Biography

Lorenzo Natale received his degree in Electronic Engineering (with honours) in 2000 and Ph.D. in Robotics in 2004 from the University of Genoa. He was later postdoctoral researcher at the MIT Computer Science and Artificial Intelligence Laboratory. He was invited professor at the University of Genova where he taught the courses of Natural and Artificial Systems and Antropomorphic Robotics for students of the Bioengineering curriculum. At the moment he is Tenure-Track Researcher at the IIT. In the past ten years Lorenzo Natale worked on various humanoid platforms. He was one of the main contributors to the design and development of the iCub platform and he has been leading the development of the iCub software architecture and the YARP middleware. His research interests range from vision and tactile sensing to software architectures for robotics. He contributed more than one hundred papers on international conferences and journals. He served as Program Chair of ICDL-Epirob 2014 and HAI 2017 and has been associate editor of international conferences (RO-MAN, ICDL-Epirob, Humanoids, ICRA) and journals (IEEE RA-L, IJHR, IJARS and the Humanoid Robotics specialty of frontiers in Robotics and AI).

Abstract

Object learning using vision and touch

Robots can actively interact with the environment to learn about objects and their properties. To extract structured information useful for learning, however, the robots need to be endowed with appropriate exploratory  behaviors.

In the past few years I have been working on the iCub humanoid robot to study these problems, focusing on vision and touch to guide the exploration of objects and train objet recognition systems. 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 these 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 various, recent, experiments with the iCub humanoid robot.