In my talk I will first present a tool chain for handling 3D object models in robotic applications. Objects are modelled either on a turntable or in a human's hand (tentative results here) and models are generated for recognition and 6DOF pose estimation as well as real-time 6DOF object tracking. Recognition puts an emphasis on handling difficult cluttered scenes with occlusions by employing a multi-hypothesis verification framework. I will demonstrate hands-on usage in ROS. Furthermore I will talk about a particular project, RALLI, where we are using the above techniques in a setting where a humanoid Robot (a Pepper) is to learn action verbs and their meanings from a human demonstrator.
Michael Zillich is a postdoctoral researcher in the field of robot vision, which integrates machine vision methods such as object segmentation, recognition and tracking into robotic control architectures. He holds a PhD in Electrical Engineering from Vienna University of Technology (2007) and a diploma in Mechatronics from Johannes Kepler University Linz (1998). He spent 6 months during his PhD studies at KTH Stockholm in 2000, and was a postdoctoral researcher at the University of Birmingham 2006 - 2008. Having returned back to ACIN/TU Wien, he was principal investigator in EU project CogX and coordinated FWF project InSitu. He was further involved in national project FWF NFN Cognitive Vision and EU projects RobVision, ActIPret and CoSy. He is currently coordinating EU project SQUIRREL and is principal investigator WWTF project RALLI. Michael Zillich is (co)-author of over 90 publications and served on the program committees of a number of international conferences and as reviewer for international journals. In 2013, together with ACIN colleague Walter Wohlkinger, he founded Blue Danube Robotics, a company dedicated to safe human robot collaboration in industrial and home environments.