Dexterous grasping of novel objects from a single view

In this thesis, a novel generative-evaluative method was proposed to solve the problem of dexterous grasping of the novel object with a single view. The generative model is learned from human demonstration. The grasps generated by the generative model are used to train the evaluative model. Two novel evaluative network architectures are proposed. The evaluative model is a deep evaluative network that is trained in the simulation. The generative-evaluative method is tested in a real grasp data set with 49 previously unseen challenging objects. The generative-evaluative method achieves a success rate of 78% that outperforms the purely generative method, that has a success rate of 57%. The thesis provides insights into the strengths and weaknesses of the generative-evaluative method by comparing different deep network architectures