Object grasping is a key task in robot manipulation. Performing a grasp largely depends on
the object properties and grasp constraints. This paper proposes a new statistical relational
learning approach to recognize graspable points in object point clouds. We characterize
each point with numerical shape features and represent each cloud as a (hyper-) graph by
considering qualitative spatial relations between neighboring points. Further, we use kernels
on graphs to exploit extended contextual shape information and compute discriminative …

… using SRL, we build a graph-based representation of the object exploiting both local
numerical features and higher-level information about the structure of the object — extended
contextual shape information of the object. we contribute a relational kernel-based approach
to numerical feature pooling for robot grasping: for each descriptor of the object point, our
relational kernel exploits extended contextual information by pooling numerical shape features …