Embodied Reasoning for Discovering Object Properties via Manipulation
Jan Kristof Behrens,Michal Nazarczuk,Karla Stepanova,Matej Hoffmann,Yiannis Demiris,Krystian Mikolajczyk,Jan Kristof Behrens,Michal Nazarczuk,Karla Stepanova,Matej Hoffmann,Yiannis Demiris,Krystian Mikolajczyk
In this paper, we present an integrated system that includes reasoning from visual and natural language inputs, action and motion planning, executing tasks by a robotic arm, manipulating objects, and discovering their properties. A vision to action module recognises the scene with objects and their attributes and analyses enquiries formulated in natural language. It performs multi-modal reasoning ...
