Improving Robotic Grasping Ability Through Deep Shape Generation

TL;DR

This paper presents a framework that generates new object shapes in a learned feature space to augment training data, significantly improving the performance of robotic grasp planning networks in simulation and real-world tests.

Contribution

It introduces a novel shape generation method in feature space to enhance dataset quality for robotic grasping, leveraging autoencoders and outlier detection.

Findings

Enhanced grasping success rates in simulation and real-world experiments.

Generated shapes with high rarity and graspness scores improve dataset diversity.

Significant performance gains over baseline methods.

Abstract

Data-driven approaches have become a dominant paradigm for robotic grasp planning. However, the performance of these approaches is enormously influenced by the quality of the available training data. In this paper, we propose a framework to generate object shapes to improve the grasping dataset quality, thus enhancing the grasping ability of a pre-designed learning-based grasp planning network. In this framework, the object shapes are embedded into a low-dimensional feature space using an AutoEncoder (encoder-decoder) based structure network. The rarity and graspness scores are defined for each object shape using outlier detection and grasp-quality criteria. Subsequently, new object shapes are generated in feature space that leverages the original high rarity and graspness score objects' features, which can be employed to augment the grasping dataset. Finally, the results obtained from the simulation and real-world experiments demonstrate that the grasping ability of the learning-based grasp planning network can be effectively improved with the generated object shapes.