Detect the Correct Grasp in Mugs Using 3D Local Features
Abstract:In this paper, the problem of grasping novel objects is considered. A new approach is suggested to predict the best grasp position from RGB-D images of mugs, specifically ones that are being seen for the first time through vision. In this work, by using surface normal and curvature as the local features of the 3D point cloud, we are able to use different machine learning models which can learn from these features to predict the graspable or the non-graspable position in a mug. Experimental evaluations show tha… Show more
Set email alert for when this publication receives citations?
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.