University of Birmingham > Talks@bham > Artificial Intelligence and Natural Computation seminars > Generation of Feasible Scenes in an Ontological Framework

Generation of Feasible Scenes in an Ontological Framework

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Leandro Minku.

Host: Nick Hawes

I will describe a novel algorithm for generating potential scenes, given observations made by a mobile robot. This algorithm assumes the shape of all possible objects is known, and selects candidate shapes based on the object faces observed. Geometric constraints are then applied to eliminate impossible scenes. A key aspect of this work is the use of an ontology as the central data store for all information processing onboard the robotic platform. I will provide a brief introduction to ontologies, outline our future plans for using ontologies in robotics, and discuss KnowRob, the ontology platform we have adopted. Finally, I will describe preliminary work on sensor processing using a Kinect. This work aims to use knowledge of object construction to help identify objects by finding primitive shapes in a scene.

Speaker’s homepage: http://www.zeynsaigol.com

This talk is part of the Artificial Intelligence and Natural Computation seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Talks@bham, University of Birmingham. Contact Us | Help and Documentation | Privacy and Publicity.
talks@bham is based on talks.cam from the University of Cambridge.