Francesco Rea
Instituto Italiano di Tecnologia (IIT )
"iCub" a shared platform for research in robotics & AIWe all hope that someday soon we will have robots to assist us in our daily lives. However, the goal of dependable assistive robotics will require the ability to function in the context of unstructured scenarios. We can understand which skills the new generation of assistive robots should exhibit by studying human-human interactions and extending these models to human-robot interaction. Most users will be familiar with a range of elementary forms of interaction. By leveraging these basic forms we can reduce the need for interactive training. In particular, these sorts of models require the mutual understanding between the human and the robot about goals and intentions. Thus the models should build on mutual communication strategies that exploit essential social signals such as affect, joint attention, direction of gaze, and turn taking.
In this talk I will present our recent achievements in social robotics and affective computing, focusing on the problem of assistive robotics in unstructured environments. Our work provides insight into problems and solutions for providing assistive robots, especially to an aging population.
Bio: Francesco Rea received an M.Sc. degree in Robotics and Automation at the University of Salford, Greater Manchester University (UK) in 2008 with distinction and a Ph.D. degree in Robotics at the University of Genoa (Italy) in 2012 contributing to different EU projects (POETICON,eMorph). He joined the Instituto Italiano di Tecnologia (IIT) Genoa in 2013 as a postdoctoral fellow to support research on the perception and cognitive modeling and human-robot interaction in the EU project DARWIN. He was also involved in the study and dynamic simulation of the human body under loads, a project in collaboration with the US Department of Defense (Natick, USA). He spent research periods at the Emergent Robotics Lab, Osaka University, and since 2016 he conducts research on robotics for the Cognitive Robotics and Human-Human Interaction Research Stream in the Robotics, Brain, and Cognitive Science Department at IIT Genoa.
In 2017, he won the Canada-Italy Innovation Award with the title "Computational Neuroscience models for auditory aware robots” aiming at providing humanoid robots with auditory awareness in collaboration with the University of Lethbridge. His main areas of interest are modeling and replication of human and humanoid perception and cognitive skills, human-robot interaction and dynamic simulation of multibody systems.
Francesco will be here with Matt Tata, Assoc. Professor from U. Lethbridge, and students. :
Matt Tata was born in Boston and grew up in northern New York State. He spent most of his early years studying classical guitar and cross-country skiing but began to take school seriously as an undergraduate student at Cornell University. Matt was initially interested in biological and environmental engineering and received a BSc in Environmental Systems Technology, but quickly turned his attention to other pursuits. After finishing his undergraduate degree, he attended a semester at Berklee College of Music in what he refers to as a futile attempt to learn to play jazz. From music school in Boston Matt headed out west to work as a ski guide and instructor near Lake Tahoe, CA. Then inspiration struck. He decided to make a clean break from the world of fast-food and moved to Canada. Matt completed MSc and Ph.D. degrees at UBC in Vancouver, BC, with most of his efforts focused on auditory and visual perception and the neuroscience of attention. While at UBC, he coached the varsity cross-country ski team and met a nice Canadian girl who, against all odds, decided he was OK enough to marry. Matt is the principal investigator of the Human Cognitive Neuroscience Lab. His group studies visual and auditory sensory systems, perception, attention, and disorders of attention, and the neurobiological basis of reward processing. They make extensive use of the Dense-Array EEG system at the CCBN Imaging Centre as well as a multi-speaker "virtual" auditory presentation system.
Presented by the AI Seminar series @UAlberta
