NAVER LABS Europe seminars are open to the public. This seminar is virtual and requires registration.
Date: 11th May 2021, 4:00 pm (GMT +01.00)
Towards embodied intelligence
Speaker: Roberto Calandra is a Research Scientist at Facebook AI Research. Previously, he was a Postdoctoral Scholar at the University of California, Berkeley (US) in the Berkeley Artificial Intelligence Research Laboratory (BAIR). His education includes a Ph.D. from TU Darmstadt (Germany), a M.Sc. in Machine Learning and Data Mining from the Aalto university (Finland), and a B.Sc. in Computer Science from the Università degli studi di Palermo (Italy). His scientific interests are broadly at the conjunction of Decision-making, Robotics and Machine Learning. Research topics that he is currently developing include Model-based Reinforcement Learning, Tactile Sensing, Morphology Adaptation, and Bayesian Optimization. He has also been Program Chair for AISTATS 2020, Guest Editor for the JMLR special issue on Bayesian Optimization, and co-organized over a dozen workshops at international conferences (Neurips, ICML, ICLR, RSS, etc).
Abstract: The creation of intelligent embodied artificial agents has long been a dream for roboticists and artificial intelligence researchers alike. In this talk, I will argue for several key advances that I believe are necessary before we can achieve this dream. Specifically, I will present our contributions to two of these key research areas: multi-modal sensing, and data-efficient learning for fast adaptation. Regarding multi-modal sensing, I will discuss the importance of using alternative sensor modalities in addition to vision and will present our recent research on using touch sensing to allow robots to perceive, understand, and interact with the world around them. On the topic of data-efficient learning, I will discuss the use of model-based reinforcement learning — which explicitly creates explainable models of the world — and present some of our recent works to understand and overcome the limitations of current approaches.