ICS Research Seminar on "Object learning using vision and touch"
ICS Research Seminar on "Object learning using vision and touch" by Dr. Lorenzo Natale, Istituto Italiano di Tecnologia (IIT), Italy
Abstract: Robots can actively interact with the environment to learn about objects and their properties, using their sensory system. To extract structured information useful for learning, however, the robot needs to be endowed with appropriate exploratory behaviors. In the past few years, I have been working on humanoid robots to study these problems, focusing in particular on vision and touch. With my group, we have proposed techniques for active object exploration, object modeling and object recognition using haptic information (touch, proprioception and force). In particular, we have shown that object recognition can be greatly simplified using appropriate control strategies. We have also studied deep-learning methods and developed a visual system for incremental object learning in a human-robot interaction scenario. In this talk I will revise our work, showing experiments with the iCub and R1 humanoid robots.
13. April 2018, 10:00h, ICS Karlstraße 45, 2. floor, media room (library)