Date and Time: April 24, 2020 at 1300 AEST
Title: Gaze Estimation and Perspective-Taking Mechanisms in Humans and Robots
Abstract: Humans are inherently social beings that benefit from their perceptional capability to embody another point of view. In this talk, I examine this capability, termed perspective-taking, using a mixed forward/reverse engineering approach. I first present an implementation of a bio-inspired framework that is capable of solving perspective-taking tasks on the iCub humanoid robot. One crucial component of this perspective-taking framework is estimating the human’s gaze. I introduce a gaze estimation method that not only achieves state-of-the-art performance in close distance scenarios (i.e. laptop screen viewing) but also excels in our new dataset that resembles human-robot-interactions. Furthermore, I argue that it is necessary to understand the underlying mechanisms of perspective-taking in humans. To achieve this goal, I developed a computational model that is crucial in explaining human data in a variety of experiments, and that can also be used to put forward several testable predictions. Finally, I will present some ongoing work on Visual Place Recognition at the Queensland University of Technology in collaboration with Professor Michael Milford.
Bio: Dr Tobias Fischer conducts interdisciplinary research at the intersection of computer vision, cognitive robotics and computational cognition. His main goal is to develop high-performing, bio-inspired computer vision algorithms that can be simultaneously used to examine the perceptional capabilities of animals/humans and robots. Before joining Michael Milford’s group at QUT as a Research Fellow in January 2020, Dr Fischer was a postdoctoral researcher in the Personal Robotics Lab at Imperial College London. His PhD from Imperial College (January 2019) has been awarded the UK Best Thesis in Robotics Award 2018 and the Eryl Cadwaladr Davies Prize for the best thesis in Imperial’s EEE Department in 2018. He previously received an M.Sc. degree (distinction) in Artificial Intelligence from The University of Edinburgh, in 2014, and a B.Sc. degree in Computer Engineering from Ilmenau University of Technology, Germany, in 2013.