Submit to our RSS workshop on
New Frontiers for Deep Learning in Robotics
Come join us at #CVPR 2017 for our workshop on
Deep Learning for Robotic Vision

I am a researcher at the newly formed Australian Centre of Excellence for Robotic Vision (ACRV). My research is on Robotics and Computer Vision looking at learning and Artificial Intelligence (AI). Before joining the ACRV node in Peter Corke's lab at QUT I worked at the IDSIA Robotics Lab and received a PhD from the Università della Svizzera Italiana (USI) for my work on robotic learning for visual perception and actions on the iCub humanoid. Previously I worked on Space Security and AI at the Advanced Concepts Team of the European Space Agency. I studied Space Robotics in a Joint European Master Programme (SpaceMaster) at Aalto (TKK) and the Kiruna Space Campus (LTU). Most of my work has been published in (Space) Robotics, ML and AI conferences.

News and Current Projects

Australian Centre of Robotic Vision

The Australian Centre of Excellence for Robotic Vision will play a key role in developing the underlying science and technologies that will enable robots to see, to understand their environment using the sense of vision, and to perform useful tasks in the complex, unstructured and dynamically changing environments in which we live and work.

icVision - Robotic Vision Framework

icVision is an easy-to-use, modular framework performing computer vision related tasks in support of cognitive robotics research on the iCub humanoid robot. The system currently allows object recognition, identification and localisation. One of the main design goals is to allow rapid ...

More info

Teleoperating a Humanoid Robot

I create robots with more autonomous and more adaptive behaviours, leading to more `intelligent´ robots (video on the right). Using Machine Learning and Computer Vision, we make our robots `see', that is, we develop computer vision algorithms for object detection. On the left a first try to allow for easier control of a humanoid robot by an operator is shown.