Learning dexterous grasps that generalize to novel objects by combining hand and contact models

We show how a robot learns grasps for high-DOF hands that generalize to novel objects, given as little as one demonstrated grasp. During grasp learning two types of probability density are learned that model the demonstrated grasp. The first density type (the contact model) models the relationship of an individual finger part to local surface features at its contact point. The second density type (the hand configuration model) models the whole hand configuration during the approach to grasp.