Exploring Uncertainty and Movement in Categorical Perception Using Robots [chapter]

Nathaniel Powell, Josh Bongard
2016 Lecture Notes in Computer Science  
Cognitive agents are able to perform categorical perception through physical interaction (active categorical perception; ACP), or passively at a distance (distal categorical perception; DCP). It is possible that the former scaffolds the learning of the latter. However, it is unclear whether DCP indeed scaffolds ACP in humans and animals, nor how a robot could be trained to likewise learn DCP from ACP. Here we demonstrate a method for doing so which involves uncertainty: robots are trained to
more » ... form ACP when uncertain and DCP when certain. Furthermore, we demonstrate that robots trained in such a manner are more competent at categorizing novel objects than robots trained to categorize in other ways. This suggests that such a mechanism would also be useful for humans and animals, suggesting that they may be employing some version of this mechanism.
doi:10.1007/978-3-319-45823-6_58 fatcat:fz362hlyzvdwjbyjfrywbcndri