2016
Affordance-based Active Belief: Recognition using visual and manual actions
Dirk Ruiken, Jay Ming Wong, Tiffany Q. Liu, Mitchell Hebert, Takeshi Takahashi, Michael W. Lanighan +1
IROS 2016poster
This paper presents an active, model-based recognition system. It applies information theoretic measures in a belief-driven planning framework to recognize objects using the history of visual and manual interactions and to select the most informative actions. A generalization of the aspect graph is…