Conference: 'Continuous Learning in Robotics'

In the Department of Intelligent and Interactive Systems (IIS) at the University of Innsbruck, our motto is "Making robots learn to perceive and act with understanding." My work applies to different fields, such as vision and robotics. Robots deployed in unstructured real-world environments will inevitably face new tasks and challenges over time, which will require capabilities that cannot be entirely foreseen at the outset. Robots capable of learning from demonstrations can significantly benefit from the added ability to learn new movement skills without forgetting what they have learned in the past. In this talk, I will present my work on the continuous learning of trajectories from demonstrations using hypernetworks.

About the speaker

Antonio Rodríguez-Sánchez is currently an associate professor in the Intelligent and Interactive Systems (IIS) group of the Department of Computer Science at the University of Innsbruck (Austria). In 2010, he completed his Ph.D. at the Vision Research Centre (York University, Toronto, Canada) on modeling attention and intermediate areas of the visual cortex, under the supervision of Professor John K. Tsotsos (Canada Research Chair in Computational Vision). His current research interests encompass various areas of artificial intelligence: computational neuroscience, deep neural networks, computer vision, machine learning, and robotics.