RADIO: Robots in Assisted Living Environments

When: Tuesday, March 8, 2016
Where: PGH 232
Time: 5:30 PM

Speaker: Dr. Vangelis Karkaletsis and Dr. Theodoros Giannakopoulos

Host: Prof. Ioannis Kakadiaris

Remotely monitoring for early symptoms of cognitive impairment, frailty and social exclusion can help elderly people safely prolong independent living. Beneficial as it might be, such close observation can become obtrusive and stigmatizing when it necessitates the obvious presence of specialized devices. The core premise that the RADIO project validates is that the medical monitoring sensors can become an accepted part of the user’s daily and social life if they serve a dual purpose: all monitoring devices are justified by functionalities related to comfort and automation. More specifically, the project integrates home automation and mobile robotics technologies into a RADIO Home that is able to assist and monitor. For example, the robot can be made to look around for forgotten items, but it also takes measurements about walking speed, gait patterns, the time required to get off a chair; the smart home motion sensors and light switches can automatically switch the bathroom lights on and off, but also log bathroom usage and a wide range of activities of daily living.

Besides this core concept, the talk discusses technical challenges in implementing this idea and our current architecture and solutions. Some of the challenges stem from the need to justify monitoring sensors by comfort functionalities, restricting the range of devices that can be used. Related are challenges concerning usability, since the comfort functionalities also need to be usable: in the robot example, we also need a user interface that will make it easy and intuitive to actually take advantage of the functionality offered by the robot.

The recognition of ADLs (activities of daily living) along with the identification of particular mood states is achieved through multimodal signal analysis based on several sensors: colour and depth cameras, microphones and range finders. This talk also focuses on providing a general description of the adopted methodologies for multimodal event and mood recognition.

Bio:

Dr. Vangelis Karkaletsis is the head of the Software and Knowledge Engineering Laboratory (SKEL) of the Institute of Informatics and Telecommunications at NCSR "Demokritos", and responsible for the Institute's educational activities. His research interests are in the areas of Language and Knowledge Engineering, as applied to content analysis, natural language interfaces, ontology engineering. He has extensive experience in the coordination and technical management of European and national projects. He is currently site manager for the H2020 Big Data Europe project for the development of a Big Data Integrator platform, and coordinator of the H2020 Radio project on the use of robots in assisted living environments. He is also scientific manager of the H2020 project Your Data Stories on the analysis of open governmental data and their linking to social web. He has organised international workshops, conferences, summer schools. He teaches for many years at post-graduate courses on language and knowledge technologies. He is co-founder of the spin-off company ‘i-sieve Technologies’ that exploited SKEL research work on on-line content analysis. He is currently involved in the founding of the new spin-off company Newsum that exploits SKEL technology on multilingual and multi-document summarization.

Dr. Theodoros Giannakopoulos was born in Athens, Greece, in 1980. He received the Degree in Informatics and Telecommunications from the University of Athens (UOA), Athens, Greece, in 2002, the M.Sc. (Honors) Diploma in signal and image processing from the University of Patras, Patras, Greece, in 2004 and the Ph.D. degree in the department of Informatics and Telecommunications, UOA, in 2009. He is currently a Research Associate in the Institute of Informatics and Telecommunication, NCSR Demokritos. His main research interests are pattern recognition and multimedia analysis.