# Learning better generative models for dexterous, single-view grasping of novel objects

## TL;DR

This paper introduces new methods for learning dexterous grasping models from limited data, improving transfer success rates for novel objects from 55% to nearly 88% through model compression, view-based modeling, and autonomous training.

## Contribution

The paper proposes a view-based grasp model, model compression techniques, and autonomous training methods to enhance grasp transfer reliability and efficiency.

## Key findings

- Grasp transfer success increased from 55.1% to 81.6% with new methods.
- Autonomous training further improved success to 87.8%.
- 539 grasps tested on real objects demonstrate effectiveness.

## Abstract

This paper concerns the problem of how to learn to grasp dexterously, so as to be able to then grasp novel objects seen only from a single view-point. Recently, progress has been made in data-efficient learning of generative grasp models which transfer well to novel objects. These generative grasp models are learned from demonstration (LfD). One weakness is that, as this paper shall show, grasp transfer under challenging single view conditions is unreliable. Second, the number of generative model elements rises linearly in the number of training examples. This, in turn, limits the potential of these generative models for generalisation and continual improvement. In this paper, it is shown how to address these problems. Several technical contributions are made: (i) a view-based model of a grasp; (ii) a method for combining and compressing multiple grasp models; (iii) a new way of evaluating contacts that is used both to generate and to score grasps. These, together, improve both grasp performance and reduce the number of models learned for grasp transfer. These advances, in turn, also allow the introduction of autonomous training, in which the robot learns from self-generated grasps. Evaluation on a challenging test set shows that, with innovations (i)-(iii) deployed, grasp transfer success rises from 55.1% to 81.6%. By adding autonomous training this rises to 87.8%. These differences are statistically significant. In total, across all experiments, 539 test grasps were executed on real objects.