Dans le cadre des séminaires de l'Axe transversal ROBOTIQUE, GIPSA-lab accueille Adriana TAPUS, de l'ENSTA ParisTech, spécialiste en robotique sociale. Elle donnera un séminaire exceptionnel et ouvert à tous-tes le 4 mai 2017 à 10h45 en salle Mont Blanc. Sa présentation a pour titre : Studies and Lessons Learnt in Lifelong Learning, Adaptation, and Adjustability for Personalized Human-Robot Interaction.
Robots are more and more present in our daily lives. Lately, robots have been used in human-centric environments and they have to move and navigate in cluttered and dynamic environments, to interact with humans, and to obey to some social rules so as to produce an appropriate social behavior in accordance to human's profile (i.e., personality, state of mood, and preferences) and context. Natural longitudinal human-robot interaction is still an open issue in robotics, especially with respect to lifelong learning, robot behavior adaptation, and adjustability. The personalization aspect necessitates the robot to understand the human partner. In other words, the robot adapts and adjusts its behavior to fit the user’s profile (e.g., personality, preferences, emotional state, levels of physical and/or cognitive impairment) and the task to accomplish. The purpose of this adjustment is to be in better agreement with the users and to best help them to maximize their performance in the task. In my talk, I will discuss different personalized interaction models applied for health-related applications, cooperation, and driving tasks that were developed in my lab and the some of the difficulties that we encountered and the lessons learnt.
Prof. Adriana TAPUS is Full Professor in the Robotics and Computer Vision Lab in the Computer Science and System Engineering Department, at ENSTA-ParisTech, France. In 2011, she obtained the French Habilitation (HDR) for her thesis entitled “Towards Personalized Human-Robot Interaction”. She received her PhD in Computer Science from Swiss Federal Institute of Technology Lausanne (EPFL), Switzerland in 2005 and her degree of Engineer in Computer Science and Engineering from “Politehnica'' University of Bucharest, Romania in 2001. She worked as an Associate Researcher at the University of Southern California (USC), where she was among the pioneers on the development of socially assistive robotics, also participating to activity in machine learning, human sensing, and human-robot interaction. Her main interest is on long-term learning (i.e. in particular in interaction with humans), human modeling, and on-line robot behavior adaptation to external environmental factors. Prof. Tapus is Associate Editor for International Journal of Social Robotics, Editor for IROS, General Chair for ECMR 2017, Program Chair for HRI 2018, General Chair for HRI2019, and in the steering committee of several major robotics conferences. She has more than 100 research publications and she received the Romanian Academy Award for her contributions in assistive robotics in 2010. She's also the PI of various EU and French National research grants.