Deep Dexterous Grasping of Novel Objects from a Single View
This addresses the open problem of robotic dexterous grasping for novel objects from limited visual input, with incremental improvements in architecture and evaluation.
The paper tackled the problem of dexterous grasping of novel objects from a single view by developing a simulator, dataset, and generative-evaluative architectures, achieving a grasp success rate improvement from 69.53% to 90.49% in simulation and 87.8% on real robots compared to a 57.1% baseline.
Dexterous grasping of a novel object given a single view is an open problem. This paper makes several contributions to its solution. First, we present a simulator for generating and testing dexterous grasps. Second we present a data set, generated by this simulator, of 2.4 million simulated dexterous grasps of variations of 294 base objects drawn from 20 categories. Third, we present a basic architecture for generation and evaluation of dexterous grasps that may be trained in a supervised manner. Fourth, we present three different evaluative architectures, employing ResNet-50 or VGG16 as their visual backbone. Fifth, we train, and evaluate seventeen variants of generative-evaluative architectures on this simulated data set, showing improvement from 69.53% grasp success rate to 90.49%. Finally, we present a real robot implementation and evaluate the four most promising variants, executing 196 real robot grasps in total. We show that our best architectural variant achieves a grasp success rate of 87.8% on real novel objects seen from a single view, improving on a baseline of 57.1%.