatives are being taken to ensure that AI is developed responsibly and for the good of humanity. For example, the topic of fairness in AI is present in more and more conferences and many bachelor's degree programmes offer courses on ethics in AI, explained Lapedriza.

The eHealth Center, the academic centre for digital health

The eHealth Center is an academic centre that is open to the world. Its goal is to educate and empower citizens and professionals, through the use of technology, and to lead a paradigm shift in health. It is people-centred, using research, education and guidance to contribute to society's progress and well-being.

^{UOC R&I} 

^{The UOC's research and innovation (R&I) is helping overcome pressing challenges faced by global societies in the 21st century, by studying interactions between technology and human & social sciences with a specific focus on the network society, e-learning and e-health.} 

^{Over 500 researchers and 52 research groups work among the University's seven faculties and two research centres: the Internet Interdisciplinary Institute (IN3) and the eHealth Center (eHC).}

^{The University also cultivates online learning innovations at its eLearning Innovation Center (eLinC), as well as UOC community entrepreneurship and knowledge transfer via the Hubbik platform.}

^{The United Nations' 2030 Agenda for Sustainable Development and open knowledge serve as strategic pillars for the UOC's teaching, research and innovation. More information: research.uoc.edu #UOC25years}