← Search

Takeshi Takahashi

2 accepted papers

2018

Intrinsically Motivated Self-Supervised Deep Sensorimotor Learning for Grasping

IROS 2018poster

Deep learning has been successful in a variety of applications that have high-dimensional state spaces such as object recognition, video games, and machine translation. Deep neural networks can automatically learn important features from high-dimensional state given large training datasets. However,…

Cited by 1SourceScholar
2016

Affordance-based Active Belief: Recognition using visual and manual actions

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…

Cited by 12SourceScholar