AI-powered Advanced Perception for Social Robots

8 luglio 2024
Orario di inizio 
Polo Ferrari 2 - Via Sommarive 9, Povo (Trento)
Room B108
Comunità universitaria
Ingresso libero
Dipartimento Ingegneria Industriale
Antonio Paolillo, IDSIA, Dalle Molle Institute for Artificial Intelligence - Lugano

Service robots can provide a smoother interaction experience if they can comprehend the surroundings and predict the nearby users' intentions. In this way, robots can proactively enact friendly behaviors that lead to an improved user experience. This talk presents how we tackle this complex perception task using machine learning techniques to detect potential users' intention to interact. We explore different classification approaches, using different sets of features considering the behavior of the people moving in the social space of the robot—the tests with real robots deployed into the wild show the potential of the proposed perception algorithms.


Antonio Paolillo is Researcher at Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI, in Lugano (Switzerland) and responsible for the activities in rehabilitation robotics and social human-robot interaction of the "Autonomous Robotics" research area at IDSIA. He received his Ph.D. in System Engineering from Sapienza University of Rome, Italy (2015). He was a post-doc at EPFL, Lausanne, Switzerland (2019-2020); Idiap Research Institute, Martigny, Switzerland (2018-2019); CNRS-University of Montpellier, France (2015-2017). He visited the CNRS-AIST Joint Robotics Laboratory of Tsukuba, Japan (2015), CNRS-University of Montpellier, France (2014), and Örebro University, Sweden (2014). In 2015, he participated in the DARPA Robotics Challenge as a member of the AIST-NEDO team. He is Associate Editor for IEEE Robotics and Automation Letters (RA-L), and Ubiquitous Robots (UR) 2024, and for the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) from 2021 to 2023. He is a PI of the European project SERMAS and is involved in other Swiss projects. He is the Chair of the 17th International Workshop on Human-Friendly Robotics (HFR 2024).

PDF icon Poster (PDF | 592 KB)